var bibbase_data = {"data":"\"Loading..\"\n\n
\n\n \n\n \n\n \n \n\n \n\n \n \n\n \n\n \n
\n generated by\n \n \"bibbase.org\"\n\n \n
\n \n\n
\n\n \n\n\n
\n\n Excellent! Next you can\n create a new website with this list, or\n embed it in an existing web page by copying & pasting\n any of the following snippets.\n\n
\n JavaScript\n (easiest)\n
\n \n <script src=\"https://bibbase.org/show?bib=https%3A%2F%2Ffolk.ntnu.no%2Fstaal%2Fdist%2Fmypubs.bib&jsonp=1&jsonp=1\"></script>\n \n
\n\n PHP\n
\n \n <?php\n $contents = file_get_contents(\"https://bibbase.org/show?bib=https%3A%2F%2Ffolk.ntnu.no%2Fstaal%2Fdist%2Fmypubs.bib&jsonp=1\");\n print_r($contents);\n ?>\n \n
\n\n iFrame\n (not recommended)\n
\n \n <iframe src=\"https://bibbase.org/show?bib=https%3A%2F%2Ffolk.ntnu.no%2Fstaal%2Fdist%2Fmypubs.bib&jsonp=1\"></iframe>\n \n
\n\n

\n For more details see the documention.\n

\n
\n
\n\n
\n\n This is a preview! To use this list on your own web site\n or create a new web site from it,\n create a free account. The file will be added\n and you will be able to edit it in the File Manager.\n We will show you instructions once you've created your account.\n
\n\n
\n\n

To the site owner:

\n\n

Action required! Mendeley is changing its\n API. In order to keep using Mendeley with BibBase past April\n 14th, you need to:\n

    \n
  1. renew the authorization for BibBase on Mendeley, and
    2. \n
  2. update the BibBase URL\n in your page the same way you did when you initially set up\n this page.\n
    3. \n
\n

\n\n

\n \n \n Fix it now\n

\n
\n\n
\n\n\n
\n \n \n
\n
\n  \n 2022\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Differential Privacy for Symmetric Log-Concave Mechanisms.\n \n \n \n \n\n\n \n Vinterbo, S. A.\n\n\n \n\n\n\n In Proceedings of the 25th International Conference on Artificial Intelligence and Statistics (AISTATS), volume 151, of Proceedings of Machine Learning Research, March 2022. PMLR\n \n\n\n\n
\n\n\n\n \n \n \"DifferentialPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{vinterboDifferentialPrivacySymmetric2022,\n  title = {Differential Privacy for Symmetric Log-Concave Mechanisms},\n  booktitle = {Proceedings of the 25th International Conference on Artificial Intelligence and Statistics ({{AISTATS}})},\n  author = {Vinterbo, S. A.},\n  year = {2022},\n  month = mar,\n  series = {Proceedings of Machine Learning Research},\n  volume = {151},\n  publisher = {{PMLR}},\n  url = {https://arxiv.org/abs/2202.11393}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2021\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n A Closed Form Scale Bound for the ($ε$, $δ$)-Differentially Private Gaussian Mechanism Valid for All Privacy Regimes.\n \n \n \n \n\n\n \n Vinterbo, S. A.\n\n\n \n\n\n\n 2021.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@misc{vinterbo2021closed,\n  title = {A Closed Form Scale Bound for the ({$\\epsilon$}, {$\\delta$})-Differentially Private {{Gaussian Mechanism}} Valid for All Privacy Regimes},\n  author = {Vinterbo, Staal A.},\n  year = {2021},\n  eprint = {2012.10523},\n  eprinttype = {arxiv},\n  primaryclass = {cs.CR},\n  url = {https://arxiv.org/abs/2012.10523},\n  archiveprefix = {arXiv}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Hvorfor er personvern så vanskelig?.\n \n \n \n \n\n\n \n Vinterbo, S. A.\n\n\n \n\n\n\n In Den digitale hverdagen, pages 147–157. John Grieg Forlag, Trondheim, 1. edition, 2021.\n \n\n\n\n
\n\n\n\n \n \n \"HvorforPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@incollection{vinterboHvorforErPersonvern2021,\n  title = {{Hvorfor er personvern s\\aa{} vanskelig?}},\n  booktitle = {{Den digitale hverdagen}},\n  author = {Vinterbo, Staal A.},\n  year = {2021},\n  edition = {1.},\n  pages = {147--157},\n  publisher = {{John Grieg Forlag}},\n  address = {{Trondheim}},\n  url = {https://www.ntva.no/for-publisering/hero-artikkel/den-digitale-hverdagen/},\n  isbn = {978-82-533-0400-7},\n  langid = {norsk}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2019\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n An Open Access Medical Knowledge Base for Community Driven Diagnostic Decision Support System Development.\n \n \n \n \n\n\n \n Müller, L.; Gangadharaiah, R.; Klein, S. C.; Perry, J.; Bernstein, G.; Nurkse, D.; Wailes, D.; Graham, R.; El-Kareh, R.; Mehta, S.; Vinterbo, S. A.; and Aronoff-Spencer, E.\n\n\n \n\n\n\n BMC Medical Informatics and Decision Making, 19(1): 93. April 2019.\n \n\n\n\n
\n\n\n\n \n \n \"AnPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{muller_open_2019,\n  title = {An Open Access Medical Knowledge Base for Community Driven Diagnostic Decision Support System Development},\n  author = {M{\\"u}ller, Lars and Gangadharaiah, Rashmi and Klein, Simone C. and Perry, James and Bernstein, Greg and Nurkse, David and Wailes, Dustin and Graham, Rishi and {El-Kareh}, Robert and Mehta, Sanjay and Vinterbo, Staal A. and {Aronoff-Spencer}, Eliah},\n  year = {2019},\n  month = apr,\n  journal = {BMC Medical Informatics and Decision Making},\n  volume = {19},\n  number = {1},\n  pages = {93},\n  issn = {1472-6947},\n  doi = {10.1186/s12911-019-0804-1},\n  url = {https://doi.org/10.1186/s12911-019-0804-1},\n  urldate = {2019-09-02},\n  abstract = {While early diagnostic decision support systems were built around knowledge bases, more recent systems employ machine learning to consume large amounts of health data. We argue curated knowledge bases will remain an important component of future diagnostic decision support systems by providing ground truth and facilitating explainable human-computer interaction, but that prototype development is hampered by the lack of freely available computable knowledge bases.},\n  file = {/Users/staal/Documents/Zotero/storage/JER7B7GI/Müller et al. - 2019 - An open access medical knowledge base for communit.pdf;/Users/staal/Documents/Zotero/storage/2UXQ8SRC/s12911-019-0804-1.html}\n}\n\n
\n
\n\n\n
\n While early diagnostic decision support systems were built around knowledge bases, more recent systems employ machine learning to consume large amounts of health data. We argue curated knowledge bases will remain an important component of future diagnostic decision support systems by providing ground truth and facilitating explainable human-computer interaction, but that prototype development is hampered by the lack of freely available computable knowledge bases.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Trust and Expectations of Researchers and Public Health Departments for the Use of HIV Molecular Epidemiology.\n \n \n \n \n\n\n \n Schairer, C. E.; Mehta, S. R.; Vinterbo, S. A.; Hoenigl, M.; Kalichman, M.; and Little, S. J.\n\n\n \n\n\n\n AJOB Empirical Bioethics, 10(3): 201–213. August 2019.\n \n\n\n\n
\n\n\n\n \n \n \"TrustPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{schairer_trust_2019-1,\n  title = {Trust and {{Expectations}} of {{Researchers}} and {{Public Health Departments}} for the {{Use}} of {{HIV Molecular Epidemiology}}},\n  author = {Schairer, Cynthia E. and Mehta, Sanjay R. and Vinterbo, Staal A. and Hoenigl, Martin and Kalichman, Michael and Little, Susan J.},\n  year = {2019},\n  month = aug,\n  journal = {AJOB Empirical Bioethics},\n  volume = {10},\n  number = {3},\n  pages = {201--213},\n  issn = {2329-4515},\n  doi = {10.1080/23294515.2019.1601648},\n  url = {https://doi.org/10.1080/23294515.2019.1601648},\n  urldate = {2019-09-02},\n  abstract = {Background: Molecular epidemiology (ME) is a technique used to study the dynamics of pathogen transmission through a population. When used to study HIV infections, ME generates powerful information about how HIV is transmitted, including epidemiologic patterns of linkage and, potentially, transmission direction. Thus, ME raises challenging questions about the most responsible way to protect individual privacy while acquiring and using these data to advance public health and inform HIV intervention strategies. Here, we report on stakeholders' expectations for how researchers and public health agencies might use HIV ME. Methods: We conducted in-depth semistructured interviews with 40 key stakeholders to find out how these individuals respond to the proposed risks and benefits of HIV ME. Transcripts were coded and analyzed using Atlas.ti. Expectations were assessed through analysis of responses to hypothetical scenarios designed to help interviewees think through the implications of this emerging technique in the contexts of research and public health. Results: Our analysis reveals a wide range of imagined responsibilities, capabilities, and trustworthiness of researchers and public health agencies. Specifically, many respondents expect researchers and public health agencies to use HIV ME carefully and maintain transparency about how data will be used. Informed consent was discussed as an important opportunity for notification of privacy risks. Furthermore, some respondents wished that public health agencies were held to the same form of oversight and accountability represented by informed consent in research. Conclusions: To prevent HIV ME from becoming a barrier to testing or a source of public mistrust, the sense of vulnerability expressed by some respondents must be addressed. In research, informed consent is an obvious opportunity for this. Without giving specimen donors a similar opportunity to opt out, public health agencies may find it difficult to adopt HIV ME without deterring testing and treatment.},\n  pmid = {31050604},\n  keywords = {genetics,HIV,molecular epidemiology,privacy},\n  file = {/Users/staal/Documents/Zotero/storage/XVZUPP24/23294515.2019.html}\n}\n\n
\n
\n\n\n
\n Background: Molecular epidemiology (ME) is a technique used to study the dynamics of pathogen transmission through a population. When used to study HIV infections, ME generates powerful information about how HIV is transmitted, including epidemiologic patterns of linkage and, potentially, transmission direction. Thus, ME raises challenging questions about the most responsible way to protect individual privacy while acquiring and using these data to advance public health and inform HIV intervention strategies. Here, we report on stakeholders' expectations for how researchers and public health agencies might use HIV ME. Methods: We conducted in-depth semistructured interviews with 40 key stakeholders to find out how these individuals respond to the proposed risks and benefits of HIV ME. Transcripts were coded and analyzed using Atlas.ti. Expectations were assessed through analysis of responses to hypothetical scenarios designed to help interviewees think through the implications of this emerging technique in the contexts of research and public health. Results: Our analysis reveals a wide range of imagined responsibilities, capabilities, and trustworthiness of researchers and public health agencies. Specifically, many respondents expect researchers and public health agencies to use HIV ME carefully and maintain transparency about how data will be used. Informed consent was discussed as an important opportunity for notification of privacy risks. Furthermore, some respondents wished that public health agencies were held to the same form of oversight and accountability represented by informed consent in research. Conclusions: To prevent HIV ME from becoming a barrier to testing or a source of public mistrust, the sense of vulnerability expressed by some respondents must be addressed. In research, informed consent is an obvious opportunity for this. Without giving specimen donors a similar opportunity to opt out, public health agencies may find it difficult to adopt HIV ME without deterring testing and treatment.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2018\n \n \n (4)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Differentially Private Continual Release of Graph Statistics.\n \n \n \n \n\n\n \n Song, S.; Little, S.; Mehta, S.; Vinterbo, S.; and Chaudhuri, K.\n\n\n \n\n\n\n arXiv:1809.02575 [cs]. September 2018.\n \n\n\n\n
\n\n\n\n \n \n \"DifferentiallyPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n\n\n\n
\n 
@article{song_differentially_2018,\n  title = {Differentially {{Private Continual Release}} of {{Graph Statistics}}},\n  author = {Song, Shuang and Little, Susan and Mehta, Sanjay and Vinterbo, Staal and Chaudhuri, Kamalika},\n  year = {2018},\n  month = sep,\n  journal = {arXiv:1809.02575 [cs]},\n  eprint = {1809.02575},\n  eprinttype = {arxiv},\n  primaryclass = {cs},\n  url = {http://arxiv.org/abs/1809.02575},\n  urldate = {2018-09-22},\n  abstract = {Motivated by understanding the dynamics of sensitive social networks over time, we consider the problem of continual release of statistics in a network that arrives online, while preserving privacy of its participants. For our privacy notion, we use differential privacy -- the gold standard in privacy for statistical data analysis. The main challenge in this problem is maintaining a good privacy-utility tradeoff; naive solutions that compose across time, as well as solutions suited to tabular data either lead to poor utility or do not directly apply. In this work, we show that if there is a publicly known upper bound on the maximum degree of any node in the entire network sequence, then we can release many common graph statistics such as degree distributions and subgraph counts continually with a better privacy-accuracy tradeoff. Code available at https://bitbucket.org/shs037/graphprivacycode},\n  archiveprefix = {arXiv},\n  keywords = {Computer Science - Cryptography and Security,Computer Science - Data Structures and Algorithms},\n  file = {/Users/staal/Documents/Zotero/storage/VHT9IBD4/Song et al. - 2018 - Differentially Private Continual Release of Graph .pdf;/Users/staal/Documents/Zotero/storage/RU7LW3ZX/1809.html}\n}\n\n
\n
\n\n\n
