{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T19:04:30Z","timestamp":1789585470679,"version":"build-2803163510"},"reference-count":15,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Sentinel Innovation Center","award":["75F40119D10037"],"award-info":[{"award-number":["75F40119D10037"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To describe considerations for integration of human and artificial intelligence for creating a postmarketing surveillance system capable of timely and reliably identifying causal effects of medications on safety endpoints.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>The FDA has prioritized more extensive Electronic Health Records (EHR) integration along with generative artificial intelligence and machine learning (Gen AI\/ML) into the national active surveillance program for medical products\u2014the Sentinel Initiative. Based on our experience of leading these efforts, we provide perspectives on the opportunities and challenges of Gen AI\/ML integration into Sentinel.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Using specific examples, we outline the role of Gen AI and ML in a causal inference framework for scalable information extraction, assessment of fitness-for-purpose of data sources, diagnosing residual confounding, and enhancing confounding adjustment. Critically, we outline steps and checkpoints along the way where human involvement remains indispensable.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion and conclusion<\/jats:title>\n                    <jats:p>In public health applications where stakes are high, use of Gen AI\/ML needs to be carefully considered with appropriate guardrails ensuring human expert involvement.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocag121","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T18:25:55Z","timestamp":1784053555000},"page":"1834-1838","source":"Crossref","is-referenced-by-count":0,"title":["Integrating human and artificial intelligence for robust postmarketing safety surveillance systems: reflections from the FDA Sentinel Innovation Center"],"prefix":"10.1093","volume":"33","author":[{"given":"Rishi J","family":"Desai","sequence":"first","affiliation":[{"name":"Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women\u2019s Hospital and Harvard Medical School , Boston, MA 02120,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1609-7420","authenticated-orcid":false,"given":"Robert","family":"Ball","sequence":"additional","affiliation":[{"name":"Center for Drug Evaluation and Research, United States Food and Drug Administration , Silver Spring, MD 20993,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4874-5864","authenticated-orcid":false,"given":"Gerald","family":"Dal Pan","sequence":"additional","affiliation":[{"name":"Center for Drug Evaluation and Research, United States Food and Drug Administration , Silver Spring, MD 20993,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Schneeweiss","sequence":"additional","affiliation":[{"name":"Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women\u2019s Hospital and Harvard Medical School , Boston, MA 02120,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"2026091614321284200_ocag121-B1","doi-asserted-by":"crossref","first-page":"2091","DOI":"10.1056\/NEJMp1809643","article-title":"The FDA Sentinel Initiative\u2014an evolving national resource","volume":"379","author":"Platt","year":"2018","journal-title":"N Engl J Med"},{"key":"2026091614321284200_ocag121-B2","doi-asserted-by":"crossref","first-page":"815","DOI":"10.1002\/cpt.2979","article-title":"Six years of the US Food and Drug Administration\u2019s postmarket active risk identification and analysis system in the Sentinel Initiative: implications for real world evidence generation","volume":"114","author":"Maro","year":"2023","journal-title":"Clin Pharmacol Ther"},{"key":"2026091614321284200_ocag121-B3","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1038\/s41746-021-00542-0","article-title":"Broadening the reach of the FDA Sentinel system: a roadmap for integrating electronic health record data in a causal analysis framework","volume":"4","author":"Desai","year":"2021","journal-title":"NPJ Digit Med"},{"key":"2026091614321284200_ocag121-B4","doi-asserted-by":"crossref","first-page":"e076460","DOI":"10.1136\/bmj-2023-076460","article-title":"Process guide for inferential studies using healthcare data from routine clinical practice to evaluate causal effects of drugs (PRINCIPLED): considerations from the FDA Sentinel Innovation Center","volume":"384","author":"Desai","year":"2024","journal-title":"BMJ"},{"key":"2026091614321284200_ocag121-B5","doi-asserted-by":"crossref","first-page":"1663","DOI":"10.1016\/j.jval.2022.09.001","article-title":"HARmonized protocol template to enhance reproducibility of hypothesis evaluating real-world evidence studies on treatment effects: a good practices report of a joint ISPE\/ISPOR task force","volume":"25","author":"Wang","year":"2022","journal-title":"Value Health"},{"key":"2026091614321284200_ocag121-B6","author":"The Food and Drug Administration","year":"2024"},{"key":"2026091614321284200_ocag121-B7","doi-asserted-by":"publisher","DOI":"10.1097\/EDE.0000000000001978","article-title":"An Expedited Chart Review Process for Large Database Studies Using Natural Language Processing and Multiwave Adaptive Sampling","author":"Wang","journal-title":"Epidemiology"},{"key":"2026091614321284200_ocag121-B8","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2025.58433","article-title":"Use of clinical notes to assess neuropsychiatric events after montelukast initiation","author":"Jaffe","year":"2026","journal-title":"JAMA Netw Open"},{"key":"2026091614321284200_ocag121-B9","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1038\/s41746-025-02234-5","article-title":"Strengthening inferential studies in the FDA Sentinel initiative: results from a methodological demonstration project","volume":"9","author":"Desai","year":"2025","journal-title":"NPJ Digit Med"},{"key":"2026091614321284200_ocag121-B10","doi-asserted-by":"crossref","first-page":"e71113","DOI":"10.2196\/71113","article-title":"Automated extraction of mortality information from publicly available sources using large language models: development and evaluation study","volume":"27","author":"Al-Garadi","year":"2025","journal-title":"J Med Internet Res."},{"key":"2026091614321284200_ocag121-B11","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwaf258","article-title":"Augmenting fact and date of death in electronic health records using internet media sources: a validation study from two large healthcare systems","author":"LeNoue-Newton","year":"2026","journal-title":"Am J Epidemiol"},{"key":"2026091614321284200_ocag121-B12","doi-asserted-by":"publisher","DOI":"10.1002\/pds.70383","article-title":"A Plasmode Simulation-Based Bias Analysis for Residual Confounding by Unmeasured Variables Leveraging Information-Rich Subsets","volume-title":"Pharmacoepidemiol Drug Saf","author":"Desai","year":"2026"},{"key":"2026091614321284200_ocag121-B13","doi-asserted-by":"crossref","first-page":"1632","DOI":"10.1093\/aje\/kwae023","article-title":"Targeted learning with an undersmoothed LASSO propensity score model for large-scale covariate adjustment in health-care database studies","volume":"193","author":"Wyss","year":"2024","journal-title":"Am J Epidemiol"},{"key":"2026091614321284200_ocag121-B14","doi-asserted-by":"crossref","first-page":"e70366","DOI":"10.1002\/sim.70366","article-title":"Assessing treatment effects in observational data with missing confounders: a comparative study of practical doubly-robust and traditional missing data methods","volume":"45","author":"Williamson","year":"2026","journal-title":"Stat Med"},{"key":"2026091614321284200_ocag121-B15","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1093\/aje\/kwaf017","article-title":"High-dimensional multiple imputation for partially observed confounders including natural language processing-derived auxiliary covariates","volume":"195","author":"Weberpals","year":"2026","journal-title":"Am J Epidemiol"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/advance-article-pdf\/doi\/10.1093\/jamia\/ocag121\/68779102\/ocag121.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/9\/1834\/68779102\/ocag121.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/9\/1834\/68779102\/ocag121.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T18:32:20Z","timestamp":1789583540000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/33\/9\/1834\/8734187"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"references-count":15,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,7,14]]},"published-print":{"date-parts":[[2026,9,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocag121","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,7,14]]}}}