{"corpus_id":87447224,"paper_sha":"37b520c2691bc7485419287c08c16a2d54c779bd","doi":"10.1016/J.JVAL.2019.01.006","arxiv_id":null,"pmid":30975395,"pmcid":null,"mag_id":2921518676,"dblp_id":null,"acl_id":null,"title":"Bayesian Networks for Risk Prediction Using Real-World Data: A Tool for Precision Medicine.","year":2019,"publication_date":"2019-03-15","venue":"Value in Health","journal":{"name":"Value in health : the journal of the International Society for Pharmacoeconomics and Outcomes Research","pages":"\n          439-445\n        ","volume":"22 4"},"journal_issn":null,"journal_title":null,"publication_types":["Review","JournalArticle"],"pubmed_pub_types":["Journal Article","Review"],"s2_fields_of_study":["Medicine","Computer Science"],"reference_count":30,"citation_count":166,"influential_citation_count":7,"is_open_access":true,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":[{"d":"Bayes Theorem","mj":false,"ui":"D001499"},{"d":"Data Interpretation, Statistical","mj":false,"ui":"D003627"},{"d":"Data Mining","mj":false,"qs":[{"q":"methods","mj":true,"ui":"Q000379"},{"q":"statistics & numerical data","mj":false,"ui":"Q000706"}],"ui":"D057225"},{"d":"Heart Diseases","mj":false,"qs":[{"q":"epidemiology","mj":false,"ui":"Q000453"},{"q":"therapy","mj":false,"ui":"Q000628"}],"ui":"D006331"},{"d":"Humans","mj":false,"ui":"D006801"},{"d":"Machine Learning","mj":true,"ui":"D000069550"},{"d":"Models, Statistical","mj":false,"ui":"D015233"},{"d":"Neoplasms","mj":false,"qs":[{"q":"epidemiology","mj":false,"ui":"Q000453"},{"q":"therapy","mj":false,"ui":"Q000628"}],"ui":"D009369"},{"d":"Precision Medicine","mj":false,"qs":[{"q":"adverse effects","mj":false,"ui":"Q000009"},{"q":"methods","mj":true,"ui":"Q000379"},{"q":"statistics & numerical data","mj":false,"ui":"Q000706"}],"ui":"D057285"},{"d":"Risk Assessment","mj":false,"ui":"D018570"},{"d":"Risk Factors","mj":false,"ui":"D012307"},{"d":"Treatment Outcome","mj":false,"ui":"D016896"}],"chemicals":null,"comments_corrections":null,"source_flags":5,"s2_open_access_pdf_url":"http://www.valueinhealthjournal.com/article/S1098301519300579/pdf","s2_open_access_landing_url":"https://www.semanticscholar.org/paper/37b520c2691bc7485419287c08c16a2d54c779bd","s2_open_access_license":"publisher-specific-oa","s2_open_access_status":"BRONZE","pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"OBJECTIVE\nThe fields of medicine and public health are undergoing a data revolution. An increasing availability of data has brought about a growing interest in machine-learning algorithms. Our objective is to present the reader with an introduction to a knowledge representation and machine-learning tool for risk estimation in medical science known as Bayesian networks (BNs).\n\n\nSTUDY DESIGN\nIn this article we review how BNs are compact and intuitive graphical representations of joint probability distributions (JPDs) that can be used to conduct causal reasoning and risk estimation analysis and offer several advantages over regression-based methods. We discuss how BNs represent a different approach to risk estimation in that they are graphical representations of JPDs that take the form of a network representing model random variables and the influences between them, respectively.\n\n\nMETHODS\nWe explore some of the challenges associated with traditional risk prediction methods and then describe BNs, their construction, application, and advantages in risk prediction based on examples in cancer and heart disease.\n\n\nRESULTS\nRisk modeling with BNs has advantages over regression-based approaches, and in this article we focus on three that are relevant to health outcomes research: (1) the generation of network structures in which relationships between variables can be easily communicated; (2) their ability to apply Bayes's theorem to conduct individual-level risk estimation; and (3) their easy transformation into decision models.\n\n\nCONCLUSIONS\nBayesian networks represent a powerful and flexible tool for the analysis of health economics and outcomes research data in the era of precision medicine.","claims":[{"public_id":"cl_3922e222922a1ed1016c5895f944694c","status":"active","text":"Bayesian networks are compact and intuitive graphical representations of joint probability distributions that can be used to conduct causal reasoning and risk estimation analysis, offering several advantages over regression-based methods.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/claims/cl_3922e222922a1ed1016c5895f944694c"},{"public_id":"cl_766d2056817d3c41cb6d473b668c01da","status":"active","text":"Bayesian networks represent a powerful and flexible tool for the analysis of health economics and outcomes research data in the era of precision medicine.","confidence":0.9,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/claims/cl_766d2056817d3c41cb6d473b668c01da"},{"public_id":"cl_ed7a495f1c51841f12278f10d7a760b7","status":"active","text":"Risk modeling with Bayesian networks has three advantages relevant to health outcomes research: generation of easily communicated network structures, ability to apply Bayes's theorem for individual-level risk estimation, and easy transformation into decision