\n Motivated by understanding the dynamics of sensitive social networks over time, we consider the problem of continual release of statistics in a network that arrives online, while preserving privacy of its participants. For our privacy notion, we use differential privacy – the gold standard in privacy for statistical data analysis. The main challenge in this problem is maintaining a good privacy-utility tradeoff; naive solutions that compose across time, as well as solutions suited to tabular data either lead to poor utility or do not directly apply. In this work, we show that if there is a publicly known upper bound on the maximum degree of any node in the entire network sequence, then we can release many common graph statistics such as degree distributions and subgraph counts continually with a better privacy-accuracy tradeoff. Code available at https://bitbucket.org/shs037/graphprivacycode\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Simple Algorithm for Estimating Distribution Parameters from N-Dimensional Randomized Binary Responses.\n \n \n \n \n\n\n \n Vinterbo, S. A.\n\n\n \n\n\n\n In Information Security: 20th International Conference, ISC 2018, London (Guilford), UK, September 9-11, 2018, Proceedings, of Lecture Notes in Computer Science, London (Guilford), UK, September 2018. Springer\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@inproceedings{vinterbo_simple_2018-1,\n  title = {A Simple Algorithm for Estimating Distribution Parameters from N-Dimensional Randomized Binary Responses},\n  booktitle = {Information {{Security}}: 20th {{International Conference}}, {{ISC}} 2018, {{London}} ({{Guilford}}), {{UK}}, {{September}} 9-11, 2018, {{Proceedings}}},\n  author = {Vinterbo, Staal A.},\n  year = {2018},\n  month = sep,\n  series = {Lecture {{Notes}} in {{Computer Science}}},\n  eprint = {1803.03981},\n  eprinttype = {arxiv},\n  publisher = {{Springer}},\n  address = {{London (Guilford), UK}},\n  url = {http://arxiv.org/abs/1803.03981},\n  urldate = {2018-03-20},\n  abstract = {Randomized response for privacy protection is attractive as provided disclosure control can be quantified by means such as differential privacy. However, recovering statistics involving multiple dependent binary attributes can be difficult, posing a barrier to the use of randomized response for privacy protection. In this work, we identify a family of randomizers for which we are able to present a simple and efficient algorithm for obtaining unbiased maximum likelihood estimates for k-way marginal distributions from the randomized data. We also provide theoretical bounds on the statistical efficiency of these estimates, allowing the assessment of sample sizes for these randomizers. The identified family consists of randomizers generated by an iterated Kronecker product of an invertible and bisymmetric 2 x 2 matrix. This family includes modes of Google's Rappor randomizer, as well as applications of two well-known classical randomized response methods: Warner's original method, and Simmons' unrelated question method. We find that randomizers in this family can also be considered to be equivalent to each other with respect to the efficiency -- differential privacy tradeoff. Importantly, the estimation algorithm is simple to implement, an aspect critical to technologies for privacy protection and security.},\n  archiveprefix = {arXiv},\n  copyright = {All rights reserved},\n  keywords = {Computer Science - Cryptography and Security},\n  file = {/Users/staal/Documents/Zotero/storage/Y6XVSXIQ/Vinterbo - 2018 - A simple algorithm for estimating distribution par.pdf;/Users/staal/Documents/Zotero/storage/LUYR6JX9/1803.html}\n}\n\n
\n
\n\n\n
\n Randomized response for privacy protection is attractive as provided disclosure control can be quantified by means such as differential privacy. However, recovering statistics involving multiple dependent binary attributes can be difficult, posing a barrier to the use of randomized response for privacy protection. In this work, we identify a family of randomizers for which we are able to present a simple and efficient algorithm for obtaining unbiased maximum likelihood estimates for k-way marginal distributions from the randomized data. We also provide theoretical bounds on the statistical efficiency of these estimates, allowing the assessment of sample sizes for these randomizers. The identified family consists of randomizers generated by an iterated Kronecker product of an invertible and bisymmetric 2 x 2 matrix. This family includes modes of Google's Rappor randomizer, as well as applications of two well-known classical randomized response methods: Warner's original method, and Simmons' unrelated question method. We find that randomizers in this family can also be considered to be equivalent to each other with respect to the efficiency – differential privacy tradeoff. Importantly, the estimation algorithm is simple to implement, an aspect critical to technologies for privacy protection and security.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n The Tension between Anonymity and Privacy.\n \n \n \n \n\n\n \n Vinterbo, S. A.\n\n\n \n\n\n\n In NISK 2018, May 2018. \n \n\n\n\n
\n\n\n\n \n \n \"ThePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 8 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{vinterbo_tension_2018,\n  title = {The Tension between Anonymity and Privacy},\n  booktitle = {{{NISK}} 2018},\n  author = {Vinterbo, Staal A.},\n  year = {2018},\n  month = may,\n  url = {https://folk.ntnu.no/staal/dist/pubs/nisk2018final.pdf},\n  abstract = {Privacy in the context of information and data is often defined in terms of anonymity, particularly in regulations such as the GDPR. Operationally, it is appealing to define privacy in terms of computable data properties as this makes it possible to verify compliance. A well known example of privacy defined as such is k-anonymity. At the same time, uncertainty regarding real-world privacy is increasing with the amount of data collected about us all. We present arguments for why focusing on anonymity or computable properties of data is not very helpful in this regard. In particular, we count exploitable failures of privacy defined in terms of computable properties of n-bit data and conclude that these counterexamples to protection cannot be rare.}\n}\n\n
\n
\n\n\n
\n Privacy in the context of information and data is often defined in terms of anonymity, particularly in regulations such as the GDPR. Operationally, it is appealing to define privacy in terms of computable data properties as this makes it possible to verify compliance. A well known example of privacy defined as such is k-anonymity. At the same time, uncertainty regarding real-world privacy is increasing with the amount of data collected about us all. We present arguments for why focusing on anonymity or computable properties of data is not very helpful in this regard. In particular, we count exploitable failures of privacy defined in terms of computable properties of n-bit data and conclude that these counterexamples to protection cannot be rare.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Parallel Feature Selection Using Only Counts.\n \n \n \n \n\n\n \n Vinterbo, S. A; and Que, J.\n\n\n \n\n\n\n In NIK 2018, May 2018. \n \n\n\n\n
\n\n\n\n \n \n \"ParallelPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{vinterboParallelFeatureSelection2018,\n  title = {Parallel {{Feature Selection Using Only Counts}}},\n  booktitle = {{{NIK}} 2018},\n  author = {Vinterbo, Staal A and Que, Jialan},\n  year = {2018},\n  month = may,\n  url = {https://folk.ntnu.no/staal/dist/pubs/nik2018final.pdf},\n  abstract = {Count queries belong to a class of summary statistics routinely used in basket analysis, inventory tracking, and study cohort finding. In this article, we demonstrate how it is possible to use simple count queries for parallelizing sequential data mining algorithms. Specifically, we parallelize a published algorithm for finding minimum sets of discriminating features and demonstrate that the parallel speedup is close to the expected optimum.}\n}\n\n
\n
\n\n\n
\n Count queries belong to a class of summary statistics routinely used in basket analysis, inventory tracking, and study cohort finding. In this article, we demonstrate how it is possible to use simple count queries for parallelizing sequential data mining algorithms. Specifically, we parallelize a published algorithm for finding minimum sets of discriminating features and demonstrate that the parallel speedup is close to the expected optimum.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2017\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Perceptions of Molecular Epidemiology Studies of HIV among Stakeholders.\n \n \n \n \n\n\n \n Schairer, C.; and others\n\n\n \n\n\n\n Journal of Public Health Research, 6(3). December 2017.\n \n\n\n\n
\n\n\n\n \n \n \"PerceptionsPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{schairer_perceptions_2017-2,\n  title = {Perceptions of Molecular Epidemiology Studies of {{HIV}} among Stakeholders},\n  author = {Schairer, Cynthia and {others}},\n  year = {2017},\n  month = dec,\n  journal = {Journal of Public Health Research},\n  volume = {6},\n  number = {3},\n  issn = {2279-9036},\n  doi = {10.4081/jphr.2017.992},\n  url = {http://www.jphres.org/index.php/jphres/article/view/992},\n  urldate = {2018-02-15},\n  abstract = {Background: Advances in viral sequence analysis make it possible to track the spread of infectious pathogens, such as HIV, within a population. When used to study HIV, these analyses (i.e., molecular epidemiology) potentially allow inference of the identity of individual research subjects. Current privacy standards are likely insufficient for this type of public health research. To address this challenge, it will be important to understand how stakeholders feel about the benefits and risks of such research. Design and Methods: To better understand perceived benefits and risks of these research methods, in-depth qualitative interviews were conducted with HIV-infected individuals, individuals at high-risk for contracting HIV, and professionals in HIV care and prevention. To gather additional perspectives, attendees to a public lecture on molecular epidemiology were asked to complete an informal questionnaire. Results: Among those interviewed and polled, there was near unanimous support for using molecular epidemiology to study HIV. Questionnaires showed strong agreement about benefits of molecular epidemiology, but diverse attitudes regarding risks. Interviewees acknowledged several risks, including privacy breaches and provocation of anti-gay sentiment. The interviews also demonstrated a possibility that misunderstandings about molecular epidemiology may affect how risks and benefits are evaluated. Conclusions: While nearly all study participants agree that the benefits of HIV molecular epidemiology outweigh the risks, concerns about privacy must be addressed to ensure continued trust in research institutions and willingness to participate in research.},\n  copyright = {Copyright (c) 2017 Cynthia Schairer, Sanjay Mehta, Staal A Vinterbo, Martin Hoenigl, Michael Kalichman, Susan Little},\n  langid = {english},\n  keywords = {HIV,molecular epidemiology,privacy,qualitative interviews,research ethics},\n  file = {/Users/staal/Documents/Zotero/storage/J5ZQHJMX/Schairer et al. - 2017 - Perceptions of molecular epidemiology studies of H.pdf;/Users/staal/Documents/Zotero/storage/Q4FBRT9P/992.html}\n}\n\n
\n
\n\n\n
\n Background: Advances in viral sequence analysis make it possible to track the spread of infectious pathogens, such as HIV, within a population. When used to study HIV, these analyses (i.e., molecular epidemiology) potentially allow inference of the identity of individual research subjects. Current privacy standards are likely insufficient for this type of public health research. To address this challenge, it will be important to understand how stakeholders feel about the benefits and risks of such research. Design and Methods: To better understand perceived benefits and risks of these research methods, in-depth qualitative interviews were conducted with HIV-infected individuals, individuals at high-risk for contracting HIV, and professionals in HIV care and prevention. To gather additional perspectives, attendees to a public lecture on molecular epidemiology were asked to complete an informal questionnaire. Results: Among those interviewed and polled, there was near unanimous support for using molecular epidemiology to study HIV. Questionnaires showed strong agreement about benefits of molecular epidemiology, but diverse attitudes regarding risks. Interviewees acknowledged several risks, including privacy breaches and provocation of anti-gay sentiment. The interviews also demonstrated a possibility that misunderstandings about molecular epidemiology may affect how risks and benefits are evaluated. Conclusions: While nearly all study participants agree that the benefits of HIV molecular epidemiology outweigh the risks, concerns about privacy must be addressed to ensure continued trust in research institutions and willingness to participate in research.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2014\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Structural Basis for Translational Surveillance by the Large Ribosomal Subunit-Associated Protein Quality Control Complex.\n \n \n \n \n\n\n \n Lyumkis, D.; dos Passos, D. O.; Tahara, E. B.; Webb, K.; Bennett, E. J.; Vinterbo, S.; Potter, C. S.; Carragher, B.; and Joazeiro, C. A. P.\n\n\n \n\n\n\n Proceedings of the National Academy of Sciences, 111(45): 15981–15986. November 2014.\n \n\n\n\n
\n\n\n\n \n \n \"StructuralPaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{lyumkis_structural_2014,\n  title = {Structural Basis for Translational Surveillance by the Large Ribosomal Subunit-Associated Protein Quality Control Complex},\n  author = {Lyumkis, Dmitry and dos Passos, Dario Oliveira and Tahara, Erich B. and Webb, Kristofor and Bennett, Eric J. and Vinterbo, Staal and Potter, Clinton S. and Carragher, Bridget and Joazeiro, Claudio A. P.},\n  year = {2014},\n  month = nov,\n  journal = {Proceedings of the National Academy of Sciences},\n  volume = {111},\n  number = {45},\n  pages = {15981--15986},\n  issn = {0027-8424, 1091-6490},\n  doi = {10.1073/pnas.1413882111},\n  url = {http://www.pnas.org/content/111/45/15981},\n  urldate = {2016-01-11},\n  abstract = {All organisms have evolved mechanisms to manage the stalling of ribosomes upon translation of aberrant mRNA. In eukaryotes, the large ribosomal subunit-associated quality control complex (RQC), composed of the listerin/Ltn1 E3 ubiquitin ligase and cofactors, mediates the ubiquitylation and extraction of ribosome-stalled nascent polypeptide chains for proteasomal degradation. How RQC recognizes stalled ribosomes and performs its functions has not been understood. Using single-particle cryoelectron microscopy, we have determined the structure of the RQC complex bound to stalled 60S ribosomal subunits. The structure establishes how Ltn1 associates with the large ribosomal subunit and properly positions its E3-catalytic RING domain to mediate nascent chain ubiquitylation. The structure also reveals that a distinguishing feature of stalled 60S particles is an exposed, nascent chain-conjugated tRNA, and that the Tae2 subunit of RQC, which facilitates Ltn1 binding, is responsible for selective recognition of stalled 60S subunits. RQC components are engaged in interactions across a large span of the 60S subunit surface, connecting the tRNA in the peptidyl transferase center to the distally located nascent chain tunnel exit. This work provides insights into a mechanism linking translation and protein degradation that targets defective proteins immediately after synthesis, while ignoring nascent chains in normally translating ribosomes.},\n  copyright = {All rights reserved},\n  langid = {english},\n  pmid = {25349383},\n  keywords = {cryo-EM,listerin/Ltn1 E3 ubiquitin ligase,protein quality control,Tae2/Nemf,translational surveillance},\n  file = {/Users/staal/Documents/Zotero/storage/G9CBM8VH/Lyumkis et al. - 2014 - Structural basis for translational surveillance by.pdf;/Users/staal/Documents/Zotero/storage/FTN55JHP/15981.html}\n}\n\n
\n
\n\n\n
