{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T07:28:45Z","timestamp":1789025325389,"version":"build-2803163510"},"reference-count":13,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"22","funder":[{"DOI":"10.13039\/100006512","name":"Duke University School of Medicine","doi-asserted-by":"crossref","award":["NA"],"award-info":[{"award-number":["NA"]}],"id":[{"id":"10.13039\/100006512","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["www.ahajournals.org"],"crossmark-restriction":true},"short-container-title":["Circulation"],"published-print":{"date-parts":[[2026,6,2]]},"abstract":"<jats:sec>\n                    <jats:title>BACKGROUND:<\/jats:title>\n                    <jats:p>Clinical end point classification (CEC) is the gold standard for cardiovascular end point measurement in clinical trials but adds time and cost. We developed and validated an artificial intelligence (AI) algorithm (adaptive AI for CEC [ADAPT-CEC]) that adjudicates multiple cardiovascular end points and adapts to new definitions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS:<\/jats:title>\n                    <jats:p>ADAPT-CEC was derived from myocardial infarction (MI), stroke, and heart failure from the ODYSSEY OUTCOMES (Evaluation of Cardiovascular Outcomes After an Acute Coronary Syndrome During Treatment With Alirocumab) trial and externally validated on MI, stroke, bleeding and cardiovascular (CV) death from the EUCLID (Examining Use of Ticagrelor in Peripheral Artery Disease) trial after adaptation with 20 EUCLID suspected events per end point. ADAPT-CEC was compared via F1 score with direct Generative Pretrained Transformer (GPT) 4o adjudication and a hybrid approach where the 30% of suspected events with the lowest AI prediction certainty used human adjudication. The EUCLID primary end point of CV death, MI, or stroke was re-estimated for all 3 adjudication strategies.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS:<\/jats:title>\n                    <jats:p>Among 13 885 suspected EUCLID primary end point events, ADAPT-CEC, hybrid, and GPT 4o strategies correctly classified 86.4%, 95.6%, and 76.3% of all end points and 99.4%, 99.6%, and 99.8% of all non\u2013end points compared with human adjudication, respectively. Hybrid adjudication F1 metrics were the highest (CV death, 0.94 [95% CI, 0.92\u20130.96]; MI, 0.80 [95% CI, 0.77\u20130.82]; stroke, 0.82 [95% CI, 0.78\u20130.86]; bleeding, 0.83 [95% CI, 0.82\u20130.85]). ADAPT-CEC F1 metrics were lower for CV death, MI, and stroke but similar to GPT 4o, while bleeding (0.78 [95% CI, 0.77\u20130.79]) was superior to GPT 4o. The EUCLID primary treatment effect was similar by human adjudication (hazard ratio [HR], 1.02 [95% CI, 0.93\u20131.13]); hybrid (HR, 1.04 [95% CI, 0.94\u20131.15]); ADAPT-CEC (HR, 0.98 [95% CI, 0.88\u20131.09]), and GPT 4.0 (HR, 1.06 [95% CI, 0.95\u20131.19]) adjudication.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSIONS:<\/jats:title>\n                    <jats:p>After brief adaptation, a single trial\u2013derived AI algorithm can adjudicate similar (MI and stroke) and new end points (CV death and bleeding) in a second trial and replicate the EUCLID primary outcome treatment effect. A hybrid approach with humans adjudicating those suspected events with the lowest 30% of ADAPT-CEC prediction certainty was superior to ADAPT-CEC alone or GPT 4o alone and replicated the EUCLID primary outcome treatment effect. Prospective studies of adaptive AI adjudication are needed to determine future trial implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1161\/circulationaha.126.080072","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T17:45:10Z","timestamp":1774892710000},"page":"1694-1706","update-policy":"https:\/\/doi.org\/10.1161\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":2,"title":["Adaptive AI for Cardiovascular Event Adjudication: Cardiovascular Event Adjudication Across Different Definitions in the ODYSSEY OUTCOMES and EUCLID Trials"],"prefix":"10.1161","volume":"153","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1599-2957","authenticated-orcid":true,"given":"Sreekanth","family":"Vemulapalli","sequence":"first","affiliation":[{"name":"Duke Clinical Research Institute, Durham, NC (S.V., D.W., W.S.J., M.R.P., R.D.L., R.H.)."},{"name":"Departments of Medicine (S.V., W.S.J., M.R.P., R.D.L.), Duke University School of Medicine, Durham, NC."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1445-994X","authenticated-orcid":true,"given":"Karla","family":"Pe\u00f1a Guerra","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Bioinformatics, Duke University, Durham, NC (K.P.G., R.H.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3431-2014","authenticated-orcid":true,"given":"Daniel","family":"Wojdyla","sequence":"additional","affiliation":[{"name":"Duke Clinical Research Institute, Durham, NC (S.V., D.W., W.S.J., M.R.P., R.D.L., R.H.