{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T09:24:38Z","timestamp":1770888278163,"version":"3.50.1"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2025,3,29]],"date-time":"2025-03-29T00:00:00Z","timestamp":1743206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HL171809"],"award-info":[{"award-number":["R01HL171809"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01AG084550"],"award-info":[{"award-number":["R01AG084550"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HL133786"],"award-info":[{"award-number":["R01HL133786"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01GM139891"],"award-info":[{"award-number":["R01GM139891"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01AG069900"],"award-info":[{"award-number":["R01AG069900"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["U01HG011181"],"award-info":[{"award-number":["U01HG011181"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["P50HD106446"],"award-info":[{"award-number":["P50HD106446"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01LM012806"],"award-info":[{"award-number":["R01LM012806"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["K99LM014428"],"award-info":[{"award-number":["K99LM014428"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Vanderbilt University Medical Center\u2019s Synthetic Derivative"},{"DOI":"10.13039\/100006108","name":"National Center for Advancing Translational Science","doi-asserted-by":"crossref","award":["UL1 TR002243"],"award-info":[{"award-number":["UL1 TR002243"]}],"id":[{"id":"10.13039\/100006108","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>Diagnosis codes documented in electronic health records (EHR) are often relied upon to clinically phenotype patients for biomedical research. However, these diagnoses can be incomplete and inaccurate, leading to false negatives when searching for patients with phenotypes of interest. This study aims to determine whether PheMAP, a comprehensive knowledgebase integrating multiple clinical terminologies beyond diagnosis to capture phenotypes, can effectively identify patients lacking relevant EHR diagnosis codes.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>We investigated a collection of 3.5 million patient records from Vanderbilt University Medical Center\u2019s EHR and focused on 4 well-studied phenotypes: (1) type 2 diabetes mellitus (T2DM), (2) dementia, (3) prostate cancer, and (4) sensorineural hearing loss. We applied PheMAP to match structured concepts in patient records and calculated a phenotype risk score (PheScore) to indicate patient-phenotype similarity. Patients meeting predefined PheScore criteria but lacking diagnosis codes were identified. Clinically knowledgeable experts adjudicated randomly selected patients per phenotype as Positive, Possibly Positive, or Negative.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Our approach indicated that 5.3% of patients lacked a diagnosis for T2DM, 4.5% for dementia, 2.2% for prostate cancer, and 0.2% for sensorineural hearing loss. The expert review indicated 100% precision (for Possibly Positive or Positive cases) for dementia and sensorineural hearing loss, and 90.0% and 85.0% precision for T2DM and prostate cancer, respectively. Excluding Possibly Positive cases, the precision for T2DM and prostate cancer was 88.9% and 81.3%, respectively.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Conclusions<\/jats:title>\n                  <jats:p>Leveraging clinical terminologies incorporated by PheMAP can effectively identify patients with phenotypes who lack EHR diagnosis codes, thereby enhancing phenotyping quality and related research reliability.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/jamia\/ocaf055","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T20:02:34Z","timestamp":1743451354000},"page":"1007-1014","source":"Crossref","is-referenced-by-count":1,"title":["Beyond Phecodes: leveraging PheMAP to identify patients lacking diagnosis codes in electronic health records"],"prefix":"10.1093","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6719-1388","authenticated-orcid":false,"given":"Chao","family":"Yan","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, TN 37203,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Monika E","family":"Grabowska","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, TN 37203,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7993-7212","authenticated-orcid":false,"given":"Rut","family":"Thakkar","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, TN 37203,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alyson L","family":"Dickson","sequence":"additional","affiliation":[{"name":"Department of Medicine, Vanderbilt University Medical Center , Nashville, TN 37232,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7733-0847","authenticated-orcid":false,"given":"Peter J","family":"Emb\u00ed","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, TN 37203,","place":["United States"]},{"name":"Department of Medicine, Vanderbilt University Medical Center , Nashville, TN 37232,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"QiPing","family":"Feng","sequence":"additional","affiliation":[{"name":"Department of Medicine, Vanderbilt University Medical Center , Nashville, TN 37232,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joshua C","family":"Denny","sequence":"additional","affiliation":[{"name":"All of United States Research Program, National Institute of Health , Bethesda, MD 20892,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0342-1965","authenticated-orcid":false,"given":"Vern