\n All organisms have evolved mechanisms to manage the stalling of ribosomes upon translation of aberrant mRNA. In eukaryotes, the large ribosomal subunit-associated quality control complex (RQC), composed of the listerin/Ltn1 E3 ubiquitin ligase and cofactors, mediates the ubiquitylation and extraction of ribosome-stalled nascent polypeptide chains for proteasomal degradation. How RQC recognizes stalled ribosomes and performs its functions has not been understood. Using single-particle cryoelectron microscopy, we have determined the structure of the RQC complex bound to stalled 60S ribosomal subunits. The structure establishes how Ltn1 associates with the large ribosomal subunit and properly positions its E3-catalytic RING domain to mediate nascent chain ubiquitylation. The structure also reveals that a distinguishing feature of stalled 60S particles is an exposed, nascent chain-conjugated tRNA, and that the Tae2 subunit of RQC, which facilitates Ltn1 binding, is responsible for selective recognition of stalled 60S subunits. RQC components are engaged in interactions across a large span of the 60S subunit surface, connecting the tRNA in the peptidyl transferase center to the distally located nascent chain tunnel exit. This work provides insights into a mechanism linking translation and protein degradation that targets defective proteins immediately after synthesis, while ignoring nascent chains in normally translating ribosomes.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Ensuring Privacy in the Study of Pathogen Genetics.\n \n \n \n\n\n \n Mehta, S. R.; Vinterbo, S. A.; and Little, S. J.\n\n\n \n\n\n\n The Lancet. Infectious Diseases, 14(8): 773–777. August 2014.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{mehta_ensuring_2014-1,\n  title = {Ensuring Privacy in the Study of Pathogen Genetics},\n  author = {Mehta, Sanjay R. and Vinterbo, Staal A. and Little, Susan J.},\n  year = {2014},\n  month = aug,\n  journal = {The Lancet. Infectious Diseases},\n  volume = {14},\n  number = {8},\n  pages = {773--777},\n  issn = {1474-4457},\n  doi = {10.1016/S1473-3099(14)70016-7},\n  abstract = {Rapid growth in the genetic sequencing of pathogens in recent years has led to the creation of large sequence databases. This aggregated sequence data can be very useful for tracking and predicting epidemics of infectious diseases. However, the balance between the potential public health benefit and the risk to personal privacy for individuals whose genetic data (personal or pathogen) are included in such work has been difficult to delineate, because neither the true benefit nor the actual risk to participants has been adequately defined. Existing approaches to minimise the risk of privacy loss to participants are based on de-identification of data by removal of a predefined set of identifiers. These approaches neither guarantee privacy nor protect the usefulness of the data. We propose a new approach to privacy protection that will quantify the risk to participants, while still maximising the usefulness of the data to researchers. This emerging standard in privacy protection and disclosure control, which is known as differential privacy, uses a process-driven rather than data-centred approach to protecting privacy.},\n  copyright = {All rights reserved},\n  langid = {english},\n  pmcid = {PMC4111774},\n  pmid = {24721230},\n  keywords = {Biomedical Research,Communicable Diseases,Confidentiality,Databases; Factual,Humans}\n}\n\n
\n
\n\n\n
\n Rapid growth in the genetic sequencing of pathogens in recent years has led to the creation of large sequence databases. This aggregated sequence data can be very useful for tracking and predicting epidemics of infectious diseases. However, the balance between the potential public health benefit and the risk to personal privacy for individuals whose genetic data (personal or pathogen) are included in such work has been difficult to delineate, because neither the true benefit nor the actual risk to participants has been adequately defined. Existing approaches to minimise the risk of privacy loss to participants are based on de-identification of data by removal of a predefined set of identifiers. These approaches neither guarantee privacy nor protect the usefulness of the data. We propose a new approach to privacy protection that will quantify the risk to participants, while still maximising the usefulness of the data to researchers. This emerging standard in privacy protection and disclosure control, which is known as differential privacy, uses a process-driven rather than data-centred approach to protecting privacy.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2013\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n A Stability-based Validation Procedure for Differentially Private Machine Learning.\n \n \n \n \n\n\n \n Chaudhuri, K.; and Vinterbo, S. A.\n\n\n \n\n\n\n In NIPS, 2013. \n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Chaudhuri2013,\n  title = {A {{Stability-based Validation Procedure}} for {{Differentially Private Machine Learning}}},\n  booktitle = {{{NIPS}}},\n  author = {Chaudhuri, Kamalika and Vinterbo, Staal A.},\n  year = {2013},\n  url = {http://papers.nips.cc/paper/5014-a-stability-based-validation-procedure-for-differentially-private-machine-learning.pdf},\n  copyright = {All rights reserved},\n  owner = {staal}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Optimod - An Automated Approach for Constructing and Optimizing Initial Models for Single-Particle Electron Microscopy.\n \n \n \n\n\n \n Lyumkis, D.; Vinterbo, S. A.; Potter, C. S.; and Carragher, B.\n\n\n \n\n\n\n Journal of Structural Biology, 184(3): 417–426. 2013.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Lyumkis2013,\n  title = {Optimod - {{An Automated Approach}} for {{Constructing}} and {{Optimizing Initial Models}} for {{Single-Particle Electron Microscopy}}},\n  author = {Lyumkis, Dmitry and Vinterbo, Staal A. and Potter, Clinton S. and Carragher, Bridget},\n  year = {2013},\n  journal = {Journal of Structural Biology},\n  volume = {184},\n  number = {3},\n  pages = {417--426},\n  doi = {10.1016/j.jsb.2013.10.009},\n  copyright = {All rights reserved},\n  owner = {staal}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2012\n \n \n (3)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n iDASH: Integrating Data for Analysis, Anonymization, and Sharing.\n \n \n \n\n\n \n Ohno-Machado, L.; Bafna, V.; Boxwala, A. A.; Chapman, B. E.; Chapman, W. W.; Chaudhuri, K.; Day, M. E.; Farcas, C.; Heintzman, N. D.; Jiang, X.; Kim, H.; Kim, J.; Matheny, M. E.; Resnic, F. S.; and Vinterbo, S. A.\n\n\n \n\n\n\n J Am Med Inform Assoc, 19(2): 196–201. 2012.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{ohno-machado_idash_2012,\n  title = {{{iDASH}}: Integrating Data for Analysis, Anonymization, and Sharing},\n  shorttitle = {{{iDASH}}},\n  author = {{Ohno-Machado}, Lucila and Bafna, Vineet and Boxwala, Aziz A. and Chapman, Brian E. and Chapman, Wendy Webber and Chaudhuri, Kamalika and Day, Michele E. and Farcas, Claudiu and Heintzman, Nathaniel D. and Jiang, Xiaoqian and Kim, Hyeoneui and Kim, Jihoon and Matheny, Michael E. and Resnic, Frederic S. and Vinterbo, Staal A.},\n  year = {2012},\n  journal = {J Am Med Inform Assoc},\n  volume = {19},\n  number = {2},\n  pages = {196--201},\n  doi = {10.1136/amiajnl-2011-000538},\n  aauthor = {Ohno-Machado, Lucila and Bafna, Vineet and Boxwala, Aziz A and Chapman, Brian E and Chapman, Wendy W and Chaudhuri, Kamalika and Day, Michele E and Farcas, Claudiu and Heintzman, Nathaniel D and Jiang, Xiaoqian and Kim, Hyeoneui and Kim, Jihoon and Matheny, Michael E and Resnic, Frederic S and Vinterbo, Staal A},\n  abstract = {iDASH (integrating data for analysis, anonymization, and sharing) is the newest National Center for Biomedical Computing funded by the NIH. It focuses on algorithms and tools for sharing data in a privacy-preserving manner. Foundational privacy technology research performed within iDASH is coupled with innovative engineering for collaborative tool development and data-sharing capabilities in a private Health Insurance Portability and Accountability Act (HIPAA)-certified cloud. Driving Biological Projects, which span different biological levels (from molecules to individuals to populations) and focus on various health conditions, help guide research and development within this Center. Furthermore, training and dissemination efforts connect the Center with its stakeholders and educate data owners and data consumers on how to share and use clinical and biological data. Through these various mechanisms, iDASH implements its goal of providing biomedical and behavioral researchers with access to data, software, and a high-performance computing environment, thus enabling them to generate and test new hypotheses.},\n  copyright = {All rights reserved},\n  noissn = {1527-974X},\n  nomonth = {nov},\n  owner = {staal},\n  pmid = {22081224}\n}\n\n
\n
\n\n\n
\n iDASH (integrating data for analysis, anonymization, and sharing) is the newest National Center for Biomedical Computing funded by the NIH. It focuses on algorithms and tools for sharing data in a privacy-preserving manner. Foundational privacy technology research performed within iDASH is coupled with innovative engineering for collaborative tool development and data-sharing capabilities in a private Health Insurance Portability and Accountability Act (HIPAA)-certified cloud. Driving Biological Projects, which span different biological levels (from molecules to individuals to populations) and focus on various health conditions, help guide research and development within this Center. Furthermore, training and dissemination efforts connect the Center with its stakeholders and educate data owners and data consumers on how to share and use clinical and biological data. Through these various mechanisms, iDASH implements its goal of providing biomedical and behavioral researchers with access to data, software, and a high-performance computing environment, thus enabling them to generate and test new hypotheses.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Protecting Count Queries in Study Design.\n \n \n \n\n\n \n Vinterbo, S. A.; Sarwate, A. D.; and Boxwala, A.\n\n\n \n\n\n\n J Am Med Inform Assoc, 19(5): 750–7. 2012.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Vinterbo2012,\n  title = {Protecting {{Count Queries}} in {{Study Design}}},\n  author = {Vinterbo, Staal A. and Sarwate, Anand D. and Boxwala, Aziz},\n  year = {2012},\n  journal = {J Am Med Inform Assoc},\n  volume = {19},\n  number = {5},\n  pages = {750--7},\n  doi = {10.1136/amiajnl-2011-000459},\n  copyright = {All rights reserved},\n  owner = {staal},\n  pmid = {22511018},\n  file = {/Users/staal/Documents/Zotero/storage/4GP8X7F6/Vinterbo2012Count.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Differentially Private Projected Histograms: Construction and Use for Prediction.\n \n \n \n \n\n\n \n Vinterbo, S. A.\n\n\n \n\n\n\n In Proceedings of ECML-PKDD 2012, September 24-28, Bristol UK., volume 7524, of Lecture Notes in Artificial Intelligence Series (LNAI), pages 19–34, 2012. Springer Verlag\n \n\n\n\n
\n\n\n\n \n \n \"DifferentiallyPaper\n  \n \n \n \"DifferentiallyLink\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 2 downloads\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Vinterbo2012a,\n  title = {Differentially {{Private Projected Histograms}}: {{Construction}} and {{Use}} for {{Prediction}}},\n  booktitle = {Proceedings of {{ECML-PKDD}} 2012, {{September}} 24-28, {{Bristol UK}}.},\n  author = {Vinterbo, Staal A.},\n  year = {2012},\n  series = {Lecture {{Notes}} in {{Artificial Intelligence}} Series ({{LNAI}})},\n  volume = {7524},\n  pages = {19--34},\n  publisher = {{Springer Verlag}},\n  doi = {10.1007/978-3-642-33486-3<sub>2</sub>},\n  url = {http://www.cs.bris.ac.uk/~flach/ECMLPKDD2012papers/1125758.pdf},\n  copyright = {All rights reserved},\n  ee = {http://dx.doi.org/10.1007/978-3-642-33486-3},\n  isbn = {978-3-642-33485-6},\n  nurl = {http://ptg.ucsd.edu/ staal/pubs/self/Proceedings/VinterboECML2012pre.pdf},\n  owner = {staal}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2011\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Anomaly and Signature Filtering Improve Classifier Performance for Detection of Suspicious Access to EHRs.\n \n \n \n \n\n\n \n Kim, J.; Grillo, J. M; Boxwala, A. A; Jiang, X.; Mandelbaum, R. B; Patel, B. A; Mikels, D.; Vinterbo, S. A; and Ohno-Machado, L.\n\n\n \n\n\n\n AMIA Annual Symposium Proceedings, 2011: 723–731. 2011.\n \n\n\n\n
\n\n\n\n \n \n \"AnomalyPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{kim_anomaly_2011,\n  title = {Anomaly and Signature Filtering Improve Classifier Performance for Detection of Suspicious Access to {{EHRs}}},\n  author = {Kim, Jihoon and Grillo, Janice M and Boxwala, Aziz A and Jiang, Xiaoqian and Mandelbaum, Rose B and Patel, Bhakti A and Mikels, Debra and Vinterbo, Staal A and {Ohno-Machado}, Lucila},\n  year = {2011},\n  journal = {AMIA Annual Symposium Proceedings},\n  volume = {2011},\n  pages = {723--731},\n  issn = {1942-597X},\n  url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3243249/},\n  abstract = {Our objective is to facilitate semi-automated detection of suspicious access to EHRs. Previously we have shown that a machine learning method can play a role in identifying potentially inappropriate access to EHRs. However, the problem of sampling informative instances to build a classifier still remained. We developed an integrated filtering method leveraging both anomaly detection based on symbolic clustering and signature detection, a rule-based technique. We applied the integrated filtering to 25.5 million access records in an intervention arm, and compared this with 8.6 million access records in a control arm where no filtering was applied. On the training set with cross-validation, the AUC was 0.960 in the control arm and 0.998 in the intervention arm. The difference in false negative rates on the independent test set was significant, P=1.6\\~A—10(-6). Our study suggests that utilization of integrated filtering strategies to facilitate the construction of classifiers can be helpful.},\n  copyright = {All rights reserved},\n  owner = {staal},\n  pmid = {22195129}\n}\n\n
\n
\n\n\n
\n Our objective is to facilitate semi-automated detection of suspicious access to EHRs. Previously we have shown that a machine learning method can play a role in identifying potentially inappropriate access to EHRs. However, the problem of sampling informative instances to build a classifier still remained. We developed an integrated filtering method leveraging both anomaly detection based on symbolic clustering and signature detection, a rule-based technique. We applied the integrated filtering to 25.5 million access records in an intervention arm, and compared this with 8.6 million access records in a control arm where no filtering was applied. On the training set with cross-validation, the AUC was 0.960 in the control arm and 0.998 in the intervention arm. The difference in false negative rates on the independent test set was significant, P=1.6×10(-6). Our study suggests that utilization of integrated filtering strategies to facilitate the construction of classifiers can be helpful.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2010\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n An Evaluation of Heuristics for Rule Ranking.\n \n \n \n \n\n\n \n Dreiseitl, S.; Osl, M.; Baumgartner, C.; and Vinterbo, S. A.\n\n\n \n\n\n\n Artificial Intelligence in Medicine, 50(3): 175–180. 2010.\n \n\n\n\n
