{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T09:36:29Z","timestamp":1764581789613,"version":"3.46.0"},"reference-count":20,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:00:00Z","timestamp":1759881600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01-HL138306","R01-CA236468","R01LM014401"],"award-info":[{"award-number":["R01-HL138306","R01-CA236468","R01LM014401"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,8]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Effective treatment of medical conditions begins with an accurate diagnosis. However, many conditions are often underdiagnosed, either being overlooked or diagnosed after significant delays. Electronic health records (EHRs) contain extensive patient health information, offering an opportunity to probabilistically identify underdiagnosed individuals. The rationale is that both diagnosed and underdiagnosed patients may display similar health profiles in EHR data, distinguishing them from condition-free patients. Thus, EHR data can be leveraged to develop models that assess an individual\u2019s risk of having a condition. To date, this opportunity has largely remained unexploited, partly due to the lack of suitable statistical methods. The key challenge is the positive-unlabeled EHR data structure, which consists of data for diagnosed (\u201cpositive\u201d) patients and the remaining (\u201cunlabeled\u201d) that include underdiagnosed patients and many condition-free patients. Therefore, data for patients who are unambiguously condition-free, essential for developing risk assessment models, are unavailable. To overcome this challenge, we propose ascertaining condition statuses for a small subset of unlabeled patients. We develop a novel statistical method for building accurate models using this supplemented EHR data to estimate the probability that a patient has the condition of interest. We study the asymptotic properties of our method and assess its finite-sample performance through simulation studies. Finally, we apply our method to develop a preliminary model for identifying potentially underdiagnosed non-alcoholic steatohepatitis patients using data from Penn Medicine EHRs.<\/jats:p>","DOI":"10.1093\/biomtc\/ujaf157","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:08:00Z","timestamp":1762520880000},"source":"Crossref","is-referenced-by-count":0,"title":["A semiparametric method for addressing underdiagnosis using electronic health record data"],"prefix":"10.1093","volume":"81","author":[{"given":"Weidong","family":"Ma","sequence":"first","affiliation":[{"name":"Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania Department of Biostatistics, , Philadelphia, PA 19104 ,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4649-079X","authenticated-orcid":false,"given":"Jordana B","family":"Cohen","sequence":"additional","affiliation":[{"name":"Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania Department of Biostatistics, , Philadelphia, PA 19104 ,","place":["United States"]},{"name":"Renal-Electrolyte and Hypertension Division , Department of Medicine, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104 ,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinbo","family":"Chen","sequence":"additional","affiliation":[{"name":"Epidemiology and Informatics, Perelman School of Medicine, University of Pennsylvania Department of Biostatistics, , Philadelphia, PA 19104 ,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,12,1]]},"reference":[{"key":"2025120103575604700_bib1","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1111\/biom.13400","article-title":"Statistical inference for association studies using electronic health records: handling both selection bias and outcome misclassification","volume":"78","author":"Beesley","year":"2022","journal-title":"Biometrics."},{"key":"2025120103575604700_bib2","doi-asserted-by":"crossref","first-page":"719","DOI":"10.1007\/s10994-020-05877-5","article-title":"Learning from positive and unlabeled data: a survey","volume":"109","author":"Bekker","year":"2020","journal-title":"Machine Learning"},{"key":"2025120103575604700_bib3","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1111\/1467-9868.00243","article-title":"A unified approach to regression analysis under double-sampling designs","volume":"62","author":"Chen","year":"2000","journal-title":"Journal of the Royal Statistical Society. Series B. Statistical Methodology"},{"key":"2025120103575604700_bib4","doi-asserted-by":"crossref","first-page":"C1","DOI":"10.1111\/ectj.12097","article-title":"Double\/debiased machine learning for treatment and structural parameters","volume":"21","author":"Chernozhukov","year":"2018","journal-title":"The Econometrics Journal"},{"key":"2025120103575604700_bib5","doi-asserted-by":"crossref","first-page":"2023","DOI":"10.1111\/biom.13721","article-title":"A robust approach for electronic health record-based case-control studies with contaminated case pools","volume":"79","author":"Dai","year":"2023","journal-title":"Biometrics."