@article{ning2019feature,
  title={Feature extraction for phenotyping from semantic and knowledge resources},
  author={Ning, Wenxin and Chan, Stephanie and Beam, Andrew and Yu, Ming and Geva, Alon and Liao, Katherine and Mullen, Mary and Mandl, Kenneth D and Kohane, Isaac and Cai, Tianxi and others},
  journal={Journal of biomedical informatics},
  volume={91},
  pages={103122},
  year={2019},
  keywords={NLP, Distributed Representations},
  abstract={Phenotyping algorithms can efficiently and accurately identify patients with a specific disease phenotype and construct electronic health records (EHR)-based cohorts for subsequent clinical or genomic studies. Previous studies have introduced unsupervised EHR-based feature selection methods that yielded algorithms with high accuracy. However, those selection methods still require expert intervention to tweak the parameter settings according to the EHR data distribution for each phenotype. To further accelerate the development of phenotyping algorithms, we propose a fully automated and robust unsupervised feature selection method that leverages only publicly available medical knowledge sources, instead of EHR data.},
  url_Paper={},
  publisher={Academic Press}
}

{"_id":"heNqpNfrcQL9pXrBb","bibbaseid":"ning-chan-beam-yu-geva-liao-mullen-mandl-etal-featureextractionforphenotypingfromsemanticandknowledgeresources-2019","authorIDs":[],"author_short":["Ning, W.","Chan, S.","Beam, A.","Yu, M.","Geva, A.","Liao, K.","Mullen, M.","Mandl, K. D","Kohane, I.","Cai, T.","others"],"bibdata":{"bibtype":"article","type":"article","title":"Feature extraction for phenotyping from semantic and knowledge resources","author":[{"propositions":[],"lastnames":["Ning"],"firstnames":["Wenxin"],"suffixes":[]},{"propositions":[],"lastnames":["Chan"],"firstnames":["Stephanie"],"suffixes":[]},{"propositions":[],"lastnames":["Beam"],"firstnames":["Andrew"],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Ming"],"suffixes":[]},{"propositions":[],"lastnames":["Geva"],"firstnames":["Alon"],"suffixes":[]},{"propositions":[],"lastnames":["Liao"],"firstnames":["Katherine"],"suffixes":[]},{"propositions":[],"lastnames":["Mullen"],"firstnames":["Mary"],"suffixes":[]},{"propositions":[],"lastnames":["Mandl"],"firstnames":["Kenneth","D"],"suffixes":[]},{"propositions":[],"lastnames":["Kohane"],"firstnames":["Isaac"],"suffixes":[]},{"propositions":[],"lastnames":["Cai"],"firstnames":["Tianxi"],"suffixes":[]},{"firstnames":[],"propositions":[],"lastnames":["others"],"suffixes":[]}],"journal":"Journal of biomedical informatics","volume":"91","pages":"103122","year":"2019","keywords":"NLP, Distributed Representations","abstract":"Phenotyping algorithms can efficiently and accurately identify patients with a specific disease phenotype and construct electronic health records (EHR)-based cohorts for subsequent clinical or genomic studies. Previous studies have introduced unsupervised EHR-based feature selection methods that yielded algorithms with high accuracy. However, those selection methods still require expert intervention to tweak the parameter settings according to the EHR data distribution for each phenotype. To further accelerate the development of phenotyping algorithms, we propose a fully automated and robust unsupervised feature selection method that leverages only publicly available medical knowledge sources, instead of EHR data.","url_paper":"","publisher":"Academic Press","bibtex":"@article{ning2019feature,\n title={Feature extraction for phenotyping from semantic and knowledge resources},\n author={Ning, Wenxin and Chan, Stephanie and Beam, Andrew and Yu, Ming and Geva, Alon and Liao, Katherine and Mullen, Mary and Mandl, Kenneth D and Kohane, Isaac and Cai, Tianxi and others},\n journal={Journal of biomedical informatics},\n volume={91},\n pages={103122},\n year={2019},\n keywords={NLP, Distributed Representations},\n abstract={Phenotyping algorithms can efficiently and accurately identify patients with a specific disease phenotype and construct electronic health records (EHR)-based cohorts for subsequent clinical or genomic studies. Previous studies have introduced unsupervised EHR-based feature selection methods that yielded algorithms with high accuracy. However, those selection methods still require expert intervention to tweak the parameter settings according to the EHR data distribution for each phenotype. To further accelerate the development of phenotyping algorithms, we propose a fully automated and robust unsupervised feature selection method that leverages only publicly available medical knowledge sources, instead of EHR data.},\n url_Paper={},\n publisher={Academic Press}\n}\n\n\n","author_short":["Ning, W.","Chan, S.","Beam, A.","Yu, M.","Geva, A.","Liao, K.","Mullen, M.","Mandl, K. D","Kohane, I.","Cai, T.","others"],"key":"ning2019feature","id":"ning2019feature","bibbaseid":"ning-chan-beam-yu-geva-liao-mullen-mandl-etal-featureextractionforphenotypingfromsemanticandknowledgeresources-2019","role":"author","urls":{" paper":"https://www.dropbox.com/s/0k6pa735xx3gr9i/citations.txt?dl=1"},"keyword":["NLP","Distributed Representations"],"metadata":{"authorlinks":{}},"downloads":15,"html":""},"bibtype":"article","biburl":"https://www.dropbox.com/s/0k6pa735xx3gr9i/citations.txt?dl=1","creationDate":"2019-07-24T12:46:58.186Z","downloads":15,"keywords":["nlp","distributed representations"],"search_terms":["feature","extraction","phenotyping","semantic","knowledge","resources","ning","chan","beam","yu","geva","liao","mullen","mandl","kohane","cai","others"],"title":"Feature extraction for phenotyping from semantic and knowledge resources","year":2019,"dataSources":["2LQLmS62hSLmYBK2a","NwvhK26aS7FPij9ck","TjsANBkNMi65yEjCQ","R7XXNLtmcExJiuMoA"]}