{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T19:03:16Z","timestamp":1792695796382,"version":"4.5.0"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T00:00:00Z","timestamp":1786060800000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to identify trajectories of multimorbidity following acute myocardial infarction (AMI), using explainable temporal machine-learning methods, and assess their clinical, prognostic, and biological significance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>Dynamic Time Warping k-means clustering was applied to post-AMI diagnostic sequences from 12\u00a0701 UK-Biobank participants. Latent Dirichlet Allocation characterised cluster themes. Multiclass classifiers (CatBoost, XGBoost, random forest, logistic regression) trained on pre-AMI diagnoses and demographics predicted trajectory membership, with SHAP interpretability. SMART scores and Cox models evaluated 5-year mortality; Phenotype-Wide Association (PheWAS) and Reactome pathway enrichment were used to identify associated biological mechanisms.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Three trajectories of multimorbidity were identified: acute cardiorenal-respiratory with metabolic disease (ACUTE-CARD; 63.4%), cardiometabolic disease with arrhythmic-ischemic burden (CARDIOMIX; 13.5%), and smoking-related multisystem multimorbidity (SMO-CARD; 23.1%). XGBoost achieved the highest discrimination (AUC-ROC 0.906; 95% CI, 0.895-0.916), with CatBoost showing comparable performance (AUC-ROC 0.900; 95% CI, 0.889-0.910). SMO-CARD had the highest 5-year mortality (43.9%). The established SMART cardiovascular risk score remained the dominant predictor of mortality while the identified trajectories provided complementary prognostic signals; these associations were weaker after full adjustment for potential confounders with each profile displaying distinct genetic and pathway signatures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The SMART score outperformed in capturing mortality risk, whereas the trajectories complement it by revealing nuanced clustering of risk factors across organ systems and in identifying trajectory-specific intervention priorities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Explainable temporal modeling of EHR data reveals clinically interpretable, biologically grounded multimorbidity trajectories after AMI that complement established risk scores and provide a reproducible approach to mechanistic phenotyping and precision care.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocag135","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T11:22:51Z","timestamp":1784546571000},"page":"2092-2101","source":"Crossref","is-referenced-by-count":1,"title":["Explainable temporal machine learning of multimorbidity trajectories after acute myocardial infarction: complementing clinical risk scores with mechanistic phenotypes"],"prefix":"10.1093","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1429-0032","authenticated-orcid":false,"given":"Anthony","family":"Onoja","sequence":"first","affiliation":[{"name":"School of Health Sciences, Faculty of Health and Medical Sciences, University of Surrey , Guildford, GU2 7XH,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kris","family":"Elomaa","sequence":"additional","affiliation":[{"name":"School of Health Sciences, Faculty of Health and Medical Sciences, University of Surrey , Guildford, GU2 7XH,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anthony D","family":"Whetton","sequence":"additional","affiliation":[{"name":"School of Biosciences and Veterinary Health Innovation Engine, School of Veterinary Medicine, University of Surrey , Guildford, GU2 7XH,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nophar","family":"Geifman","sequence":"additional","affiliation":[{"name":"School of Health Sciences, Faculty of Health and Medical Sciences, University of Surrey , Guildford, GU2 7XH,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,6]]},"reference":[{"key":"2026102204071545800_ocag135-B1","doi-asserted-by":"crossref","first-page":"2190","DOI":"10.3390\/jcm14072190","article-title":"Acute myocardial infarction mortality