},{"key":"2025120103575604700_bib6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IISA.2019.8900698","article-title":"Positive and unlabeled learning algorithms and applications: a survey","volume-title":"2019 10th International Conference on Information, Intelligence, Systems and Applications (IISA)","author":"Jaskie","year":"2019"},{"key":"2025120103575604700_bib7","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/TPAMI.2015.2456899","article-title":"Classification with noisy labels by importance reweighting","volume":"38","author":"Liu","year":"2016","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2025120103575604700_bib8","doi-asserted-by":"crossref","first-page":"1674","DOI":"10.1111\/biom.13512","article-title":"Efficient odds ratio estimation under two-phase sampling using error-prone data from a multi-national HIV research cohort","volume":"78","author":"Lotspeich","year":"2022","journal-title":"Biometrics"},{"key":"2025120103575604700_bib9","doi-asserted-by":"crossref","DOI":"10.1002\/9780470580066","volume-title":"Complex Surveys: A Guide to Analysis Using R","author":"Lumley","year":"2010"},{"key":"2025120103575604700_bib10","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1093\/biomet\/79.2.355","article-title":"Inference using surrogate outcome data and a validation sample","volume":"79","author":"Pepe","year":"1992","journal-title":"Biometrika"},{"key":"2025120103575604700_bib11","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/0378-3758(94)90194-5","article-title":"Auxiliary outcome data and the mean score method","volume":"42","author":"Pepe","year":"1994","journal-title":"Journal of Statistical Planning and Inference"},{"key":"2025120103575604700_bib12","doi-asserted-by":"crossref","first-page":"846","DOI":"10.1080\/01621459.1994.10476818","article-title":"Estimation of regression coefficients when some regressors are not always observed","volume":"89","author":"Robins","year":"1994","journal-title":"Journal of the American Statistical Association"},{"key":"2025120103575604700_bib13","doi-asserted-by":"crossref","first-page":"102149","DOI":"10.1016\/j.eclinm.2023.102149","article-title":"Large-scale identification of undiagnosed hepatic steatosis using natural language processing","volume":"62","author":"Schneider","year":"2023","journal-title":"eClinicalMedicine"},{"key":"2025120103575604700_bib14","doi-asserted-by":"crossref","first-page":"2649","DOI":"10.1111\/biom.13713","article-title":"Multiwave validation sampling for error-prone electronic health records","volume":"79","author":"Shepherd","year":"2023","journal-title":"Biometrics."},{"key":"2025120103575604700_bib15","volume-title":"Semiparametric Theory and Missing Data","author":"Tsiatis","year":"2006"},{"key":"2025120103575604700_bib16","first-page":"Article 25","article-title":"Super learner","volume":"6","author":"van\u00a0der\u00a0Laan","year":"2007","journal-title":"Statistical Applications in Genetics and Molecular Biology"},{"key":"2025120103575604700_bib17","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Decision curve analysis: A novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Medical Decision Making"},{"key":"2025120103575604700_bib18","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1111\/biom.13264","article-title":"Case contamination in electronic health records based case-control studies","volume":"77","author":"Wang","year":"2021","journal-title":"Biometrics."},{"key":"2025120103575604700_bib19","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1093\/jamia\/ocz170","article-title":"A maximum likelihood approach to electronic health record phenotyping using positive and unlabeled patients","volume":"27","author":"Zhang","year":"2019","journal-title":"Journal of the American Medical Informatics Association"},{"key":"2025120103575604700_bib20","doi-asserted-by":"crossref","first-page":"3660","DOI":"10.1214\/23-EJS2188","article-title":"Regression in tensor product spaces by the method of sieves","volume":"17","author":"Zhang","year":"2023","journal-title":"Electronic Journal of Statistics"}],"container-title":["Biometrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/81\/4\/ujaf157\/65663385\/ujaf157.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/81\/4\/ujaf157\/65663385\/ujaf157.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T09:33:40Z","timestamp":1764581620000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biometrics\/article\/doi\/10.1093\/biomtc\/ujaf157\/8361919"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,8]]},"references-count":20,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,10,8]]}},"URL":"https:\/\/doi.org\/10.1093\/biomtc\/ujaf157","relation":{},"ISSN":["0006-341X","1541-0420"],"issn-type":[{"value":"0006-341X","type":"print"},{"value":"1541-0420","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,12]]},"published":{"date-parts":[[2025,10,8]]},"article-number":"ujaf157"}}