Eric","family":"Kerchberger","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, TN 37203,","place":["United States"]},{"name":"Department of Medicine, Vanderbilt University Medical Center , Nashville, TN 37232,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bradley A","family":"Malin","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, TN 37203,","place":["United States"]},{"name":"Department of Computer Science, Vanderbilt University , Nashville, TN 37203,","place":["United States"]},{"name":"Department of Biostatistics, Vanderbilt University Medical Center , Nashville, TN 37203,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Qi","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center , Nashville, TN 37203,","place":["United States"]},{"name":"Department of Computer Science, Vanderbilt University , Nashville, TN 37203,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,3,29]]},"reference":[{"key":"2025052712460110700_ocaf055-B1","doi-asserted-by":"crossref","first-page":"1416","DOI":"10.1377\/hlthaff.2016.1651","article-title":"HITECH Act drove large gains in hospital electronic health record adoption","volume":"36","author":"Adler-Milstein","year":"2017","journal-title":"Health Aff"},{"key":"2025052712460110700_ocaf055-B2","doi-asserted-by":"crossref","first-page":"851","DOI":"10.1093\/aje\/kwy292","article-title":"Challenges and opportunities for using big healthcare data to advance medical science and public health","volume":"188","author":"Shortreed","year":"2019","journal-title":"Am J Epidemiol"},{"key":"2025052712460110700_ocaf055-B3","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1186\/s13073-015-0166-y","article-title":"Extracting research-quality phenotypes from electronic health records to support precision medicine","volume":"7","author":"Wei","year":"2015","journal-title":"Genome Med"},{"key":"2025052712460110700_ocaf055-B4","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1093\/bioinformatics\/btq126","article-title":"PheWAS: demonstrating the feasibility of a phenome-wide scan to discover gene\u2013disease associations","volume":"26","author":"Denny","year":"2010","journal-title":"Bioinformatics"},{"key":"2025052712460110700_ocaf055-B5","doi-asserted-by":"crossref","first-page":"e0175508","DOI":"10.1371\/journal.pone.0175508","article-title":"Evaluating phecodes, clinical classification software, and ICD-9-CM codes for phenome-wide association studies in the electronic health record","volume":"12","author":"Wei","year":"2017","journal-title":"PloS One"},{"key":"2025052712460110700_ocaf055-B6","doi-asserted-by":"crossref","first-page":"79re1","DOI":"10.1126\/scitranslmed.3001807","article-title":"Electronic medical records for genetic research: results of the eMERGE consortium","volume":"3","author":"Kho","year":"2011","journal-title":"Sci Transl Med"},{"key":"2025052712460110700_ocaf055-B7","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1038\/s41746-020-0221-y","article-title":"An overview of clinical decision support systems: benefits, risks, and strategies for success","volume":"3","author":"Sutton","year":"2020","journal-title":"NPJ Digit Med"},{"key":"2025052712460110700_ocaf055-B8","doi-asserted-by":"crossref","first-page":"331","DOI":"10.6004\/jnccn.2018.7104","article-title":"A systematic review of clinical decision support systems for clinical oncology practice","volume":"17","author":"Pawloski","year":"2019","journal-title":"J Natl Compr Canc Netw"},{"key":"2025052712460110700_ocaf055-B9","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1038\/s41746-024-01038-3","article-title":"Leveraging generative AI to prioritize drug repurposing candidates for Alzheimer\u2019s disease with real-world clinical validation","volume":"7","author":"Yan","year":"2024","journal-title":"NPJ Digit Med"},{"key":"2025052712460110700_ocaf055-B10","doi-asserted-by":"crossref","first-page":"e667","DOI":"10.1016\/S2589-7500(20)30192-8","article-title":"Artificial intelligence in COVID-19 drug repurposing","volume":"2","author":"Zhou","year":"2020","journal-title":"Lancet Digit Health"},{"key":"2025052712460110700_ocaf055-B11","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1093\/jamia\/ocw042","article-title":"Opportunities and challenges in developing risk prediction models with electronic health records data: a systematic review","volume":"24","author":"Goldstein","year":"2017","journal-title":"J Am Med Inform Assoc"},{"key":"2025052712460110700_ocaf055-B12","doi-asserted-by":"crossref","first-page":"1584","DOI":"10.1093\/jamia\/ocac086","article-title":"Forecasting the future clinical events of a patient through contrastive learning","volume":"29","author":"Zhang","year":"2022","journal-title":"J Am Med Inform Assoc"},{"key":"2025052712460110700_ocaf055-B13","first-page":"1248","article-title":"Learning clinical workflows to identify subgroups of heart failure patients","volume":"2016","author":"Yan","year":"2016","journal-title":"AMIA Annu Symp Proc"},{"key":"2025052712460110700_ocaf055-B14","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.jbi.2015.09.009","article-title":"Paving the COWpath: learning and visualizing clinical pathways from electronic health record data","volume":"58","author":"Zhang","year":"2015","journal-title":"J Biomed Inform"},{"key":"2025052712460110700_ocaf055-B15","doi-asserted-by":"crossref","first-page":"e14325","DOI":"10.2196\/14325","article-title":"Mapping ICD-10 and ICD-10-CM codes to phecodes: workflow development and initial evaluation","volume":"7","author":"Wu","year":"2019","journal-title":"JMIR Med Inform"},{"key":"2025052712460110700_ocaf055-B16","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1136\/amiajnl-2011-000597","article-title":"Impact