\n\n\n\n \n \n \"AnLink\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Dreiseitl2010,\n  title = {An Evaluation of Heuristics for Rule Ranking},\n  author = {Dreiseitl, Stephan and Osl, Melanie and Baumgartner, Christian and Vinterbo, Staal A.},\n  year = {2010},\n  journal = {Artificial Intelligence in Medicine},\n  volume = {50},\n  number = {3},\n  pages = {175--180},\n  doi = {10.1016/j.artmed.2010.03.005},\n  bibsource = {DBLP, http://dblp.uni-trier.de},\n  copyright = {All rights reserved},\n  ee = {http://dx.doi.org/10.1016/j.artmed.2010.03.005},\n  file = {/Users/staal/Documents/Zotero/storage/3FQER3AG/dreiseitl2010ruleranking.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Spectral Anonymization of Data.\n \n \n \n\n\n \n Lasko, T. A.; and Vinterbo, S. A.\n\n\n \n\n\n\n Knowledge and Data Engineering, IEEE Transactions on, 22(3): 437–446. March 2010.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Lasko2009,\n  title = {Spectral {{Anonymization}} of {{Data}}},\n  author = {Lasko, Thomas A. and Vinterbo, Staal A.},\n  year = {2010},\n  month = mar,\n  journal = {Knowledge and Data Engineering, IEEE Transactions on},\n  volume = {22},\n  number = {3},\n  pages = {437--446},\n  issn = {1041-4347},\n  doi = {10.1109/TKDE.2009.88},\n  copyright = {All rights reserved},\n  owner = {staal},\n  file = {/Users/staal/Documents/Zotero/storage/67BF2XXM/spectralTKDEpreprint.pdf;/Users/staal/Documents/Zotero/storage/7TNMS6XN/spectralTKDEpreprint.pdf;/Users/staal/Documents/Zotero/storage/FE22TJCG/spectralTKDEpreprint.pdf;/Users/staal/Documents/Zotero/storage/TKCNEIQB/spectralTKDEpreprint.pdf;/Users/staal/Documents/Zotero/storage/WQTCEUF8/spectralTKDEpreprint.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2009\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Using Ambient Intelligence for Physiological Monitoring.\n \n \n \n\n\n \n Curtis, D. W.; Bailey, J.; Pino, E. J.; Stair, T.; Vinterbo, S.; Waterman, J.; Shih, E. I.; Guttag, J. V.; Greenes, R. A.; and Ohno-Machado, L.\n\n\n \n\n\n\n Journal of Ambient Intelligence and Smart Environments, 1(2): 129–142. January 2009.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{curtis_using_2009,\n  title = {Using Ambient Intelligence for Physiological Monitoring},\n  author = {Curtis, Dorothy W. and Bailey, Jacob and Pino, Esteban J. and Stair, Thomas and Vinterbo, Staal and Waterman, Jason and Shih, Eugene I. and Guttag, John V. and Greenes, Robert A. and {Ohno-Machado}, Lucila},\n  year = {2009},\n  month = jan,\n  journal = {Journal of Ambient Intelligence and Smart Environments},\n  volume = {1},\n  number = {2},\n  pages = {129--142},\n  doi = {10.3233/AIS-2009-0018},\n  abstract = {Ambient intelligence is a way of subtly gathering information from an environment and acting on it. In the field of physiological monitoring, there are several goals that ambient intelligence can help us achieve. First, when patients are anxious, unobtrusive monitoring does not aggravate their anxiety. Second, when patients are at risk and there are insufficient caregivers to attend to each patient individually in a timely manner, unobtrusive pervasive monitoring can reassure patients that they are being cared for. Furthermore, caregivers appreciate being able to monitor more patients. The SMART system was developed to monitor patients' vital signs and locations in the waiting area of a hospital's emergency department. This paper reviews the SMART system and compares it to several other systems in related areas.},\n  copyright = {All rights reserved},\n  owner = {staal},\n  file = {/Users/staal/Documents/Zotero/storage/NCEVM6DF/b214316070x23g21.html}\n}\n\n
\n
\n\n\n
\n Ambient intelligence is a way of subtly gathering information from an environment and acting on it. In the field of physiological monitoring, there are several goals that ambient intelligence can help us achieve. First, when patients are anxious, unobtrusive monitoring does not aggravate their anxiety. Second, when patients are at risk and there are insufficient caregivers to attend to each patient individually in a timely manner, unobtrusive pervasive monitoring can reassure patients that they are being cared for. Furthermore, caregivers appreciate being able to monitor more patients. The SMART system was developed to monitor patients' vital signs and locations in the waiting area of a hospital's emergency department. This paper reviews the SMART system and compares it to several other systems in related areas.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2008\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n SMART – An Integrated Wireless System for Monitoring Unattended Patients.\n \n \n \n\n\n \n Curtis, D. W.; Pino, E. J.; Bailey, J. M.; Shih, E. I.; Waterman, J.; Vinterbo, S. A.; Stair, T. O.; Guttag, J. V.; Greenes, R. A.; and Ohno-Machado, L.\n\n\n \n\n\n\n JAMIA, 15(1): 44–53. 2008.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Curtis2008,\n  title = {{{SMART}} -- {{An Integrated Wireless System}} for {{Monitoring Unattended Patients}}},\n  author = {Curtis, Dorothy W. and Pino, Esteban J. and Bailey, Jacob M. and Shih, Eugene I. and Waterman, Jason and Vinterbo, Staal A. and Stair, Thomas O. and Guttag, John V. and Greenes, Robert A. and {Ohno-Machado}, Lucila},\n  year = {2008},\n  journal = {JAMIA},\n  volume = {15},\n  number = {1},\n  pages = {44--53},\n  doi = {10.1197/jamia.M2016},\n  copyright = {All rights reserved},\n  owner = {staal},\n  file = {/Users/staal/Documents/Zotero/storage/HX9GU3RG/Curtis2008JAMIA.pdf;/Users/staal/Documents/Zotero/storage/SFNPF7KV/Curtis2008JAMIA.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2007\n \n \n (3)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Applying a Decision Support System in Clinical Practice: Results from Melanoma Diagnosis.\n \n \n \n \n\n\n \n Dreiseitl, S.; Binder, M.; Vinterbo, S.; and Kittler, H.\n\n\n \n\n\n\n In Proceedings of AMIA 2007, 2007. \n \n\n\n\n
\n\n\n\n \n \n \"ApplyingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Dreiseitl2007,\n  title = {Applying a Decision Support System in Clinical Practice: {{Results}} from Melanoma Diagnosis},\n  booktitle = {Proceedings of {{AMIA}} 2007},\n  author = {Dreiseitl, Stephan and Binder, Michael and Vinterbo, Staal and Kittler, Harald},\n  year = {2007},\n  url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2655775/},\n  abstract = {We investigate the performance of a decision-support tool for the diagnosis of pigmented skin lesions. Previously, we had developed andvalidated a neural network-based systems for automated melanoma diagnosis. The work reported in this paper investigates the use of this system in a real-world clinical trial with 511 patients and 3827 lesion evaluations. We analyzed a number of outcomes of the trial, such as direct comparison of system performance in laboratory and clinical setting, the performance of physicians using the system compared to a control dermatologist without the system, and repeatability of system recommendations. The results show that system performance was significantly less inthe laboratory setting compared to the real-world setting. Dermatologists using the system, however, achieved higher sensitivities and specificities than numbers reported in the literature for physicians of similar training who did not use a decision-support system. We also show that the process of acquiring lesion images using digital dermoscopy devices needs to be standardized before sufficiently high repeatability of measurements can be assured.},\n  copyright = {All rights reserved},\n  owner = {staal},\n  file = {/Users/staal/Documents/Zotero/storage/67AXXS3T/amia07.pdf;/Users/staal/Documents/Zotero/storage/ACTNR22T/amia07.pdf;/Users/staal/Documents/Zotero/storage/P9U9EJFK/amia07.pdf}\n}\n\n
\n
\n\n\n
\n We investigate the performance of a decision-support tool for the diagnosis of pigmented skin lesions. Previously, we had developed andvalidated a neural network-based systems for automated melanoma diagnosis. The work reported in this paper investigates the use of this system in a real-world clinical trial with 511 patients and 3827 lesion evaluations. We analyzed a number of outcomes of the trial, such as direct comparison of system performance in laboratory and clinical setting, the performance of physicians using the system compared to a control dermatologist without the system, and repeatability of system recommendations. The results show that system performance was significantly less inthe laboratory setting compared to the real-world setting. Dermatologists using the system, however, achieved higher sensitivities and specificities than numbers reported in the literature for physicians of similar training who did not use a decision-support system. We also show that the process of acquiring lesion images using digital dermoscopy devices needs to be standardized before sufficiently high repeatability of measurements can be assured.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Data Mining in Biomedicine.\n \n \n \n\n\n \n Ohno-Machado, L.; and Vinterbo, S. A.\n\n\n \n\n\n\n In Wong, S.; and Li, C., editor(s), volume 1, of Science, Engineering, and Biology Informatics, pages 305–319. World Scientific, 2007.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@incollection{Ohno-Machado2007,\n  title = {Data {{Mining}} in {{Biomedicine}}},\n  author = {{Ohno-Machado}, Lucial and Vinterbo, Staal A.},\n  editor = {Wong, Stephen and Li, Chung-Sheng},\n  year = {2007},\n  series = {Science, {{Engineering}}, and {{Biology Informatics}}},\n  volume = {1},\n  pages = {305--319},\n  publisher = {{World Scientific}},\n  copyright = {All rights reserved},\n  owner = {staal}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Stab at Approximating Minimum Subadditive Join.\n \n \n \n \n\n\n \n Vinterbo, S. A.\n\n\n \n\n\n\n In Algorithms and Data Structures: 10th International Workshop, WADS 2007, Halifax, Canada, August 15-17, 2007 Proceedings, of LNCS, August 2007. Springer Verlag\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Vinterbo2007,\n  title = {A {{Stab}} at {{Approximating Minimum Subadditive Join}}},\n  booktitle = {Algorithms and {{Data Structures}}: 10th {{International Workshop}}, {{WADS}} 2007, {{Halifax}}, {{Canada}}, {{August}} 15-17, 2007 {{Proceedings}}},\n  author = {Vinterbo, Staal A.},\n  year = {2007},\n  month = aug,\n  series = {{{LNCS}}},\n  publisher = {{Springer Verlag}},\n  doi = {10.1007/978-3-540-73951-7<sub>1</sub>9},\n  url = {self/Proceedings/minicover-wads2007.pdf},\n  abstract = {Let (L, {${_\\ast}$}) be a semilattice, and let c:L -{$>$} [0, {$\\infty$}) be mono- tone and increasing on L. We state the Minimum Join problem as: given size n sub-collection X of L and integer k with 1 {$<$}= k {$<$}= n, find a size k sub-collection (x1 , x2 , . . . , xk ) of X that minimizes c(x1 {${_\\ast}$} x2 {${_\\ast}$} {$\\cdot$} {$\\cdot$} {$\\cdot$} {${_\\ast}$} xk ). If c(a {${_\\ast}$} b) {$<$}= c(a) + c(b) holds, we call this the Minimum Subadditive Join (MSJ) problem and present a greedy (k - p + 1)-approximation al- gorithm requiring O((k - p)n + n\\textsuperscript{p}) joins for constant integer 0 {$<$} p {$<$}= k. We show that the MSJ Minimum Coverage problem of selecting k out of n finite sets such that their union is minimal is essentially as hard to approximate as the Maximum Balanced Complete Bipartite Subgraph (MBCBS) problem. The motivating by-product of the above is that the privacy in databases related k-ambiguity problem over L with subaddi- tive information loss can be approximated within k - p, and that the k-ambiguity problem is essentially at least as hard to approximate as MBCBS.},\n  copyright = {All rights reserved},\n  owner = {staal},\n  file = {/Users/staal/Documents/Zotero/storage/7689CAWT/minicover-wads2007.pdf;/Users/staal/Documents/Zotero/storage/CS5SMJCF/minicover-wads2007.pdf;/Users/staal/Documents/Zotero/storage/G4CJ4Q5S/minicover-wads2007.pdf;/Users/staal/Documents/Zotero/storage/G527A64C/minicover-wads2007.pdf;/Users/staal/Documents/Zotero/storage/WGKN39AX/minicover-wads2007.pdf}\n}\n\n
\n
\n\n\n
\n Let (L, $∗$) be a semilattice, and let c:L -$>$ [0, $∞$) be mono- tone and increasing on L. We state the Minimum Join problem as: given size n sub-collection X of L and integer k with 1 $<$= k $<$= n, find a size k sub-collection (x1 , x2 , . . . , xk ) of X that minimizes c(x1 $∗$ x2 $∗$ $·$ $·$ $·$ $∗$ xk ). If c(a $∗$ b) $<$= c(a) + c(b) holds, we call this the Minimum Subadditive Join (MSJ) problem and present a greedy (k - p + 1)-approximation al- gorithm requiring O((k - p)n + n\\textsuperscriptp) joins for constant integer 0 $<$ p $<$= k. We show that the MSJ Minimum Coverage problem of selecting k out of n finite sets such that their union is minimal is essentially as hard to approximate as the Maximum Balanced Complete Bipartite Subgraph (MBCBS) problem. The motivating by-product of the above is that the privacy in databases related k-ambiguity problem over L with subaddi- tive information loss can be approximated within k - p, and that the k-ambiguity problem is essentially at least as hard to approximate as MBCBS.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2006\n \n \n (2)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Approximation Properties of Haplotype Tagging.\n \n \n \n\n\n \n Vinterbo, S. A.; Dreiseitl, S.; and Ohno-Machado, L.\n\n\n \n\n\n\n BMC Bioinformatics, 7: 8. 2006.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{Vinterbo2006,\n  title = {Approximation Properties of Haplotype Tagging.},\n  author = {Vinterbo, Staal A. and Dreiseitl, Stephan and {Ohno-Machado}, Lucila},\n  year = {2006},\n  journal = {BMC Bioinformatics},\n  volume = {7},\n  pages = {8},\n  doi = {10.1186/1471-2105-7-8},\n  abstract = {BACKGROUND: Single nucleotide polymorphisms (SNPs) are locations at which the genomic sequences of population members differ. Since these differences are known to follow patterns, disease association studies are facilitated by identifying SNPs that allow the unique identification of such patterns. This process, known as haplotype tagging, is formulated as a combinatorial optimization problem and analyzed in terms of complexity and approximation properties. RESULTS: It is shown that the tagging problem is NP-hard but approximable within 1 + ln((n2 - n)/2) for n haplotypes but not approximable within (1-epsilon) ln(n/2) for any epsilon {$>$} 0 unless NP subset DTIME(n(log log n)). A simple, very easily implementable algorithm that exhibits the above upper bound on solution quality is presented. This algorithm has running time O(np/2(2m-p+1)) {$<$} or = O(m(n2-n)/2) where p {$<$} or = min(n, m) for n haplotypes of size m. As we show that the approximation bound is asymptotically tight, the algorithm presented is optimal with respect to this asymptotic bound. CONCLUSION: The haplotype tagging problem is hard, but approachable with a fast, practical, and surprisingly simple algorithm that cannot be significantly improved upon on a single processor machine. Hence, significant improvement in computational efforts expended can only be expected if the computational effort is distributed and done in parallel.},\n  copyright = {All rights reserved},\n  owner = {staal},\n  pii = {1471-2105-7-8},\n  pmid = {16401341},\n  keywords = {16401341,Algorithms,Animals,Chromosome Mapping,Computational Biology,Genome; Human,Haplotypes,Humans,Models; Genetic,Models; Statistical,Models; Theoretical,Polymorphism; Single Nucleotide,Reproducibility of Results,Sequence Alignment,Software},\n  file = {/Users/staal/Documents/Zotero/storage/52UIT7JS/bmc-snptag.pdf;/Users/staal/Documents/Zotero/storage/BU5SXSHJ/bmc-snptag.pdf;/Users/staal/Documents/Zotero/storage/DEH4SPRA/bmc-snptag.pdf;/Users/staal/Documents/Zotero/storage/NK89WPWD/bmc-snptag.pdf;/Users/staal/Documents/Zotero/storage/T3UU8CIQ/bmc-snptag.pdf;/Users/staal/Documents/Zotero/storage/ZAAPRRT3/bmc-snptag.pdf}\n}\n\n