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7288-9596","authenticated-orcid":true,"given":"W. Schuyler","family":"Jones","sequence":"additional","affiliation":[{"name":"Duke Clinical Research Institute, Durham, NC (S.V., D.W., W.S.J., M.R.P., R.D.L., R.H.)."},{"name":"Departments of Medicine (S.V., W.S.J., M.R.P., R.D.L.), Duke University School of Medicine, Durham, NC."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3791-2148","authenticated-orcid":true,"given":"Kenneth W.","family":"Mahaffey","sequence":"additional","affiliation":[{"name":"Stanford Center for Clinical Research, Stanford University School of Medicine, Palo Alto, CA (K.W.M.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5450-8676","authenticated-orcid":true,"given":"Robert A.","family":"Harrington","sequence":"additional","affiliation":[{"name":"Weill Cornell Medicine, New York, NY (R.A.H.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6896-2941","authenticated-orcid":true,"given":"Philippe Gabriel","family":"Steg","sequence":"additional","affiliation":[{"name":"Universit\u00e9 Paris-Cit\u00e9, AP-HP and INSERMU_1148, Paris, France (P.G.S.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2954-0695","authenticated-orcid":true,"given":"Gregory G.","family":"Schwartz","sequence":"additional","affiliation":[{"name":"Cardiology Section, Rocky Mountain Regional VA Medical Center and University of Colorado School of Medicine, Aurora, CO (G.G.S.)."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2393-0855","authenticated-orcid":true,"given":"Manesh R.","family":"Patel","sequence":"additional","affiliation":[{"name":"Duke Clinical Research Institute, Durham, NC (S.V., D.W., W.S.J., M.R.P., R.D.L., R.H.)."},{"name":"Departments of Medicine (S.V., W.S.J., M.R.P., R.D.L.), Duke University School of Medicine, Durham, NC."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2999-4961","authenticated-orcid":true,"given":"Renato D.","family":"Lopes","sequence":"additional","affiliation":[{"name":"Duke Clinical Research Institute, Durham, NC (S.V., D.W., W.S.J., M.R.P., R.D.L., R.H.)."},{"name":"Departments of Medicine (S.V., W.S.J., M.R.P., R.D.L.), Duke University School of Medicine, Durham, NC."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4980-845X","authenticated-orcid":true,"given":"Ricardo","family":"Henao","sequence":"additional","affiliation":[{"name":"Duke Clinical Research Institute, Durham, NC (S.V., D.W., W.S.J., M.R.P., R.D.L., R.H.)."},{"name":"Electrical and Computer Engineering (R.H.), Duke University School of Medicine, Durham, NC."},{"name":"Department of Biostatistics and Bioinformatics, Duke University, Durham, NC (K.P.G., R.H.)."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1177\/1740774520939231"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2025.10.055"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2023.4859"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1801174"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa1611688"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(1950)3:1<32::aid-cncr2820030106>3.0.co;2-3"},{"key":"e_1_3_3_8_2","unstructured":"Nixon J Dusenberry M Zhang L Jerfel G Tran D. Measuring calibration in deep learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 2019 pp. 2."},{"key":"e_1_3_3_9_2","doi-asserted-by":"crossref","unstructured":"Niculescu-Mizil A Caruana CR. Predicting good probabilities with supervised learning. 22nd International Conference on Machine Learning 2005:624\u2013632.","DOI":"10.1145\/1102351.1102430"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1186\/cvm-2-4-187"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cct.2006.02.002"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehae753"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1111\/jth.13626"},{"key":"e_1_3_3_14_2","unstructured":"Wang AT Convertino W Cheng X Henao R Carin L On Understanding Attention-Based In-Context Learning for Categorical Data. In Forty-second International Conference on Machine Learning. Accessed May 11 2026. https:\/\/doi.org\/10.48550\/arXiv.2405.17248"}],"container-title":["Circulation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ahajournals.org\/doi\/full\/10.1161\/CIRCULATIONAHA.126.080072","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T18:01:51Z","timestamp":1781632911000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ahajournals.org\/doi\/10.1161\/CIRCULATIONAHA.126.080072"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,2]]},"references-count":13,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2026,6,2]]}},"alternative-id":["10.1161\/CIRCULATIONAHA.126.080072"],"URL":"https:\/\/doi.org\/10.1161\/circulationaha.126.080072","relation":{},"ISSN":["0009-7322","1524-4539"],"issn-type":[{"value":"0009-7322","type":"print"},{"value":"1524-4539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,2]]},"assertion":[{"value":"2026-02-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}