in the older population of the United States: an analysis of demographic and regional trends and disparities from 1999 to 2022","volume":"14","author":"Abdul Jabbar","year":"2025","journal-title":"J Clin Med"},{"key":"2026102204071545800_ocag135-B2","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1038\/s44325-025-00046-w","article-title":"Demographic and regional trends of acute myocardial infarction-related mortality among young adults in the US, 1999\u20132020","volume":"2","author":"Li","year":"2025","journal-title":"NPJ Cardiovasc Health"},{"key":"2026102204071545800_ocag135-B3","doi-asserted-by":"crossref","first-page":"1758","DOI":"10.1093\/eurjpc\/zwad214","article-title":"Trends in acute myocardial infarction mortality in the European Union, 2012\u20132020","volume":"30","author":"Zuin","year":"2023","journal-title":"Eur J Prev Cardiol"},{"key":"2026102204071545800_ocag135-B4","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.1136\/jech-2015-205689","article-title":"Mortality from heart failure, acute myocardial infarction and other ischaemic heart disease in England and Oxford: a trend study of multiple-cause-coded death certification","volume":"69","author":"Rahimi","year":"2015","journal-title":"J Epidemiol Community Health"},{"key":"2026102204071545800_ocag135-B5","doi-asserted-by":"crossref","first-page":"2209","DOI":"10.1093\/eurheartj\/ehaa035","article-title":"Acute myocardial infarction","volume":"41","author":"Hartikainen","year":"2023","journal-title":"Euro Heart J"},{"key":"2026102204071545800_ocag135-B6","doi-asserted-by":"crossref","first-page":"e0293314","DOI":"10.1371\/journal.pone.0293314","article-title":"Comorbidity clusters and in-hospital outcomes in patients admitted with acute myocardial infarction in the USA: A national population-based study","volume":"18","author":"Zghebi","year":"2023","journal-title":"PLoS One"},{"key":"2026102204071545800_ocag135-B7","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1186\/s13054-019-2486-6","article-title":"Multimorbidity states associated with higher mortality rates in organ dysfunction and sepsis: A data-driven analysis in critical care","volume":"23","author":"Zador","year":"2019","journal-title":"Crit Care"},{"key":"2026102204071545800_ocag135-B8","doi-asserted-by":"crossref","first-page":"e1002501","DOI":"10.1371\/journal.pmed.1002501","article-title":"Multimorbidity and survival for patients with acute myocardial infarction in England and Wales: Latent class analysis of a nationwide population-based cohort","volume":"15","author":"Hall","year":"2018","journal-title":"PLoS Med"},{"key":"2026102204071545800_ocag135-B9","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1186\/s12916-021-02098-y","article-title":"Association of multimorbidity and changes in health-related quality of life following myocardial infarction: a UK multicentre longitudinal patient-reported outcomes study","volume":"19","author":"Munyombwe","year":"2021","journal-title":"BMC Med"},{"key":"2026102204071545800_ocag135-B10","doi-asserted-by":"crossref","first-page":"oeae009","DOI":"10.1093\/ehjopen\/oeae009","article-title":"Impact of multimorbidity patterns on outcomes and treatment in patients with coronary artery disease","volume":"4","author":"Zheng","year":"2024","journal-title":"Eur Heart J Open"},{"key":"2026102204071545800_ocag135-B11","doi-asserted-by":"crossref","first-page":"e064275","DOI":"10.1136\/bmjopen-2022-064275","article-title":"Multimorbidity of cardiometabolic diseases: a cross-sectional study of patterns, clusters and associated risk factors in sub-Saharan Africa","volume":"13","author":"Otieno","year":"2023","journal-title":"BMJ Open"},{"key":"2026102204071545800_ocag135-B12","doi-asserted-by":"crossref","first-page":"e46821","DOI":"10.2196\/46821","article-title":"Assessing global, regional, and national time trends and associated risk factors of the mortality in ischemic heart disease through global burden of disease 2019 study: population-based study","volume":"10","author":"Shu","year":"2024","journal-title":"JMIR Public Health Surveill"},{"key":"2026102204071545800_ocag135-B13","doi-asserted-by":"crossref","first-page":"euae102.541","DOI":"10.1093\/europace\/euae102.541","article-title":"Temporal