Dynamic Bayesian networks as prognostic models for clinical patient management. van Gerven, M., A., J., Taal, B., G., & Lucas, P., J., F. Journal of biomedical informatics, 41(4):515-29, 8, 2008. ![Dynamic Bayesian networks as prognostic models for clinical patient management. [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website doi abstract bibtex Prognostic models in medicine are usually been built using simple decision rules, proportional hazards models, or Markov models. Dynamic Bayesian networks (DBNs) offer an approach that allows for the incorporation of the causal and temporal nature of medical domain knowledge as elicited from domain experts, thereby allowing for detailed prognostic predictions. The aim of this paper is to describe the considerations that must be taken into account when constructing a DBN for complex medical domains and to demonstrate their usefulness in practice. To this end, we focus on the construction of a DBN for prognosis of carcinoid patients, compare performance with that of a proportional hazards model, and describe predictions for three individual patients. We show that the DBN can make detailed predictions, about not only patient survival, but also other variables of interest, such as disease progression, the effect of treatment, and the development of complications. Strengths and limitations of our approach are discussed and compared with those offered by traditional methods.
@article{
title = {Dynamic Bayesian networks as prognostic models for clinical patient management.},
type = {article},
year = {2008},
keywords = {Algorithms,Bayes Theorem,Carcinoid Tumor,Carcinoid Tumor: diagnosis,Carcinoid Tumor: mortality,Decision Support Systems, Clinical,Diagnosis, Computer-Assisted,Diagnosis, Computer-Assisted: methods,Humans,Neural Networks (Computer),Prognosis,Risk Assessment,Risk Assessment: methods,Risk Factors,Survival Analysis,Survival Rate},
pages = {515-29},
volume = {41},
websites = {http://www.sciencedirect.com/science/article/pii/S1532046408000154},
month = {8},
id = {812f1eae-d7e5-3eff-85a4-ec3d22a0c90a},
created = {2015-04-12T20:17:33.000Z},
accessed = {2015-04-11},
file_attached = {false},
profile_id = {95e10851-cdf3-31de-9f82-1ab629e601b0},
group_id = {838ecfe2-7c01-38b2-970d-875a87910530},
last_modified = {2017-03-14T14:27:28.880Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
private_publication = {false},
abstract = {Prognostic models in medicine are usually been built using simple decision rules, proportional hazards models, or Markov models. Dynamic Bayesian networks (DBNs) offer an approach that allows for the incorporation of the causal and temporal nature of medical domain knowledge as elicited from domain experts, thereby allowing for detailed prognostic predictions. The aim of this paper is to describe the considerations that must be taken into account when constructing a DBN for complex medical domains and to demonstrate their usefulness in practice. To this end, we focus on the construction of a DBN for prognosis of carcinoid patients, compare performance with that of a proportional hazards model, and describe predictions for three individual patients. We show that the DBN can make detailed predictions, about not only patient survival, but also other variables of interest, such as disease progression, the effect of treatment, and the development of complications. Strengths and limitations of our approach are discussed and compared with those offered by traditional methods.},
bibtype = {article},
author = {van Gerven, Marcel A J and Taal, Babs G and Lucas, Peter J F},
doi = {10.1016/j.jbi.2008.01.006},
journal = {Journal of biomedical informatics},
number = {4}
}
Downloads: 0
{"_id":"8uhmkPq4SgFtowWBb","authorIDs":[],"author_short":["van Gerven, M., A., J.","Taal, B., G.","Lucas, P., J., F."],"bibbaseid":"vangerven-taal-lucas-dynamicbayesiannetworksasprognosticmodelsforclinicalpatientmanagement-2008","bibdata":{"title":"Dynamic Bayesian networks as prognostic models for clinical patient management.","type":"article","year":"2008","keywords":"Algorithms,Bayes Theorem,Carcinoid Tumor,Carcinoid Tumor: diagnosis,Carcinoid Tumor: mortality,Decision Support Systems, Clinical,Diagnosis, Computer-Assisted,Diagnosis, Computer-Assisted: methods,Humans,Neural Networks (Computer),Prognosis,Risk Assessment,Risk Assessment: methods,Risk Factors,Survival Analysis,Survival Rate","pages":"515-29","volume":"41","websites":"http://www.sciencedirect.com/science/article/pii/S1532046408000154","month":"8","id":"812f1eae-d7e5-3eff-85a4-ec3d22a0c90a","created":"2015-04-12T20:17:33.000Z","accessed":"2015-04-11","file_attached":false,"profile_id":"95e10851-cdf3-31de-9f82-1ab629e601b0","group_id":"838ecfe2-7c01-38b2-970d-875a87910530","last_modified":"2017-03-14T14:27:28.880Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"private_publication":false,"abstract":"Prognostic models in medicine are usually been built using simple decision rules, proportional hazards models, or Markov models. Dynamic