\n
\n\n\n
\n BACKGROUND: Single nucleotide polymorphisms (SNPs) are locations at which the genomic sequences of population members differ. Since these differences are known to follow patterns, disease association studies are facilitated by identifying SNPs that allow the unique identification of such patterns. This process, known as haplotype tagging, is formulated as a combinatorial optimization problem and analyzed in terms of complexity and approximation properties. RESULTS: It is shown that the tagging problem is NP-hard but approximable within 1 + ln((n2 - n)/2) for n haplotypes but not approximable within (1-epsilon) ln(n/2) for any epsilon $>$ 0 unless NP subset DTIME(n(log log n)). A simple, very easily implementable algorithm that exhibits the above upper bound on solution quality is presented. This algorithm has running time O(np/2(2m-p+1)) $<$ or = O(m(n2-n)/2) where p $<$ or = min(n, m) for n haplotypes of size m. As we show that the approximation bound is asymptotically tight, the algorithm presented is optimal with respect to this asymptotic bound. CONCLUSION: The haplotype tagging problem is hard, but approachable with a fast, practical, and surprisingly simple algorithm that cannot be significantly improved upon on a single processor machine. Hence, significant improvement in computational efforts expended can only be expected if the computational effort is distributed and done in parallel.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Note on Solution Sizes in The Haplotype Tagging SNPS Problem.\n \n \n \n \n\n\n \n Vinterbo, S. A.; and Dreiseitl, S.\n\n\n \n\n\n\n In Bruzzone, A. G.; Guasch, A.; Piera, M. A.; and Rozenblit, J., editor(s), Proceedings of the 3rd European Modelling and Simulation Symposium (EMSS2006), 2006. \n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Vinterbo2006a,\n  title = {A {{Note}} on {{Solution Sizes}} in {{The Haplotype Tagging SNPS Problem}}},\n  booktitle = {Proceedings of the 3rd {{European Modelling}} and {{Simulation Symposium}} ({{EMSS2006}})},\n  author = {Vinterbo, Staal A. and Dreiseitl, Stephan},\n  editor = {Bruzzone, Agostino G. and Guasch, Antoni and Piera, Miquel Angel and Rozenblit, Jerzy},\n  year = {2006},\n  url = {https://laats.github.io/pubs/self/Proceedings/emss2006.pdf},\n  copyright = {All rights reserved},\n  owner = {staal},\n  file = {/Users/staal/Documents/Zotero/storage/54MU5HHQ/emss2006.pdf;/Users/staal/Documents/Zotero/storage/D6K8CA38/emss2006.pdf;/Users/staal/Documents/Zotero/storage/UUN9KVSS/emss2006.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2005\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Small, Fuzzy and Interpretable Gene Expression Based Classifiers.\n \n \n \n\n\n \n Vinterbo, S. A.; Kim, E.; and Ohno-Machado, L.\n\n\n \n\n\n\n Bioinformatics, 21(9): 1964–1970. January 2005.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{Vinterbo2005,\n  title = {Small, Fuzzy and Interpretable Gene Expression Based Classifiers.},\n  author = {Vinterbo, Staal A. and Kim, Eun-Young and {Ohno-Machado}, Lucila},\n  year = {2005},\n  month = jan,\n  journal = {Bioinformatics},\n  volume = {21},\n  number = {9},\n  pages = {1964--1970},\n  doi = {10.1093/bioinformatics/bti287},\n  abstract = {MOTIVATION: Interpretation of classification models derived from gene expression data is usually not simple, yet it is an important aspect in the analytical process. We investigate the performance of small rule-based classifiers based on fuzzy logic in five data sets that are different in size, laboratory origin, and biomedical domain. RESULTS: The classifiers resulted in rules that can be readily examined by biomedical researchers. The fuzzy-logic-based classifiers compare favorably with logistic regression in all data sets. AVAILABILITY: Prototype available upon request.},\n  copyright = {All rights reserved},\n  pii = {bti287},\n  pubmedid = {15661797},\n  keywords = {15661797,Algorithms,artificial intelligence,Cluster Analysis,Fuzzy Logic,Gene Expression Profiling,Humans,Neoplasm Proteins,Neoplasms,Oligonucleotide Array Sequence Analysis,Pattern Recognition; Automated,Software,Tumor Markers; Biological},\n  file = {/Users/staal/Documents/Zotero/storage/CW95CXF2/fuzzygenes-Bioinf.pdf;/Users/staal/Documents/Zotero/storage/Z7EAQVCZ/fuzzygenes-Bioinf.pdf}\n}\n\n
\n
\n\n\n
\n MOTIVATION: Interpretation of classification models derived from gene expression data is usually not simple, yet it is an important aspect in the analytical process. We investigate the performance of small rule-based classifiers based on fuzzy logic in five data sets that are different in size, laboratory origin, and biomedical domain. RESULTS: The classifiers resulted in rules that can be readily examined by biomedical researchers. The fuzzy-logic-based classifiers compare favorably with logistic regression in all data sets. AVAILABILITY: Prototype available upon request.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2004\n \n \n (6)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n A Primer on Gene Expression and Microarrays for Machine Learning Researchers.\n \n \n \n\n\n \n Kuo, W. P.; Kim, E.; Trimarchi, J.; Jenssen, T.; Vinterbo, S. A.; and Ohno-Machado, L.\n\n\n \n\n\n\n J Biomed Inform, 37(4): 293–303. August 2004.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n\n\n\n
\n 
@article{Kuo2004,\n  title = {A Primer on Gene Expression and Microarrays for Machine Learning Researchers.},\n  author = {Kuo, Winston Patrick and Kim, Eun-Young and Trimarchi, Jeff and Jenssen, Tor-Kristian and Vinterbo, Staal A. and {Ohno-Machado}, Lucila},\n  year = {2004},\n  month = aug,\n  journal = {J Biomed Inform},\n  volume = {37},\n  number = {4},\n  pages = {293--303},\n  doi = {10.1016/j.jbi.2004.07.002},\n  abstract = {Data originating from biomedical experiments has provided machine learning researchers with an important source of motivation for developing and evaluating new algorithms. A new wave of algorithmic development has been initiated with the publication of gene expression data derived from microarrays. Microarray data analysis is particularly challenging given the large number of measurements (typically in the order of thousands) that are reported for relatively few samples (typically in the order of dozens). Many data sets are now available on the web. It is important that machine learning researchers understand how data are obtained and which assumptions are necessary in the analysis. Microarray data have the potential to cause significant impact in machine learning research, not just as a rich and realistic source of cases for testing new algorithms, as has been the UCI machine learning repository in the past decades, but also as a main motivation for their development. In this article, we briefly review the biology underlying microarrays, the process of obtaining gene expression measurements, and the rationale behind the common types of analyses involved in a microarray experiment. We outline the main challenges and reiterate critical considerations regarding the construction of supervised learning models that use this type of data. The goal of this article is to familiarize machine learning researchers with data originated from gene expression microarrays.},\n  copyright = {All rights reserved},\n  pii = {S1532-0464(04)00069-3},\n  pubmedid = {15465482},\n  keywords = {15465482},\n  file = {/Users/staal/Documents/Zotero/storage/BTHW8276/Kuo2004JBIreview.pdf}\n}\n\n
\n
\n\n\n
\n Data originating from biomedical experiments has provided machine learning researchers with an important source of motivation for developing and evaluating new algorithms. A new wave of algorithmic development has been initiated with the publication of gene expression data derived from microarrays. Microarray data analysis is particularly challenging given the large number of measurements (typically in the order of thousands) that are reported for relatively few samples (typically in the order of dozens). Many data sets are now available on the web. It is important that machine learning researchers understand how data are obtained and which assumptions are necessary in the analysis. Microarray data have the potential to cause significant impact in machine learning research, not just as a rich and realistic source of cases for testing new algorithms, as has been the UCI machine learning repository in the past decades, but also as a main motivation for their development. In this article, we briefly review the biology underlying microarrays, the process of obtaining gene expression measurements, and the rationale behind the common types of analyses involved in a microarray experiment. We outline the main challenges and reiterate critical considerations regarding the construction of supervised learning models that use this type of data. The goal of this article is to familiarize machine learning researchers with data originated from gene expression microarrays.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Protecting Patient Privacy by Quantifiable Control of Disclosures in Disseminated Databases.\n \n \n \n\n\n \n Ohno-Machado, L.; Silveira, P. S. P.; and Vinterbo, S.\n\n\n \n\n\n\n Int J Med Inform, 73(7-8): 599–606. August 2004.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{Ohno-Machado2004,\n  title = {Protecting Patient Privacy by Quantifiable Control of Disclosures in Disseminated Databases.},\n  author = {{Ohno-Machado}, Lucila and Silveira, Paulo Sergio Panse and Vinterbo, Staal},\n  year = {2004},\n  month = aug,\n  journal = {Int J Med Inform},\n  volume = {73},\n  number = {7-8},\n  pages = {599--606},\n  doi = {10.1016/j.ijmedinf.2004.05.002},\n  abstract = {One of the fundamental rights of patients is to have their privacy protected by health care organizations, so that information that can be used to identify a particular individual is not used to reveal sensitive patient data such as diagnoses, reasons for ordering tests, test results, etc. A common practice is to remove sensitive data from databases that are disseminated to the public, but this can make the disseminated database useless for important public health purposes. If the degree of anonymity of a disseminated data set could be measured, it would be possible to design algorithms that can assure that the desired level of confidentiality is achieved. Privacy protection in disseminated databases can be facilitated by the use of special ambiguation algorithms. Most of these algorithms are aimed at making one individual indistinguishable from one or more of his peers. However, even in databases considered "anonymous", it may still be possible to obtain sensitive information about some individuals or groups of individuals with the use of pattern recognition algorithms. In this article, we study the problem of determining the degree of ambiguation in disseminated databases and discuss its implications in the development and testing of "anonymization" algorithms.},\n  copyright = {All rights reserved},\n  pii = {S1386505604000942},\n  pubmedid = {15246040},\n  keywords = {15246040,Algorithms,Anonymous Testing,Comparative Study,Computerized,Confidentiality,Databases,Disclosure,Humans,Medical Records Systems,Non-U.S. Gov't,P.H.S.,Privacy,Research Support,U.S. Gov't},\n  file = {/Users/staal/Documents/Zotero/storage/2TAKACDV/Ohno-Machado2004Anon.pdf;/Users/staal/Documents/Zotero/storage/6RZDE267/Ohno-Machado2004Anon.pdf;/Users/staal/Documents/Zotero/storage/FIKI3WM3/Ohno-Machado2004Anon.pdf;/Users/staal/Documents/Zotero/storage/ZHMGTVCS/Ohno-Machado2004Anon.pdf}\n}\n\n
\n
\n\n\n
\n One of the fundamental rights of patients is to have their privacy protected by health care organizations, so that information that can be used to identify a particular individual is not used to reveal sensitive patient data such as diagnoses, reasons for ordering tests, test results, etc. A common practice is to remove sensitive data from databases that are disseminated to the public, but this can make the disseminated database useless for important public health purposes. If the degree of anonymity of a disseminated data set could be measured, it would be possible to design algorithms that can assure that the desired level of confidentiality is achieved. Privacy protection in disseminated databases can be facilitated by the use of special ambiguation algorithms. Most of these algorithms are aimed at making one individual indistinguishable from one or more of his peers. However, even in databases considered \"anonymous\", it may still be possible to obtain sensitive information about some individuals or groups of individuals with the use of pattern recognition algorithms. In this article, we study the problem of determining the degree of ambiguation in disseminated databases and discuss its implications in the development and testing of \"anonymization\" algorithms.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Privacy: A Machine Learning View.\n \n \n \n\n\n \n Vinterbo, S. A.\n\n\n \n\n\n\n IEEE Transactions on Knowledge and Data Engineering, 16(8): 939–948. August 2004.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{vinterbo03:_privac,\n  title = {Privacy: {{A Machine Learning View}}},\n  author = {Vinterbo, Staal A.},\n  year = {2004},\n  month = aug,\n  journal = {IEEE Transactions on Knowledge and Data Engineering},\n  volume = {16},\n  number = {8},\n  pages = {939--948},\n  doi = {10.1109/TKDE.2004.31},\n  copyright = {All rights reserved},\n  keywords = {approximation properties,combinatorial optimization,complexity,disclosure control,machine learning.,privacy},\n  file = {/Users/staal/Documents/Zotero/storage/22DWR46T/IEEE-TKDE-DCML.pdf;/Users/staal/Documents/Zotero/storage/AEDGJDT8/IEEE-TKDE-DCML.pdf;/Users/staal/Documents/Zotero/storage/THETC6KR/citation.html}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Fast MDA Approximation Algorithm.\n \n \n \n \n\n\n \n Vinterbo, S. A.\n\n\n \n\n\n\n Technical Report DSG-TR-2004-04, Decision Systems Group, Brigham and Women's Hospital, Boston., 75 Francis Street, Boston, MA 02115, USA, December 2004.