order of atrial fibrillation and acute myocardial infarction and associated prognosis in the Danish Diet, Cancer, and Health cohort","volume":"26","author":"Frederiksen","year":"2024","journal-title":"EP Europace"},{"key":"2026102204071545800_ocag135-B14","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.1161\/CIRCULATIONAHA.116.021314","article-title":"Distribution of estimated 10-year risk of recurrent vascular events and residual risk in a secondary prevention population","volume":"134","author":"Kaasenbrood","year":"2016","journal-title":"Circulation"},{"key":"2026102204071545800_ocag135-B15","first-page":"100558","article-title":"Association of comorbidities with clinical outcomes in patients after acute myocardial infarction","volume":"29","author":"Baechli","year":"2020","journal-title":"Int J Cardiol Heart Vasc"},{"key":"2026102204071545800_ocag135-B16","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1093\/CVR\/CVAE240","article-title":"Inflammageing, a targetable pathway for preventing cardiovascular diseases","volume":"121","author":"Aranda","year":"2025","journal-title":"Cardiovasc Res"},{"key":"2026102204071545800_ocag135-B17","doi-asserted-by":"crossref","first-page":"752","DOI":"10.1016\/S0140-6736(12)62167-9","article-title":"Frailty in elderly people","volume":"381","author":"Clegg","year":"2013","journal-title":"Lancet"},{"key":"2026102204071545800_ocag135-B18","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1089\/rej.2016.1905","article-title":"Frailty and risk of cardiovascular diseases in older persons: the age, gene\/environment susceptibility-reykjavik study","volume":"20","author":"Veronese","year":"2017","journal-title":"Rejuvenation Res"},{"key":"2026102204071545800_ocag135-B19","first-page":"487","author":"Wang","year":"2018"},{"key":"2026102204071545800_ocag135-B20","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1117\/12.2666085","article-title":"Explainability and causality for robust, fair, and trustworthy artificial reasoning","author":"Rawal","year":"2023"},{"key":"2026102204071545800_ocag135-B21","doi-asserted-by":"crossref","first-page":"2733","DOI":"10.1007\/s10618-022-00889-2","article-title":"Counterfactual explanations as interventions in latent space","volume":"38","author":"Crupi","year":"2024","journal-title":"Data Min Knowl Disc"},{"key":"2026102204071545800_ocag135-B22","first-page":"143","article-title":"CAGE: causality-aware shapley value for global explanations","volume":"2155","author":"Breuer","year":"2024","journal-title":"Commun Comput Inf Sci"},{"key":"2026102204071545800_ocag135-B23","first-page":"108","article-title":"Causality-aware local interpretable model-agnostic explanations","volume":"2155","author":"Cinquini","year":"2024","journal-title":"Commun Comput Inf Sci"},{"key":"2026102204071545800_ocag135-B24","doi-asserted-by":"publisher","author":"Albini","year":"2023","DOI":"10.1145\/3600211.3604676"},{"key":"2026102204071545800_ocag135-B25","first-page":"5154","article-title":"Towards trustable explainable AI","author":"Ignatiev","year":"2020"},{"key":"2026102204071545800_ocag135-B26","author":"Duell","year":"2021"},{"key":"2026102204071545800_ocag135-B27","author":"UK Biobank - UK Biobank"},{"key":"2026102204071545800_ocag135-B28","first-page":"1","article-title":"Signaling pathways and targeted therapy for myocardial infarction","volume":"7","author":"Zhang","year":"2022","journal-title":"Signal Transduct Target Ther"},{"key":"2026102204071545800_ocag135-B29","doi-asserted-by":"crossref","first-page":"1923","DOI":"10.1093\/eurheartj\/ehv195","article-title":"Acute myocardial infarction activates distinct inflammation and proliferation pathways in circulating monocytes, prior to recruitment, and identified through conserved transcriptional responses in mice and humans","volume":"36","author":"Ruparelia","year":"2015","journal-title":"Eur Heart J"},{"key":"2026102204071545800_ocag135-B30","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1472-6963-6-161","article-title":"ICD-10 coding algorithms for defining comorbidities of acute myocardial