of data fragmentation across healthcare centers on the accuracy of a high-throughput clinical phenotyping algorithm for specifying subjects with type 2 diabetes mellitus","volume":"19","author":"Wei","year":"2012","journal-title":"J Am Med Inform Assoc"},{"key":"2025052712460110700_ocaf055-B17","doi-asserted-by":"crossref","first-page":"1989","DOI":"10.1001\/archinternmed.2010.439","article-title":"Patients treated at multiple acute health care facilities: quantifying information fragmentation","volume":"170","author":"Bourgeois","year":"2010","journal-title":"Arch Intern Med"},{"key":"2025052712460110700_ocaf055-B18","first-page":"912","article-title":"Accuracy and completeness of clinical coding using ICD-10 for ambulatory visits","volume":"2017","author":"Horsky","year":"2017","journal-title":"AMIA Annu Symp Proc"},{"key":"2025052712460110700_ocaf055-B19","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1038\/ajh.2011.179","article-title":"Underdiagnosis of hypertension using electronic health records","volume":"25","author":"Banerjee","year":"2012","journal-title":"Am J Hypertens"},{"key":"2025052712460110700_ocaf055-B20","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.ijmedinf.2018.09.004","article-title":"Errors and causes of communication failures from hospital information systems to electronic health record: a record-review study","volume":"119","author":"Khajouei","year":"2018","journal-title":"Int J Med Inform"},{"key":"2025052712460110700_ocaf055-B21","doi-asserted-by":"crossref","first-page":"S79","DOI":"10.7326\/M19-0873","article-title":"Research and reporting considerations for observational studies using electronic health record data","volume":"172","author":"Callahan","year":"2020","journal-title":"Ann of Intern Med"},{"key":"2025052712460110700_ocaf055-B22","doi-asserted-by":"crossref","first-page":"1143","DOI":"10.1093\/jamia\/ocw021","article-title":"Missing clinical and behavioral health data in a large electronic health record (EHR) system","volume":"23","author":"Madden","year":"2016","journal-title":"J Am Med Inform Assoc"},{"key":"2025052712460110700_ocaf055-B23","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/j.ijmedinf.2012.05.015","article-title":"The absence of longitudinal data limits the accuracy of high-throughput clinical phenotyping for identifying type 2 diabetes mellitus subjects","volume":"82","author":"Wei","year":"2013","journal-title":"Int J Med Inform"},{"key":"2025052712460110700_ocaf055-B24","doi-asserted-by":"crossref","first-page":"e20","DOI":"10.1093\/jamia\/ocv130","article-title":"Combining billing codes, clinical notes, and medications from electronic health records provides superior phenotyping performance","volume":"23","author":"Wei","year":"2016","journal-title":"J Am Med Inform Assoc"},{"key":"2025052712460110700_ocaf055-B25","doi-asserted-by":"crossref","first-page":"1675","DOI":"10.1093\/jamia\/ocaa104","article-title":"PheMAP: a multi-resource knowledge base for high-throughput phenotyping within electronic health records","volume":"27","author":"Zheng","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"2025052712460110700_ocaf055-B26","doi-asserted-by":"crossref","first-page":"456","DOI":"10.1093\/jamia\/ocac234","article-title":"Evaluating resources composing the PheMAP knowledge base to enhance high-throughput phenotyping","volume":"30","author":"Wan","year":"2023","journal-title":"J Am Med Inform Assoc"},{"key":"2025052712460110700_ocaf055-B27","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.jbi.2014.02.003","article-title":"Secondary use of clinical data: the Vanderbilt approach","volume":"52","author":"Danciu","year":"2014","journal-title":"J Biomed Inform"},{"key":"2025052712460110700_ocaf055-B28","doi-asserted-by":"crossref","first-page":"D267","DOI":"10.1093\/nar\/gkh061","article-title":"The Unified Medical Language System (UMLS): integrating biomedical terminology","volume":"32","author":"Bodenreider","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2025052712460110700_ocaf055-B29","doi-asserted-by":"crossref","first-page":"1994","DOI":"10.1093\/jamia\/ocae072","article-title":"Large language models facilitate the generation of electronic health record phenotyping algorithms","volume":"31","author":"Yan","year":"2024","journal-title":"J Am Med Inform Assoc"},{"key":"2025052712460110700_ocaf055-B30","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1001\/jama.2023.14217","article-title":"Creation and adoption of large language models in medicine","volume":"330","author":"Shah","year":"2023","journal-title":"JAMA"},{"key":"2025052712460110700_ocaf055-B31","doi-asserted-by":"crossref","first-page":"1134","DOI":"10.1038\/s41591-024-02855-5","article-title":"Clinical text summarization: adapting large language models can outperform human experts","volume":"30","author":"Van Veen","year":"2024","journal-title":"Nat Med"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/32\/6\/1007\/62810811\/ocaf055.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/32\/6\/1007\/62810811\/ocaf055.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T16:46:15Z","timestamp":1748364375000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/32\/6\/1007\/8100434"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,29]]},"references-count":31,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,3,29]]},"published-print":{"date-parts":[[2025,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocaf055","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,6]]},"published":{"date-parts":[[2025,3,29]]}}}