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@techreport{vinterbo04:fastMDA,\n  title = {A Fast {{MDA}} Approximation Algorithm},\n  author = {Vinterbo, Staal A.},\n  year = {2004},\n  month = dec,\n  number = {DSG-TR-2004-04},\n  address = {{75 Francis Street, Boston, MA 02115, USA}},\n  institution = {{Decision Systems Group, Brigham and Women's Hospital, Boston.}},\n  url = {self/techraps/fastMDA-techrap.pdf},\n  copyright = {All rights reserved},\n  file = {/Users/staal/Documents/Zotero/storage/4JPB2E88/fastMDA-techrap.pdf;/Users/staal/Documents/Zotero/storage/KISXJJVX/fastMDA-techrap.pdf;/Users/staal/Documents/Zotero/storage/UFHPG4HJ/fastMDA-techrap.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n A Testing Procedure for htSNP Approximation Algorithms.\n \n \n \n\n\n \n Vinterbo, S.; Dreiseitl, S.; and Ohno-Machado, L.\n\n\n \n\n\n\n In Proceedings of IDAMAP 2004 at Stanford, 2004. \n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Vinterbo2004:idamap,\n  title = {A {{Testing Procedure}} for {{htSNP Approximation Algorithms}}},\n  booktitle = {Proceedings of {{IDAMAP}} 2004 at {{Stanford}}},\n  author = {Vinterbo, Staal and Dreiseitl, Stephan and {Ohno-Machado}, Lucila},\n  year = {2004},\n  copyright = {All rights reserved},\n  owner = {staal},\n  file = {/Users/staal/Documents/Zotero/storage/239BTRWR/tagtesting_vinterbo.pdf;/Users/staal/Documents/Zotero/storage/F6CPQ84I/tagtesting_vinterbo.pdf;/Users/staal/Documents/Zotero/storage/XQGA55FP/tagtesting_vinterbo.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Multivariate Selection of Genetic Markers in Diagnostic Classification.\n \n \n \n\n\n \n Weber, G.; Vinterbo, S.; and Ohno-Machado, L.\n\n\n \n\n\n\n Artif Intell Med, 31(2): 155–67. June 2004.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{Weber2004,\n  title = {Multivariate Selection of Genetic Markers in Diagnostic Classification.},\n  author = {Weber, Griffin and Vinterbo, Staal and {Ohno-Machado}, Lucila},\n  year = {2004},\n  month = jun,\n  journal = {Artif Intell Med},\n  volume = {31},\n  number = {2},\n  pages = {155--67},\n  doi = {10.1016/j.artmed.2004.01.011},\n  abstract = {Analysis of gene expression data obtained from microarrays presents a new set of challenges to machine learning modeling. In this domain, in which the number of variables far exceeds the number of cases, identifying relevant genes or groups of genes that are good markers for a particular classification is as important as achieving good classification performance. Although several machine learning algorithms have been proposed to address the latter, identification of gene markers has not been systematically pursued. In this article, we investigate several algorithms for selecting gene markers for classification. We test these algorithms using logistic regression, as this is a simple and efficient supervised learning algorithm. We demonstrate, using 10 different data sets, that a conditionally univariate algorithm constitutes a viable choice if a researcher is interested in quickly determining a set of gene expression levels that can serve as markers for disease. We show that the classification performance of logistic regression is not very different from that of more sophisticated algorithms that have been applied in previous studies, and that the gene selection in the logistic regression algorithm is reasonable in both cases. Furthermore, the algorithm is simple, its theoretical basis is well established, and our user-friendly implementation is now freely available on the internet, serving as a benchmarking tool for the development of new algorithms.},\n  copyright = {All rights reserved},\n  pii = {S093336570400034X},\n  pubmedid = {15219292},\n  keywords = {15219292,Algorithms,Anonymous Testing,Artificial Intelligence,Comparative Study,Computerized,Confidentiality,Databases,Diagnosis,Differential,Disclosure,Gene Expression Profiling,Genetic Markers,Humans,Medical Records Systems,Multivariate Analysis,Non-U.S. Gov't,Oligonucleotide Array Sequence Analysis,P.H.S.,Privacy,Research Support,U.S. Gov't},\n  file = {/Users/staal/Documents/Zotero/storage/6ZI26J2A/Weber2004.pdf;/Users/staal/Documents/Zotero/storage/M5I5MPVB/Weber2004.pdf;/Users/staal/Documents/Zotero/storage/SJ2FFTU8/Weber2004.pdf}\n}\n\n\n
\n
\n\n\n
\n Analysis of gene expression data obtained from microarrays presents a new set of challenges to machine learning modeling. In this domain, in which the number of variables far exceeds the number of cases, identifying relevant genes or groups of genes that are good markers for a particular classification is as important as achieving good classification performance. Although several machine learning algorithms have been proposed to address the latter, identification of gene markers has not been systematically pursued. In this article, we investigate several algorithms for selecting gene markers for classification. We test these algorithms using logistic regression, as this is a simple and efficient supervised learning algorithm. We demonstrate, using 10 different data sets, that a conditionally univariate algorithm constitutes a viable choice if a researcher is interested in quickly determining a set of gene expression levels that can serve as markers for disease. We show that the classification performance of logistic regression is not very different from that of more sophisticated algorithms that have been applied in previous studies, and that the gene selection in the logistic regression algorithm is reasonable in both cases. Furthermore, the algorithm is simple, its theoretical basis is well established, and our user-friendly implementation is now freely available on the internet, serving as a benchmarking tool for the development of new algorithms.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2003\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n An Epicurean Learning Approach to Gene-Expression Data Classification.\n \n \n \n\n\n \n Albrecht, A.; Vinterbo, S. A.; and Ohno-Machado, L.\n\n\n \n\n\n\n Artif Intell Med, 28(1): 75–87. May 2003.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{Albrecht2003,\n  title = {An {{Epicurean}} Learning Approach to Gene-Expression Data Classification.},\n  author = {Albrecht, Andreas and Vinterbo, Staal A. and {Ohno-Machado}, Lucila},\n  year = {2003},\n  month = may,\n  journal = {Artif Intell Med},\n  volume = {28},\n  number = {1},\n  pages = {75--87},\n  doi = {10.1016/S0933-3657(03)00036-8},\n  abstract = {We investigate the use of perceptrons for classification of microarray data where we use two datasets that were published in [Nat. Med. 7 (6) (2001) 673] and [Science 286 (1999) 531]. The classification problem studied by Khan et al. is related to the diagnosis of small round blue cell tumours (SRBCT) of childhood which are difficult to classify both clinically and via routine histology. Golub et al. study acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL). We used a simulated annealing-based method in learning a system of perceptrons, each obtained by resampling of the training set. Our results are comparable to those of Khan et al. and Golub et al., indicating that there is a role for perceptrons in the classification of tumours based on gene-expression data. We also show that it is critical to perform feature selection in this type of models, i.e. we propose a method for identifying genes that might be significant for the particular tumour types. For SRBCTs, zero error on test data has been obtained for only 13 out of 2308 genes; for the ALL/AML problem, we have zero error for 9 out of 7129 genes that are used for the classification procedure. Furthermore, we provide evidence that Epicurean-style learning and simulated annealing-based search are both essential for obtaining the best classification results.},\n  copyright = {All rights reserved},\n  pii = {S0933365703000368},\n  pubmedid = {12850314},\n  keywords = {12850314,Algorithms,Anonymous Testing,Artificial Intelligence,Carcinoma,Child,Comparative Study,Computerized,Confidentiality,Databases,Diagnosis,Differential,Disclosure,Gene Expression Profiling,Gene Expression Regulation,Genetic Markers,Humans,Lung Neoplasms,Medical Records Systems,Multivariate Analysis,Neoplastic,Neural Networks (Computer),Non-U.S. Gov't,Oligonucleotide Array Sequence Analysis,P.H.S.,Privacy,Research Support,Rhabdomyosarcoma,Sarcoma,Small Cell,U.S. Gov't}\n}\n\n
\n
\n\n\n
\n We investigate the use of perceptrons for classification of microarray data where we use two datasets that were published in [Nat. Med. 7 (6) (2001) 673] and [Science 286 (1999) 531]. The classification problem studied by Khan et al. is related to the diagnosis of small round blue cell tumours (SRBCT) of childhood which are difficult to classify both clinically and via routine histology. Golub et al. study acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL). We used a simulated annealing-based method in learning a system of perceptrons, each obtained by resampling of the training set. Our results are comparable to those of Khan et al. and Golub et al., indicating that there is a role for perceptrons in the classification of tumours based on gene-expression data. We also show that it is critical to perform feature selection in this type of models, i.e. we propose a method for identifying genes that might be significant for the particular tumour types. For SRBCTs, zero error on test data has been obtained for only 13 out of 2308 genes; for the ALL/AML problem, we have zero error for 9 out of 7129 genes that are used for the classification procedure. Furthermore, we provide evidence that Epicurean-style learning and simulated annealing-based search are both essential for obtaining the best classification results.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2002\n \n \n (10)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Epicurean-Style Learning Applied to the Classification of Gene-Expression Data.\n \n \n \n\n\n \n Albrecht, A.; Vinterbo, S. A.; and Ohno-Machado, L.\n\n\n \n\n\n\n In Bramer, M.; Preece, A.; and Coenen, F., editor(s), Research and Development in Intelligent Systems XIX, of BCS Series, pages 47–59. Springer-Verlag, 2002.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@incollection{albrecht02:_epicur,\n  title = {Epicurean-Style {{Learning Applied}} to the {{Classification}} of {{Gene-Expression Data}}},\n  booktitle = {Research and {{Development}} in {{Intelligent Systems XIX}}},\n  author = {Albrecht, A. and Vinterbo, S. A. and {Ohno-Machado}, L.},\n  editor = {Bramer, M. and Preece, A. and Coenen, F.},\n  year = {2002},\n  series = {{{BCS Series}}},\n  pages = {47--59},\n  publisher = {{Springer-Verlag}},\n  copyright = {All rights reserved},\n  annotation = {ISBN 1-85233-674-9}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Simulated Annealing and Resampling Method for Training Perceptrons to Classify Gene-Expression Data.\n \n \n \n \n\n\n \n Albrecht, A.; Vinterbo, S. A.; Wong, C. K.; and Ohno-Machado, L.\n\n\n \n\n\n\n In Dorronsoro, J. R., editor(s), Artificial Neural Networks (ICANN'02), volume 2415, of LNCS Series, pages 401–406. Springer-Verlag, 2002.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@incollection{albrecht02:_simul_anneal,\n  title = {A {{Simulated Annealing}} and {{Resampling Method}} for {{Training Perceptrons}} to {{Classify Gene-Expression Data}}},\n  booktitle = {Artificial {{Neural Networks}} ({{ICANN}}'02)},\n  author = {Albrecht, A. and Vinterbo, S. A. and Wong, C. K. and {Ohno-Machado}, L.},\n  editor = {Dorronsoro, J. R.},\n  year = {2002},\n  series = {{{LNCS Series}}},\n  volume = {2415},\n  pages = {401--406},\n  publisher = {{Springer-Verlag}},\n  url = {self/Proceedings/ICANN.ps},\n  copyright = {All rights reserved},\n  annotation = {ISBN 3-540-44074-7},\n  file = {/Users/staal/Documents/Zotero/storage/8DRZ5TH4/ICANN.ps;/Users/staal/Documents/Zotero/storage/AZWDTEDS/ICANN.ps;/Users/staal/Documents/Zotero/storage/W5T5C6EC/ICANN.ps}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Two Applications of the LSA Machine.\n \n \n \n\n\n \n Albrecht, A.; Lappas, G.; Vinterbo, S. A.; Wong, C. K.; and Ohno-Machado, L.\n\n\n \n\n\n\n In Proceedings of the 9\\textsuperscriptth International Conference on Neural Information Processing (ICONIP'02), Singapore, 2002. \n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{albrecht02:lsa_machin,\n  title = {Two {{Applications}} of the {{LSA Machine}}},\n  booktitle = {Proceedings of the 9{\\textsuperscript{th}} {{International Conference}} on {{Neural Information Processing}} ({{ICONIP}}'02)},\n  author = {Albrecht, A. and Lappas, G. and Vinterbo, S. A. and Wong, C. K. and {Ohno-Machado}, L.},\n  year = {2002},\n  address = {{Singapore}},\n  doi = {10.1109/ICONIP.2002.1202156},\n  copyright = {All rights reserved},\n  annotation = {ISBN 981-04-7525-X}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Disambiguation Data: Extracting Information from Anonymized Sources.\n \n \n \n\n\n \n Dreiseitl, S.; Vinterbo, S.; and Ohno-Machado, L.\n\n\n \n\n\n\n JAMIA, 9(90061): S110-S114. 2002.\n \n\n\n\n
\n\n\n\n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Dreiseitl2002,\n  title = {Disambiguation Data: {{Extracting}} Information from Anonymized Sources},\n  author = {Dreiseitl, S. and Vinterbo, S. and {Ohno-Machado}, L.},\n  year = {2002},\n  journal = {JAMIA},\n  volume = {9},\n  number = {90061},\n  pages = {S110-S114},\n  doi = {10.1197/jamia.M1240},\n  copyright = {All rights reserved},\n  owner = {staal},\n  file = {/Users/staal/Documents/Zotero/storage/F8ACJBJT/Dreiseitl-JAMIA-02.pdf;/Users/staal/Documents/Zotero/storage/FNEBUT9U/Dreiseitl-JAMIA-02.pdf;/Users/staal/Documents/Zotero/storage/KURHUUJ3/Dreiseitl-JAMIA-02.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Classification of Gene Expression Data Using Fuzzy Logic.\n \n \n \n \n\n\n \n Ohno-Machado, L.; Vinterbo, S. A.; and Weber, G.\n\n\n \n\n\n\n Journal of Intelligent and Fuzzy Systems, 12(1): 19–24. 2002.\n \n\n\n\n