infarction","volume":"6","author":"So","year":"2006","journal-title":"BMC Health Serv. Res"},{"key":"2026102204071545800_ocag135-B31","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1016\/j.jclinepi.2006.12.009","article-title":"ICD-10 adaptations of the Ontario acute myocardial infarction mortality prediction rules performed as well as the original versions","volume":"60","author":"Vermeulen","year":"2007","journal-title":"J Clin Epidemiol"},{"key":"2026102204071545800_ocag135-B32","doi-asserted-by":"crossref","first-page":"e0253580","DOI":"10.1371\/journal.pone.0253580","article-title":"Acute myocardial infarction: Development and application of an ICD-10-CM-based algorithm to a large U.S. healthcare claims-based database","volume":"16","author":"Saunders-Hastings","year":"2021","journal-title":"PLoS One"},{"key":"2026102204071545800_ocag135-B33","doi-asserted-by":"publisher","first-page":"993","DOI":"10.5555\/944919.944937","article-title":"Latent dirichlet allocation","volume":"3","author":"Blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"2026102204071545800_ocag135-B34","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1016\/j.jbi.2015.10.001","article-title":"Learning probabilistic phenotypes from heterogeneous EHR data","volume":"58","author":"Pivovarov","year":"2015","journal-title":"J Biomed Inform"},{"key":"2026102204071545800_ocag135-B35","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":"2026102204071545800_ocag135-B36","doi-asserted-by":"crossref","first-page":"btad622","DOI":"10.1093\/bioinformatics\/btad655","article-title":"Next-generation phenotyping: introducing phecodeX for enhanced discovery research in medical phenomics","volume":"39","author":"Shuey","year":"2023","journal-title":"Bioinformatics"},{"key":"2026102204071545800_ocag135-B37","doi-asserted-by":"crossref","first-page":"e1312","DOI":"10.1002\/widm.1312","article-title":"Causability and explainability of artificial intelligence in medicine","volume":"9","author":"Holzinger","year":"2019","journal-title":"Wiley Interdiscip Rev Data Min Knowl Discov"},{"key":"2026102204071545800_ocag135-B38","first-page":"9391","article-title":"Reliable post hoc explanations: modeling uncertainty in explainability","volume":"34","author":"Slack","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"2026102204071545800_ocag135-B39","doi-asserted-by":"publisher","author":"Islam","year":"2022","DOI":"10.1109\/IRI54793.2022.00069"},{"key":"2026102204071545800_ocag135-B40","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1002\/hast.973","article-title":"Artificial intelligence and black-box medical decisions: accuracy versus explainability","volume":"49","author":"London","year":"2019","journal-title":"Hastings Cent Rep"},{"key":"2026102204071545800_ocag135-B41","doi-asserted-by":"crossref","first-page":"210410","DOI":"10.1109\/ACCESS.2020.3040166","article-title":"Explainable prediction of acute myocardial infarction using machine learning and shapley values","volume":"8","author":"Ibrahim","year":"2020","journal-title":"IEEE Access"},{"key":"2026102204071545800_ocag135-B42","doi-asserted-by":"crossref","first-page":"1216","DOI":"10.1038\/s41562-023-01579-9","article-title":"Participation bias in the UK Biobank distorts genetic associations and downstream analyses","volume":"7","author":"Schoeler","year":"2023","journal-title":"Nat Hum Behav"},{"key":"2026102204071545800_ocag135-B43"}],"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\/ocag135\/70512926\/ocag135.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/11\/2092\/70512926\/ocag135.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/11\/2092\/70512926\/ocag135.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T08:07:28Z","timestamp":1792656448000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/33\/11\/2092\/8753703"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,6]]},"references-count":43,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2026,8,6]]},"published-print":{"date-parts":[[2026,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocag135","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,11]]},"published":{"date-parts":[[2026,8,6]]}}}