{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T10:29:20Z","timestamp":1787740160826,"version":"build-2784847793"},"reference-count":22,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2020,2,12]],"date-time":"2020-02-12T00:00:00Z","timestamp":1581465600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Institute of Health"},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01-HG009174"],"award-info":[{"award-number":["R01-HG009174"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R00-LM011575"],"award-info":[{"award-number":["R00-LM011575"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Expert-labeled data are essential to train phenotyping algorithms for cohort identification. However expert labeling is time and labor intensive, and the costs remain prohibitive for scaling phenotyping to wider use-cases.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We present an approach referred to as polar labeling (PL), to create silver standard for training machine learning (ML) for disease classification. We test the hypothesis that ML models trained on the silver standard created by applying PL on unlabeled patient records, are comparable in performance to the ML models trained on gold standard, created by clinical experts through manual review of patient records. We perform experimental validation using health records of 38\u00a0023 patients spanning six diseases. Our results demonstrate the superior performance of the proposed approach.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>We provide a Python implementation of the algorithm and the Python code developed for this study on Github.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa088","type":"journal-article","created":{"date-parts":[[2020,2,4]],"date-time":"2020-02-04T12:25:04Z","timestamp":1580819104000},"page":"3200-3206","source":"Crossref","is-referenced-by-count":16,"title":["Polar labeling: silver standard algorithm for training disease classifiers"],"prefix":"10.1093","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6219-861X","authenticated-orcid":false,"given":"Kavishwar B","family":"Wagholikar","sequence":"first","affiliation":[{"name":"Laboratory of Computer Science , Massachusetts General Hospital, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0204-8978","authenticated-orcid":false,"given":"Hossein","family":"Estiri","sequence":"additional","affiliation":[{"name":"Laboratory of Computer Science , Massachusetts General Hospital, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marykate","family":"Murphy","sequence":"additional","affiliation":[{"name":"Partners Healthcare , Somerville, MA 02145, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shawn N","family":"Murphy","sequence":"additional","affiliation":[{"name":"Laboratory of Computer Science , Massachusetts General Hospital, Boston, MA 02114, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2020,2,12]]},"reference":[{"key":"2023013112032048400_btaa088-B1","doi-asserted-by":"crossref","first-page":"1166","DOI":"10.1093\/jamia\/ocw028","article-title":"Learning statistical models of phenotypes using noisy labeled training data","volume":"23","author":"Agarwal","year":"2016","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023013112032048400_btaa088-B2","first-page":"189","author":"Carroll","year":"2011"},{"key":"2023013112032048400_btaa088-B3","doi-asserted-by":"crossref","first-page":"e253","DOI":"10.1136\/amiajnl-2013-001945","article-title":"Applying active learning to high-throughput phenotyping algorithms for electronic health records data","volume":"20","author":"Chen","year":"2013","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023013112032048400_btaa088-B4","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1136\/eb-2017-102688","article-title":"Applying deep neural networks to unstructured text notes in electronic medical records for phenotyping youth depression","volume":"20","author":"Geraci","year":"2017","journal-title":"Evid. Based Mental Health"},{"key":"2023013112032048400_btaa088-B5","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1016\/j.jbi.2014.07.001","article-title":"Limestone: high-throughput candidate phenotype generation via tensor factorization","volume":"52","author":"Ho","year":"2014","journal-title":"J. Biomed. Inform"},{"key":"2023013112032048400_btaa088-B6","first-page":"115","author":"Ho","year":"2014"},{"key":"2023013112032048400_btaa088-B7","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1136\/amiajnl-2012-001145","article-title":"Next-generation phenotyping of electronic health records","volume":"20","author":"Hripcsak","year":"2013","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023013112032048400_btaa088-B8","first-page":"153","author":"Huang","year":"2004"},{"key":"2023013112032048400_btaa088-B9"},{"key":"2023013112032048400_btaa088-B10","doi-asserted-by":"crossref","first-page":"791","DOI":"10.1177\/1932296816681584","article-title":"Development of type 2 diabetes mellitus phenotyping framework using expert knowledge and machine learning approach","volume":"11","author":"Kagawa","year":"2017","journal-title":"J. Diabet. Sci. Technol"},{"key":"2023013112032048400_btaa088-B11","first-page":"1044","author":"Nalichowski","year":"2006"},{"key":"2023013112032048400_btaa088-B12","doi-asserted-by":"crossref","first-page":"996","DOI":"10.1093\/jamia\/ocx016","article-title":"Pragmatic (trial) informatics: a perspective from the NIH Health Care Systems Research Collaboratory","volume":"24","author":"Richesson","year":"2017","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023013112032048400_btaa088-B13","doi-asserted-by":"crossref","first-page":"e226","DOI":"10.1136\/amiajnl-2013-001926","article-title":"Electronic health records based phenotyping in next-generation clinical trials: a perspective from the NIH Health Care Systems Collaboratory","volume":"20","author":"Richesson","year":"2013","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023013112032048400_btaa088-B14","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1136\/amiajnl-2013-001935","article-title":"A review of approaches to identifying patient phenotype cohorts using electronic health records","volume":"21","author":"Shivade","year":"2014","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023013112032048400_btaa088-B15","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1093\/jamia\/ocw071","article-title":"Evaluating electronic health record data sources and algorithmic approaches to identify hypertensive individuals","volume":"24","author":"Teixeira","year":"2017","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023013112032048400_btaa088-B16","first-page":"1170","author":"Wattanasin","year":"2008"},{"key":"2023013112032048400_btaa088-B17","doi-asserted-by":"crossref","first-page":"1018","DOI":"10.1016\/j.molonc.2014.08.006","article-title":"Emerging uses of patient generated health data in clinical research","volume":"9","author":"Wood","year":"2015","journal-title":"Mol. Oncol"},{"key":"2023013112032048400_btaa088-B18","doi-asserted-by":"crossref","first-page":"1251","DOI":"10.1093\/jamia\/ocv070","article-title":"Review and evaluation of electronic health records-driven phenotype algorithm authoring tools for clinical and translational research","volume":"22","author":"Xu","year":"2015","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023013112032048400_btaa088-B19","doi-asserted-by":"crossref","DOI":"10.1093\/jamia\/ocw135","article-title":"Surrogate-assisted feature extraction for high-throughput phenotyping","volume":"24","author":"Yu","year":"2017","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023013112032048400_btaa088-B20","doi-asserted-by":"crossref","first-page":"993","DOI":"10.1093\/jamia\/ocv034","article-title":"Toward high-throughput phenotyping: unbiased automated feature extraction and selection from knowledge sources","volume":"22","author":"Yu","year":"2015","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023013112032048400_btaa088-B21","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1093\/jamia\/ocx111","article-title":"Enabling phenotypic big data with PheNorm","volume":"25","author":"Yu","year":"2017","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"2023013112032048400_btaa088-B22","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1093\/nsr\/nwx106","article-title":"A brief introduction to weakly supervised learning","volume":"5","author":"Zhou","year":"2018","journal-title":"Natl. Sci. Rev"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa088\/32923787\/btaa088.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/10\/3200\/48988332\/bioinformatics_36_10_3200.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/10\/3200\/48988332\/bioinformatics_36_10_3200.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T21:15:12Z","timestamp":1675199712000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/10\/3200\/5734649"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2020,2,12]]},"references-count":22,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2020,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa088","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,5,15]]},"published":{"date-parts":[[2020,2,12]]}}}