\n\n\n\n \n \n \"ClassificationPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{ohno-machado02:fuzzy_gene,\n  title = {Classification of {{Gene Expression Data Using Fuzzy Logic}}},\n  author = {{Ohno-Machado}, L. and Vinterbo, S. A. and Weber, G.},\n  year = {2002},\n  journal = {Journal of Intelligent and Fuzzy Systems},\n  volume = {12},\n  number = {1},\n  pages = {19--24},\n  url = {http://www.academia.edu/322135/Classification_of_Gene_Expression_Data_Using_Fuzzy_Logic},\n  copyright = {All rights reserved},\n  file = {/Users/staal/Documents/Zotero/storage/GFZIRTB8/ohno-machado-2002-fuzzy.pdf;/Users/staal/Documents/Zotero/storage/HX4UUXBJ/ohno-machado-2002-fuzzy.pdf;/Users/staal/Documents/Zotero/storage/KHIG28F2/ohno-machado-2002-fuzzy.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Effects of Data Anonymization by Cell Suppression on Descriptive Statistics and Predictive Modeling Performance.\n \n \n \n\n\n \n Ohno-Machado, L.; Vinterbo, S.; and Dreiseitl, S.\n\n\n \n\n\n\n JAMIA, 9(90061): S115-S119. 2002.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Ohno-Machado2001,\n  title = {Effects of Data Anonymization by Cell Suppression on Descriptive Statistics and Predictive Modeling Performance},\n  author = {{Ohno-Machado}, L. and Vinterbo, S. and Dreiseitl, S.},\n  year = {2002},\n  journal = {JAMIA},\n  volume = {9},\n  number = {90061},\n  pages = {S115-S119},\n  copyright = {All rights reserved},\n  owner = {staal},\n  file = {/Users/staal/Documents/Zotero/storage/AN8A7QGP/LOM-JAMIA-02.pdf;/Users/staal/Documents/Zotero/storage/ND5C8WP9/LOM-JAMIA-02.pdf;/Users/staal/Documents/Zotero/storage/RRGNW5GX/LOM-JAMIA-02.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Comparing Imperfect Measurements with the Bland-Altman Technique: Application in Gene Expression Analysis.\n \n \n \n\n\n \n Ohno-Machado, L.; Vinterbo, S.; Dreiseitl, S.; Jenssen, T.; and Kuo, W.\n\n\n \n\n\n\n JAMIA, Suppl. S: 572–6. 2002.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{Ohno-Machado2002,\n  title = {Comparing Imperfect Measurements with the {{Bland-Altman}} Technique: Application in Gene Expression Analysis.},\n  author = {{Ohno-Machado}, Lucila and Vinterbo, Staal and Dreiseitl, Stephen and Jenssen, Tor-Kristian and Kuo, Winston},\n  year = {2002},\n  journal = {JAMIA},\n  volume = {Suppl. S},\n  pages = {572--6},\n  abstract = {Several problems in medicine and biology involve the comparison of two measurements made on the same set of cases. The problem differs from a calibration problem because no gold standard can be identified. Testing the null hypothesis of no relationship using measures of association is not optimal since the measurements are made on the same cases, and therefore correlation coefficients will tend to be significant. The descriptive Bland-Altman method can be used in exploratory analysis of this problem, allowing the visualization of gross systematic differences between the two sets of measurements. We utilize the method on three sets of matched observations and demonstrate its usefulness in detecting systematic variations between two measurement technologies to assess gene expression.},\n  copyright = {All rights reserved},\n  pii = {1833},\n  pubmedid = {12463888},\n  keywords = {12463888,Algorithms,Anonymous Testing,Artificial Intelligence,Bias (Epidemiology),Carcinoma,Child,Comparative Study,Computational Biology,Computerized,Confidentiality,Data Interpretation,Databases,Diagnosis,Differential,Disclosure,DNA,Gene Expression,Gene Expression Profiling,Gene Expression Regulation,Genetic Markers,Humans,Internet,Logistic Models,Lung Neoplasms,Medical Records Systems,Messenger,Multivariate Analysis,Neoplasm,Neoplasms,Neoplastic,Neural Networks (Computer),Non-U.S. Gov't,Oligonucleotide Array Sequence Analysis,P.H.S.,Privacy,Research Support,Rhabdomyosarcoma,RNA,Sarcoma,Small Cell,Software,Statistical,U.S. Gov't}\n}\n\n
\n
\n\n\n
\n Several problems in medicine and biology involve the comparison of two measurements made on the same set of cases. The problem differs from a calibration problem because no gold standard can be identified. Testing the null hypothesis of no relationship using measures of association is not optimal since the measurements are made on the same cases, and therefore correlation coefficients will tend to be significant. The descriptive Bland-Altman method can be used in exploratory analysis of this problem, allowing the visualization of gross systematic differences between the two sets of measurements. We utilize the method on three sets of matched observations and demonstrate its usefulness in detecting systematic variations between two measurement technologies to assess gene expression.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Maximum K-Intersection, Edge Labeled Multigraph Max Capacity k-Path, and Max Factor k-Gcd Are All NP-hard.\n \n \n \n \n\n\n \n Vinterbo, S. A.\n\n\n \n\n\n\n Technical Report DSG-TR-2002-12, Decision Systems Group/Harvard Medical School, 75 Francis Street, Boston, MA 02115, USA, May 2002.\n \n\n\n\n
\n\n\n\n \n \n \"MaximumPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@techreport{vinterbo02:_maxim_np,\n  title = {Maximum K-Intersection, Edge Labeled Multigraph Max Capacity k-Path, and Max Factor k-Gcd Are All {{NP-hard}}},\n  author = {Vinterbo, Staal A.},\n  year = {2002},\n  month = may,\n  number = {DSG-TR-2002-12},\n  address = {{75 Francis Street, Boston, MA 02115, USA}},\n  institution = {{Decision Systems Group/Harvard Medical School}},\n  url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.11.2135&rep=rep1&type=pdf},\n  copyright = {All rights reserved}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Note on the Hardness of the K-Ambiguity Problem.\n \n \n \n \n\n\n \n Vinterbo, S. A.\n\n\n \n\n\n\n Technical Report DSG-TR-2002-006, Decision Systems Group/Harvard Medical School, 75 Francis Street, Boston, MA 02115, USA, May 2002.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@techreport{vinterbo02:_note_hardn_ambig_probl,\n  title = {A {{Note}} on the {{Hardness}} of the K-{{Ambiguity Problem}}},\n  author = {Vinterbo, Staal A.},\n  year = {2002},\n  month = may,\n  number = {DSG-TR-2002-006},\n  address = {{75 Francis Street, Boston, MA 02115, USA}},\n  institution = {{Decision Systems Group/Harvard Medical School}},\n  url = {http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.57.9172&rep=rep1&type=pdf},\n  copyright = {All rights reserved},\n  file = {/Users/staal/Documents/Zotero/storage/5ZT2ZS5U/ambighardness.pdf;/Users/staal/Documents/Zotero/storage/8VRUQH7A/ambighardness.pdf;/Users/staal/Documents/Zotero/storage/RE8AKXKE/ambighardness.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Building an Asynchronous Web-Based Tool for Machine Learning Classification.\n \n \n \n\n\n \n Weber, G.; Vinterbo, S.; and Ohno-Machado, L.\n\n\n \n\n\n\n JAMIA, Suppl. S: 869–73. 2002.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{Weber2002,\n  title = {Building an Asynchronous Web-Based Tool for Machine Learning Classification.},\n  author = {Weber, Griffin and Vinterbo, Staal and {Ohno-Machado}, Lucila},\n  year = {2002},\n  journal = {JAMIA},\n  volume = {Suppl. S},\n  pages = {869--73},\n  abstract = {Various unsupervised and supervised learning methods including support vector machines, classification trees, linear discriminant analysis and nearest neighbor classifiers have been used to classify high-throughput gene expression data. Simpler and more widely accepted statistical tools have not yet been used for this purpose, hence proper comparisons between classification methods have not been conducted. We developed free software that implements logistic regression with stepwise variable selection as a quick and simple method for initial exploration of important genetic markers in disease classification. To implement the algorithm and allow our collaborators in remote locations to evaluate and compare its results against those of other methods, we developed a user-friendly asynchronous web-based application with a minimal amount of programming using free, downloadable software tools. With this program, we show that classification using logistic regression can perform as well as other more sophisticated algorithms, and it has the advantages of being easy to interpret and reproduce. By making the tool freely and easily available, we hope to promote the comparison of classification methods. In addition, we believe our web application can be used as a model for other bioinformatics laboratories that need to develop web-based analysis tools in a short amount of time and on a limited budget.},\n  copyright = {All rights reserved},\n  pii = {D020001919},\n  pubmedid = {12463949},\n  keywords = {12463949,Algorithms,Anonymous Testing,Artificial Intelligence,Carcinoma,Child,Comparative Study,Computerized,Confidentiality,Databases,Diagnosis,Differential,Disclosure,DNA,Gene Expression,Gene Expression Profiling,Gene Expression Regulation,Genetic Markers,Humans,Internet,Logistic Models,Lung Neoplasms,Medical Records Systems,Multivariate Analysis,Neoplasm,Neoplasms,Neoplastic,Neural Networks (Computer),Non-U.S. Gov't,Oligonucleotide Array Sequence Analysis,P.H.S.,Privacy,Research Support,Rhabdomyosarcoma,Sarcoma,Small Cell,Software,U.S. Gov't},\n  file = {/Users/staal/Documents/Zotero/storage/26TPF5RW/amia02-weber.pdf;/Users/staal/Documents/Zotero/storage/FRPABBPG/amia02-weber.pdf;/Users/staal/Documents/Zotero/storage/GME7HZA7/amia02-weber.pdf}\n}\n\n
\n
\n\n\n
\n Various unsupervised and supervised learning methods including support vector machines, classification trees, linear discriminant analysis and nearest neighbor classifiers have been used to classify high-throughput gene expression data. Simpler and more widely accepted statistical tools have not yet been used for this purpose, hence proper comparisons between classification methods have not been conducted. We developed free software that implements logistic regression with stepwise variable selection as a quick and simple method for initial exploration of important genetic markers in disease classification. To implement the algorithm and allow our collaborators in remote locations to evaluate and compare its results against those of other methods, we developed a user-friendly asynchronous web-based application with a minimal amount of programming using free, downloadable software tools. With this program, we show that classification using logistic regression can perform as well as other more sophisticated algorithms, and it has the advantages of being easy to interpret and reproduce. By making the tool freely and easily available, we hope to promote the comparison of classification methods. In addition, we believe our web application can be used as a model for other bioinformatics laboratories that need to develop web-based analysis tools in a short amount of time and on a limited budget.\n
\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2001\n \n \n (3)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n A Comparison of Machine Learning Methods for the Diagnosis of Pigmented Skin Lesions.\n \n \n \n \n\n\n \n Dreiseitl, S.; Ohno-Machado, L.; Kittler, H.; Vinterbo, S.; Billhardt, H.; and Binder, M.\n\n\n \n\n\n\n J Biomed Inform, 34(1): 28–36. February 2001.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{Dreiseitl2001,\n  title = {A Comparison of Machine Learning Methods for the Diagnosis of Pigmented Skin Lesions.},\n  author = {Dreiseitl, S. and {Ohno-Machado}, L. and Kittler, H. and Vinterbo, S. and Billhardt, H. and Binder, M.},\n  year = {2001},\n  month = feb,\n  journal = {J Biomed Inform},\n  volume = {34},\n  number = {1},\n  pages = {28--36},\n  doi = {10.1006/jbin.2001.1004},\n  url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.13.2630},\n  abstract = {We analyze the discriminatory power of k-nearest neighbors, logistic regression, artificial neural networks (ANNs), decision tress, and support vector machines (SVMs) on the task of classifying pigmented skin lesions as common nevi, dysplastic nevi, or melanoma. Three different classification tasks were used as benchmarks: the dichotomous problem of distinguishing common nevi from dysplastic nevi and melanoma, the dichotomous problem of distinguishing melanoma from common and dysplastic nevi, and the trichotomous problem of correctly distinguishing all three classes. Using ROC analysis to measure the discriminatory power of the methods shows that excellent results for specific classification problems in the domain of pigmented skin lesions can be achieved with machine-learning methods. On both dichotomous and trichotomous tasks, logistic regression, ANNs, and SVMs performed on about the same level, with k-nearest neighbors and decision trees performing worse.},\n  copyright = {All rights reserved},\n  pubmedid = {11376540},\n  keywords = {11376540,Adult,Algorithms,Anonymous Testing,Artificial Intelligence,Bias (Epidemiology),Carcinoma,Child,Comparative Study,Computational Biology,Computer-Assisted,Computerized,Confidentiality,Data Interpretation,Databases,Decision Trees,Demograph,Diagnosis,Differential,Disclosure,DNA,Female,Gene Expression,Gene Expression Profiling,Gene Expression Regulation,Genetic Markers,Humans,Internet,Logistic Models,Lung Neoplasms,Male,Medical Records Systems,Melanoma,Messenger,Middle Aged,Multivariate Analysis,Neoplasm,Neoplasms,Neoplastic,Neural Networks (Computer),Nevus,Non-U.S. Gov't,Oligonucleotide Array Sequence Analysis,P.H.S.,Pigmented,Privacy,Research Support,Rhabdomyosarcoma,RNA,ROC Curve,Sarcoma,Skin Diseases,Skin Neoplasms,Skin Pigmentation,Small Cell,Software,Statistical,Statistics,U.S. Gov't,y},\n  file = {/Users/staal/Documents/Zotero/storage/2JCESE87/dreisetl2001-JBI.pdf;/Users/staal/Documents/Zotero/storage/6MG8J3W4/dreisetl2001-JBI.pdf;/Users/staal/Documents/Zotero/storage/FW4VR7RH/dreisetl2001-JBI.pdf}\n}\n\n
\n
\n\n\n
\n We analyze the discriminatory power of k-nearest neighbors, logistic regression, artificial neural networks (ANNs), decision tress, and support vector machines (SVMs) on the task of classifying pigmented skin lesions as common nevi, dysplastic nevi, or melanoma. Three different classification tasks were used as benchmarks: the dichotomous problem of distinguishing common nevi from dysplastic nevi and melanoma, the dichotomous problem of distinguishing melanoma from common and dysplastic nevi, and the trichotomous problem of correctly distinguishing all three classes. Using ROC analysis to measure the discriminatory power of the methods shows that excellent results for specific classification problems in the domain of pigmented skin lesions can be achieved with machine-learning methods. On both dichotomous and trichotomous tasks, logistic regression, ANNs, and SVMs performed on about the same level, with k-nearest neighbors and decision trees performing worse.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Effects of Case Removal in Prognostic Models.\n \n \n \n \n\n\n \n Ohno-Machado, L.; and Vinterbo, S.\n\n\n \n\n\n\n Methods Inf Med, 40(1): 32–8. March 2001.\n \n\n\n\n
\n\n\n\n \n \n \"EffectsPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n  \n \n abstract \n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n \n\n\n\n
\n 