Bayesian networks (DBNs) offer an approach that allows for the incorporation of the causal and temporal nature of medical domain knowledge as elicited from domain experts, thereby allowing for detailed prognostic predictions. The aim of this paper is to describe the considerations that must be taken into account when constructing a DBN for complex medical domains and to demonstrate their usefulness in practice. To this end, we focus on the construction of a DBN for prognosis of carcinoid patients, compare performance with that of a proportional hazards model, and describe predictions for three individual patients. We show that the DBN can make detailed predictions, about not only patient survival, but also other variables of interest, such as disease progression, the effect of treatment, and the development of complications. Strengths and limitations of our approach are discussed and compared with those offered by traditional methods.","bibtype":"article","author":"van Gerven, Marcel A J and Taal, Babs G and Lucas, Peter J F","doi":"10.1016/j.jbi.2008.01.006","journal":"Journal of biomedical informatics","number":"4","bibtex":"@article{\n title = {Dynamic Bayesian networks as prognostic models for clinical patient management.},\n type = {article},\n year = {2008},\n keywords = {Algorithms,Bayes Theorem,Carcinoid Tumor,Carcinoid Tumor: diagnosis,Carcinoid Tumor: mortality,Decision Support Systems, Clinical,Diagnosis, Computer-Assisted,Diagnosis, Computer-Assisted: methods,Humans,Neural Networks (Computer),Prognosis,Risk Assessment,Risk Assessment: methods,Risk Factors,Survival Analysis,Survival Rate},\n pages = {515-29},\n volume = {41},\n websites = {http://www.sciencedirect.com/science/article/pii/S1532046408000154},\n month = {8},\n id = {812f1eae-d7e5-3eff-85a4-ec3d22a0c90a},\n created = {2015-04-12T20:17:33.000Z},\n accessed = {2015-04-11},\n file_attached = {false},\n profile_id = {95e10851-cdf3-31de-9f82-1ab629e601b0},\n group_id = {838ecfe2-7c01-38b2-970d-875a87910530},\n last_modified = {2017-03-14T14:27:28.880Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n private_publication = {false},\n abstract = {Prognostic models in medicine are usually been built using simple decision rules, proportional hazards models, or Markov models. Dynamic Bayesian networks (DBNs) offer an approach that allows for the incorporation of the causal and temporal nature of medical domain knowledge as elicited from domain experts, thereby allowing for detailed prognostic predictions. The aim of this paper is to describe the considerations that must be taken into account when constructing a DBN for complex medical domains and to demonstrate their usefulness in practice. To this end, we focus on the construction of a DBN for prognosis of carcinoid patients, compare performance with that of a proportional hazards model, and describe predictions for three individual patients. We show that the DBN can make detailed predictions, about not only patient survival, but also other variables of interest, such as disease progression, the effect of treatment, and the development of complications. Strengths and limitations of our approach are discussed and compared with those offered by traditional methods.},\n bibtype = {article},\n author = {van Gerven, Marcel A J and Taal, Babs G and Lucas, Peter J F},\n doi = {10.1016/j.jbi.2008.01.006},\n journal = {Journal of biomedical informatics},\n number = {4}\n}","author_short":["van Gerven, M., A., J.","Taal, B., G.","Lucas, P., J., F."],"urls":{"Website":"http://www.sciencedirect.com/science/article/pii/S1532046408000154"},"biburl":"https://bibbase.org/service/mendeley/95e10851-cdf3-31de-9f82-1ab629e601b0","bibbaseid":"vangerven-taal-lucas-dynamicbayesiannetworksasprognosticmodelsforclinicalpatientmanagement-2008","role":"author","keyword":["Algorithms","Bayes Theorem","Carcinoid Tumor","Carcinoid Tumor: diagnosis","Carcinoid Tumor: mortality","Decision Support Systems","Clinical","Diagnosis","Computer-Assisted","Diagnosis","Computer-Assisted: methods","Humans","Neural Networks (Computer)","Prognosis","Risk Assessment","Risk Assessment: methods","Risk Factors","Survival Analysis","Survival Rate"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/95e10851-cdf3-31de-9f82-1ab629e601b0","creationDate":"2015-04-11T20:28:32.436Z","downloads":0,"keywords":["algorithms","bayes theorem","carcinoid tumor","carcinoid tumor: diagnosis","carcinoid tumor: mortality","decision support systems","clinical","diagnosis","computer-assisted","diagnosis","computer-assisted: methods","humans","neural networks (computer)","prognosis","risk assessment","risk assessment: methods","risk factors","survival analysis","survival rate"],"search_terms":["dynamic","bayesian","networks","prognostic","models","clinical","patient","management","van gerven","taal","lucas"],"title":"Dynamic Bayesian networks as prognostic models for clinical patient management.","year":2008,"dataSources":["8hwkQbNZz66Dc7LzM","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"]}