models.","confidence":0.95,"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/claims/cl_ed7a495f1c51841f12278f10d7a760b7"}],"concepts":[{"public_id":"co_2b815f041f8b93b0797789751d7b573a","status":"active","name":"causal reasoning","description":"Reasoning about cause-effect relationships that Bayesian networks can conduct as part of risk estimation analysis.","types":["analytical capability"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/concepts/co_2b815f041f8b93b0797789751d7b573a"},{"public_id":"co_3eaba7abb93d100e5c473a610bbc1b53","status":"active","name":"precision medicine","description":"Era of medicine in which Bayesian networks are presented as a tool for analysis of health economics and outcomes research data.","types":["context"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/concepts/co_3eaba7abb93d100e5c473a610bbc1b53"},{"public_id":"co_58172cb02a2b31e971075fb5a08d2e02","status":"active","name":"risk estimation analysis","description":"Analysis performed using Bayesian networks to estimate risks, often compared to regression-based methods.","types":["analytical method"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/concepts/co_58172cb02a2b31e971075fb5a08d2e02"},{"public_id":"co_707fe36ced36f8e8ea6406524c3aad82","status":"active","name":"joint probability distributions","description":"Probability distributions that are represented graphically by Bayesian networks to model random variables and their influences.","types":["mathematical concept"],"aliases":["JPDs"],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/concepts/co_707fe36ced36f8e8ea6406524c3aad82"},{"public_id":"co_85efde70c417422cd9c07c0edf6d52bf","status":"active","name":"health economics","description":"Field of analysis for which Bayesian networks are considered a powerful and flexible tool in the precision medicine era.","types":["research domain"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/concepts/co_85efde70c417422cd9c07c0edf6d52bf"},{"public_id":"co_972c28e8b7c153234da0efe1e030202c","status":"active","name":"individual-level risk estimation","description":"Risk estimation at the individual level enabled by Bayesian networks through application of Bayes's theorem.","types":["analytical capability"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/concepts/co_972c28e8b7c153234da0efe1e030202c"},{"public_id":"co_bc1d3e2450d721b740e727b2bd3b94a5","status":"active","name":"outcomes research","description":"Research on health outcomes for which Bayesian networks are considered a powerful and flexible tool in the precision medicine era.","types":["research domain"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/concepts/co_bc1d3e2450d721b740e727b2bd3b94a5"},{"public_id":"co_c516101795ff952b6531cd0843a5e279","status":"active","name":"decision models","description":"Models into which Bayesian networks can be easily transformed, facilitating decision-making.","types":["model type"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/concepts/co_c516101795ff952b6531cd0843a5e279"},{"public_id":"co_c52188f129ba40465b638112e6597c21","status":"active","name":"Bayesian networks","description":"Compact and intuitive graphical representations of joint probability distributions used for causal reasoning and risk estimation in medical science.","types":["method","knowledge representation"],"aliases":["BNs"],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/concepts/co_c52188f129ba40465b638112e6597c21"},{"public_id":"co_dfa9f64be994411b8369b4ef854f3c41","status":"active","name":"Bayes's theorem","description":"Theorem applied by Bayesian networks to conduct individual-level risk estimation.","types":["mathematical theorem"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/concepts/co_dfa9f64be994411b8369b4ef854f3c41"},{"public_id":"co_fb8b86b86159ebe2a9f5fba491ef2dc6","status":"active","name":"network structures","description":"Graphical structures generated by Bayesian networks in which relationships between variables can be easily communicated.","types":["representation"],"aliases":[],"contributors":[{"id":32,"public_id":"7c402c1b98","public_label":"뀨 (7c402c1b98)","roles":["extraction"],"url":"https://sah.borca.ai/u/7c402c1b98"},{"id":17,"public_id":"322360f1c1","public_label":"Killer Whale (322360f1c1)","roles":["review"],"url":"https://sah.borca.ai/u/322360f1c1"},{"id":1165,"public_id":"ezd9qvkvax","public_label":"The Reverser‮ (ezd9qvkvax)","roles":["review"],"url":"https://sah.borca.ai/u/ezd9qvkvax"}],"url":"https://sah.borca.ai/concepts/co_fb8b86b86159ebe2a9f5fba491ef2dc6"}],"external_ids":{"DOI":"10.1016/J.JVAL.2019.01.006","ArXiv":null,"PubMed":30975395,"PubMedCentral":null,"MAG":2921518676,"DBLP":null,"ACL":null},"open_access":{"is_open_access":true,"pdf_url":"http://www.valueinhealthjournal.com/article/S1098301519300579/pdf","landing_url":"https://www.semanticscholar.org/paper/37b520c2691bc7485419287c08c16a2d54c779bd","source":"semantic_scholar","pdf_url_source":"semantic_scholar_open_access_pdf","license":"publisher-specific-oa","status":"BRONZE","reason":null},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":5},"paper_id":638485,"paper_uid":"9807aae1-846f-4110-8490-1cc947dda953","canonical_identity":{"paper_id":638485,"paper_uid":"9807aae1-846f-4110-8490-1cc947dda953","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/87447224"}