@article{Ohno-Machado2001a,\n  title = {Effects of Case Removal in Prognostic Models.},\n  author = {{Ohno-Machado}, L. and Vinterbo, S.},\n  year = {2001},\n  month = mar,\n  journal = {Methods Inf Med},\n  volume = {40},\n  number = {1},\n  pages = {32--8},\n  url = {http://www.ncbi.nlm.nih.gov/pubmed/11310157},\n  abstract = {Constructing and updating prognostic models that learn from training cases is a time-consuming task. The more compact, and yet informative, the training sets are, the faster one can build and properly evaluate such models. We have compared different regression diagnostic methods for selection and removal of training cases in prognostic models. Univariate determinations were performed using classical regression diagnostic statistics. Multivariate determinations were performed using (1) a sequential "backward" selection of cases, and (2) a non-sequential genetic algorithm. The genetic algorithm produced final models that kept few cases and retained predictive capability. A genetic algorithm approach to case selection may be better suited for guiding removal of cases in training sets than a univariate or a sequential multivariate approach, possibly because of its ability to detect sets of cases that are influential en bloc but may not be sufficiently influential when considered in isolation.},\n  copyright = {All rights reserved},\n  pubmedid = {11310157},\n  keywords = {11310157,Adult,Algorithms,Anonymous Testing,Artificial Intelligence,Bias (Epidemiology),Carcinoma,Child,Comparative Study,Computational Biology,Computer-Assisted,Computerized,Confidentiality,Data Interpretation,Databases,Decision Trees,Demograph,Diagnosis,Differential,Disclosure,DNA,Female,Gene Expression,Gene Expression Profiling,Gene Expression Regulation,Genetic,Genetic Markers,Humans,Internet,Logistic Models,Lung Neoplasms,Male,Medical Records Systems,Melanoma,Messenger,Middle Aged,Models,Multivariate Analysis,Myocardial Infarction,Neoplasm,Neoplasms,Neoplastic,Neural Networks (Computer),Nevus,Non-U.S. Gov't,Oligonucleotide Array Sequence Analysis,P.H.S.,Pigmented,Privacy,Prognosis,Research Support,Rhabdomyosarcoma,RNA,ROC Curve,Sarcoma,Skin Diseases,Skin Neoplasms,Skin Pigmentation,Small Cell,Software,Statistical,Statistics,U.S. Gov't,Wounds and Injuries,y},\n  file = {/Users/staal/Documents/Zotero/storage/6DPR2UNV/CaseSelectionMIM.pdf;/Users/staal/Documents/Zotero/storage/B3FSZTCR/CaseSelectionMIM.pdf;/Users/staal/Documents/Zotero/storage/WTZJ5XXM/CaseSelectionMIM.pdf}\n}\n\n
\n
\n\n\n
\n Constructing and updating prognostic models that learn from training cases is a time-consuming task. The more compact, and yet informative, the training sets are, the faster one can build and properly evaluate such models. We have compared different regression diagnostic methods for selection and removal of training cases in prognostic models. Univariate determinations were performed using classical regression diagnostic statistics. Multivariate determinations were performed using (1) a sequential \"backward\" selection of cases, and (2) a non-sequential genetic algorithm. The genetic algorithm produced final models that kept few cases and retained predictive capability. A genetic algorithm approach to case selection may be better suited for guiding removal of cases in training sets than a univariate or a sequential multivariate approach, possibly because of its ability to detect sets of cases that are influential en bloc but may not be sufficiently influential when considered in isolation.\n
\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Hiding Information by Cell Suppression.\n \n \n \n\n\n \n Vinterbo, S. A.; Ohno-Machado, L.; and Dreiseitl, S.\n\n\n \n\n\n\n JAMIA, Suppl. S: 726–730. 2001.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Vinterbo2001,\n  title = {Hiding Information by Cell Suppression},\n  author = {Vinterbo, S. A. and {Ohno-Machado}, L. and Dreiseitl, S.},\n  year = {2001},\n  journal = {JAMIA},\n  volume = {Suppl. S},\n  pages = {726--730},\n  copyright = {All rights reserved},\n  owner = {staal}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 2000\n \n \n (4)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Building Knowledge in a Complex Preterm Birth Problem Domain.\n \n \n \n \n\n\n \n Goodwin, L. K.; Maher, S. G.; Ohno-Machado, L.; Iannacchione, M. A.; Crockett, P.; Dreiseitl, S.; Vinterbo, S.; and Hammond, W. E.\n\n\n \n\n\n\n JAMIA, Suppl. S: 305–309. 2000.\n \n\n\n\n
\n\n\n\n \n \n \"BuildingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Goodwin2000,\n  title = {Building Knowledge in a Complex Preterm Birth Problem Domain},\n  author = {Goodwin, L. K. and Maher, S. G. and {Ohno-Machado}, L. and Iannacchione, M. A. and Crockett, P. and Dreiseitl, S. and Vinterbo, S. and Hammond, W. E.},\n  year = {2000},\n  journal = {JAMIA},\n  volume = {Suppl. S},\n  pages = {305--309},\n  url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2243761/},\n  copyright = {All rights reserved},\n  owner = {staal},\n  file = {/Users/staal/Documents/Zotero/storage/KW42BQEE/Preterm Goodwin D200929.PDF;/Users/staal/Documents/Zotero/storage/XGHRTHGG/Preterm Goodwin D200929.PDF;/Users/staal/Documents/Zotero/storage/Z74T6H99/Preterm Goodwin D200929.PDF}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Set-Covering Approach to Specific Search for Literature about Human Genes.\n \n \n \n \n\n\n \n Jenssen, T. K.; and Vinterbo, S.\n\n\n \n\n\n\n JAMIA, Suppl. S: 384–388. 2000.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Jenssen2000,\n  title = {A Set-Covering Approach to Specific Search for Literature about Human Genes},\n  author = {Jenssen, T. K. and Vinterbo, S.},\n  year = {2000},\n  journal = {JAMIA},\n  volume = {Suppl. S},\n  pages = {384--388},\n  url = {http://www.ncbi.nlm.nih.gov/pubmed/11079910},\n  copyright = {All rights reserved},\n  owner = {staal},\n  file = {/Users/staal/Documents/Zotero/storage/H4UR5TXM/amia00.PDF;/Users/staal/Documents/Zotero/storage/IWBDMUZI/amia00.PDF;/Users/staal/Documents/Zotero/storage/ZZZD8UNQ/amia00.PDF}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Genetic Algorithm Approach to Multidisorder Diagnosis.\n \n \n \n \n\n\n \n Vinterbo, S.; and Ohno-Machado, L.\n\n\n \n\n\n\n Artificial Intelligence in Medicine, 18(2): 117–132. 2000.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n \n doi\n  \n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{sv:multidiag99,\n  title = {A Genetic Algorithm Approach to Multidisorder Diagnosis},\n  author = {Vinterbo, S. and {Ohno-Machado}, L.},\n  year = {2000},\n  journal = {Artificial Intelligence in Medicine},\n  volume = {18},\n  number = {2},\n  pages = {117--132},\n  doi = {10.1016/S0933-3657(99)00036-6},\n  url = {self/journal/gamdd.pdf},\n  copyright = {All rights reserved},\n  file = {/Users/staal/Documents/Zotero/storage/86PNWGGV/gamdd.pdf;/Users/staal/Documents/Zotero/storage/9S98ZBXB/gamdd.pdf;/Users/staal/Documents/Zotero/storage/XA79MZRS/gamdd.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Relational Approach to Defining Document Set Relevance: An Application in Human Genetics.\n \n \n \n \n\n\n \n Jenssen, T.; and Vinterbo, S.\n\n\n \n\n\n\n , (7/00). 2000.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{vinterbo:genlit00,\n  title = {A {{Relational Approach}} to {{Defining Document Set Relevance}}: {{An Application}} in {{Human Genetics}}},\n  author = {Jenssen, T.-K. and Vinterbo, S.},\n  year = {2000},\n  number = {7/00},\n  url = {self/techraps/scare-techrap.pdf},\n  copyright = {All rights reserved},\n  annotation = {ISSN 0802-6394},\n  file = {/Users/staal/Documents/Zotero/storage/XICD6H4I/scare-techrap.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 1999\n \n \n (7)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Evaluating Variable Selection Methods for Diagnosis of Myocardial Infarction.\n \n \n \n \n\n\n \n Dreiseitl, S.; Ohno-Machado, L.; and Vinterbo, S.\n\n\n \n\n\n\n JAMIA, Suppl. S: 246–250. 1999.\n \n\n\n\n
\n\n\n\n \n \n \"EvaluatingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Dreiseitl1999,\n  title = {Evaluating Variable Selection Methods for Diagnosis of Myocardial Infarction},\n  author = {Dreiseitl, S. and {Ohno-Machado}, L. and Vinterbo, S.},\n  year = {1999},\n  journal = {JAMIA},\n  volume = {Suppl. S},\n  pages = {246--250},\n  url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2232647/},\n  copyright = {All rights reserved},\n  owner = {staal}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Influential Case Detection in Medical Prognosis.\n \n \n \n\n\n \n Ohno-Machado, L.; and Vinterbo, S.\n\n\n \n\n\n\n In AIMDM'99 Workshop on Prognostic Models in Medicine, pages 33–37, 1999. \n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{lom:casesel99,\n  title = {Influential Case Detection in Medical Prognosis},\n  booktitle = {{{AIMDM}}'99 {{Workshop}} on {{Prognostic Models}} in {{Medicine}}},\n  author = {{Ohno-Machado}, L. and Vinterbo, S.},\n  year = {1999},\n  pages = {33--37},\n  copyright = {All rights reserved}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Clinical Data Processing Tools: A Machine Learning Resource.\n \n \n \n\n\n \n Ohno-Machado, L.; Vinterbo, S.; Ohrn, A.; and Dreiseitl, S.\n\n\n \n\n\n\n In Proc AMIA Symp, volume Suppl. S, pages 1132–1132, 1999. \n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{Ohno-Machado1999,\n  title = {Clinical Data Processing Tools: {{A}} Machine Learning Resource},\n  booktitle = {Proc {{AMIA Symp}}},\n  author = {{Ohno-Machado}, L. and Vinterbo, S. and Ohrn, A. and Dreiseitl, S.},\n  year = {1999},\n  volume = {Suppl. S},\n  pages = {1132--1132},\n  copyright = {All rights reserved},\n  owner = {staal},\n  annotation = {Symposium abstract}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n Computer Aided Image Interpretation.\n \n \n \n\n\n \n Vinterbo, S.; Kittler, H.; Seltenheim, M.; Pehamberger, H.; and Binder, M.\n\n\n \n\n\n\n Skin Research and Technology, 5(2): 155. 1999.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{sv:melanoma99,\n  title = {Computer Aided Image Interpretation},\n  author = {Vinterbo, S. and Kittler, H. and Seltenheim, M. and Pehamberger, H. and Binder, M.},\n  year = {1999},\n  journal = {Skin Research and Technology},\n  volume = {5},\n  number = {2},\n  pages = {155},\n  copyright = {All rights reserved},\n  annotation = {ISSI'99 abstract}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n A Recalibration Method for Predictive Models with Dichotomous Outcomes.\n \n \n \n\n\n \n Vinterbo, S.; and Ohno-Machado, L.\n\n\n \n\n\n\n In Predictive Models in Medicine: Some Methods for Construction and Adaptation. Norwegian University of Science and Technology, 1999.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@incollection{sv:recal99,\n  title = {A Recalibration Method for Predictive Models with Dichotomous Outcomes},\n  booktitle = {Predictive {{Models}} in {{Medicine}}: {{Some Methods}} for {{Construction}} and {{Adaptation}}},\n  author = {Vinterbo, S. and {Ohno-Machado}, L.},\n  year = {1999},\n  publisher = {{Norwegian University of Science and Technology}},\n  copyright = {All rights reserved},\n  crossref = {vinterbo99:phd},\n  file = {/Users/staal/Documents/Zotero/storage/GIEJZP3R/Vinterbo1999-PhD.pdf;/Users/staal/Documents/Zotero/storage/KC529UF7/Vinterbo1999-PhD.pdf;/Users/staal/Documents/Zotero/storage/TS2A5EEJ/Vinterbo1999-PhD.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n Predictive Models in Medicine: Some Methods for Construction and Adaptation.\n \n \n \n \n\n\n \n Vinterbo, S.\n\n\n \n\n\n\n Ph.D. Thesis, Norwegian University of Science and Technology, 1999.\n \n\n\n\n
\n\n\n\n \n \n \"PredictivePaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@phdthesis{vinterbo_predictive_1999,\n  title = {Predictive {{Models}} in {{Medicine}}: {{Some Methods}} for {{Construction}} and {{Adaptation}}},\n  author = {Vinterbo, S.},\n  year = {1999},\n  url = {pubs/self/Vinterbo1999-PhD.pdf},\n  school = {Norwegian University of Science and Technology},\n  annotation = {ISBN 82-7984-011-7, ISSN 0802-6394},\n  file = {/Users/staal/Documents/Zotero/storage/A9ZMT2CQ/Vinterbo1999-PhD.pdf;/Users/staal/Documents/Zotero/storage/NR5ZIT3G/Vinterbo1999-PhD.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n
\n \n\n \n \n \n \n \n \n A Genetic Algorithm to Select Variables in Logistic Regression: Example in the Domain of Myocardial Infarction.\n \n \n \n \n\n\n \n Vinterbo, S.; and Ohno-Machado, L.\n\n\n \n\n\n\n JAMIA, Suppl. S: 984–988. 1999.\n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n  \n \n 1 download\n \n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Vinterbo1999,\n  title = {A Genetic Algorithm to Select Variables in Logistic Regression: {{Example}} in the Domain of Myocardial Infarction},\n  author = {Vinterbo, S. and {Ohno-Machado}, L.},\n  year = {1999},\n  journal = {JAMIA},\n  volume = {Suppl. S},\n  pages = {984--988},\n  url = {http://www.ncbi.nlm.nih.gov/pmc/articles/PMC2232877/},\n  copyright = {All rights reserved},\n  owner = {staal},\n  file = {/Users/staal/Documents/Zotero/storage/3R5DWJUX/Vinterbo1999.pdf;/Users/staal/Documents/Zotero/storage/DMTGVQDI/amia99.pdf;/Users/staal/Documents/Zotero/storage/N9NTXXJ7/amia99.pdf;/Users/staal/Documents/Zotero/storage/PW5MI9MQ/Vinterbo1999.pdf;/Users/staal/Documents/Zotero/storage/VJZWSNTW/amia99.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 1998\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n A Description of a Strategy for Building Rough Set Classifiers Using Performance Filtering of Reducts.\n \n \n \n \n\n\n \n Vinterbo, S.; Ohno-Machado, L.; and Fraser, H.\n\n\n \n\n\n\n In Zimmermann, H.; and Lieven, K., editor(s), Proc.Sixth European Congress on Intelligent Techniques and Soft Computing (EUFIT'98), pages 975–979, 1998. \n \n\n\n\n
\n\n\n\n \n \n \"APaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@inproceedings{sv:perffilt98,\n  title = {A {{Description}} of a {{Strategy}} for {{Building Rough Set Classifiers Using Performance Filtering}} of {{Reducts}}},\n  booktitle = {Proc.{{Sixth European Congress}} on {{Intelligent Techniques}} and {{Soft Computing}} ({{EUFIT}}'98)},\n  author = {Vinterbo, S. and {Ohno-Machado}, L. and Fraser, H.},\n  editor = {Zimmermann, Hans-J{\\"u}rgen and Lieven, Karl},\n  year = {1998},\n  pages = {975--979},\n  url = {self/Proceedings/eufit98.pdf},\n  copyright = {All rights reserved},\n  optaddress = {Aachen, Germany},\n  optbooktitle = {Proc.Sixth European Congress on Intelligent Techniques and Soft Computing (EUFIT'98)},\n  optcrossref = {zimmermann:eufit98},\n  optmonth = {sep},\n  optvolume = {2},\n  optyear = {1998},\n  file = {/Users/staal/Documents/Zotero/storage/KDCTC9CP/eufit98.pdf;/Users/staal/Documents/Zotero/storage/KEMS46U2/eufit98.pdf;/Users/staal/Documents/Zotero/storage/TF7I3SR9/eufit98.pdf}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 1997\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n \n Modelling Cardiac Patient Set Residuals Using Rough Sets.\n \n \n \n \n\n\n \n Ohrn, A.; Vinterbo, S.; Szymanski, P.; and Komorowski, J.\n\n\n \n\n\n\n JAMIA, Suppl. S: 203–207. 1997.\n \n\n\n\n
\n\n\n\n \n \n \"ModellingPaper\n  \n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@article{Ohrn1997,\n  title = {Modelling Cardiac Patient Set Residuals Using Rough Sets},\n  author = {Ohrn, A. and Vinterbo, S. and Szymanski, P. and Komorowski, J.},\n  year = {1997},\n  journal = {JAMIA},\n  volume = {Suppl. S},\n  pages = {203--207},\n  url = {http://www.ncbi.nlm.nih.gov/pubmed/9357617},\n  copyright = {All rights reserved},\n  owner = {staal}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n
\n
\n  \n 1994\n \n \n (1)\n \n \n
\n
\n \n \n
\n \n\n \n \n \n \n \n Infinite Families of Simple Groups.\n \n \n \n\n\n \n Vinterbo, S.\n\n\n \n\n\n\n Master's thesis, Norwegian Institute of Technology (NTH), February 1994.\n \n\n\n\n
\n\n\n\n \n\n \n\n \n link\n  \n \n\n bibtex\n \n\n \n\n \n\n \n \n \n \n \n \n \n\n  \n \n \n\n\n\n
\n 
@mastersthesis{sv:master94,\n  title = {Infinite {{Families}} of {{Simple Groups}}},\n  author = {Vinterbo, S.},\n  year = {1994},\n  month = feb,\n  copyright = {All rights reserved},\n  school = {Norwegian Institute of Technology (NTH)}\n}\n\n
\n
\n\n\n\n
\n\n\n\n\n\n
\n
\n\n\n\n\n
\n\n\n \n\n \n \n \n \n\n
\n"}; document.write(bibbase_data.data);