{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T22:06:05Z","timestamp":1790633165559,"version":"4.1.0"},"reference-count":50,"publisher":"BMJ","issue":"2","license":[{"start":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T00:00:00Z","timestamp":1789084800000},"content-version":"unspecified","delay-in-days":72,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Centre for Studies in Primary Care Research Initiation Grant"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["Open Heart"],"accepted":{"date-parts":[[2026,8,13]]},"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To examine whether the outputs of machine learning algorithms designed to predict risk of cardiovascular disease (CVD) address known deficiencies of the Framingham Risk Score (FRS) and improve risk estimates.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>For this critical review, Medline, Embase and IEEE were searched from inception to 1 January 2025. Included were studies describing machine learning algorithms designed to specifically compare output of cardiovascular risk assessment with the FRS. Commentaries, letters, unpublished work or non-peer-reviewed papers were excluded.<\/jats:p>\n                    <jats:p>Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, two reviewers screened titles and abstracts independently, then populated a purpose-built data extraction form. A subsequent qualitative thematic analysis focused on algorithms\u2019 strengths, added value, potential harms, unintended consequences and equity implications.<\/jats:p>\n                    <jats:p>The main outcome assessed was whether, among healthy adults, the algorithm improved CVD risk prediction relative to the FRS.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Of 707 studies retrieved, 29 met inclusion criteria. 23 reported improved predictive ability relative to the FRS. Most datasets and\/or medical records used included sociodemographic predictors of CVD not included among FRS inputs. Some added costly diagnostic tests like CT angiography to FRS screening indicators. When they were defined, inputs and outcomes such as hypertension or myocardial infarction did not always adhere to FRS values. Statistical significance was generally taken as a proxy for clinical significance. Some algorithms overestimated the number at risk compared with the FRS without discussing whether that larger proportion might be at risk of overdiagnosis rather than CVD, while a few decreased the proportion found to be at risk.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Use of artificial intelligence to improve accuracy of risk assessment for CVD demonstrates the technological capacity to merge known sociodemographic predictors with biologic variables and examine non-linear interactions among these. Still needed to achieve patient benefit is clinical insight, adherence to screening principles and cost\u2013benefit assessment of inputs selected.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/openhrt-2026-004228","type":"journal-article","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:10:14Z","timestamp":1789207814000},"page":"e004228","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":1,"title":["Future promise, current clinical ambiguity: a systematic review of machine learning algorithm outputs predicting risk of cardiovascular disease"],"prefix":"10.1136","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4798-1742","authenticated-orcid":false,"given":"Susan P","family":"Phillips","sequence":"first","affiliation":[{"name":"Family Medicine, Queen\u2019s University Faculty of Health Sciences, Kingston, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han","family":"Han","sequence":"additional","affiliation":[{"name":"Centre for Studies in Primary Care, Queen\u2019s University Faculty of Health Sciences, Kingston, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"2026091203100611000_13.2.e004228.1","first-page":"838","article-title":"The accuracy of the Framingham risk-score in different socioeconomic groups: a prospective study","volume":"55","author":"Brindle","year":"2005","journal-title":"Br J Gen Pract"},{"key":"2026091203100611000_13.2.e004228.2","doi-asserted-by":"publisher","DOI":"10.1016\/j.atherosclerosis.2005.04.004"},{"key":"2026091203100611000_13.2.e004228.3","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1093\/ehjdh\/ztae080","article-title":"Machine learning based prediction models for cardiovascular disease risk using electronic health records data: systematic review and meta-analysis","volume":"6","author":"Liu","year":"2025","journal-title":"Eur Heart J Digit Health"},{"key":"2026091203100611000_13.2.e004228.4","unstructured":"World Health Organization . Cardiovascular diseases (CVDs). Available: https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/cardiovascular-diseases-(cvds) [Accessed 31 Jul 2025]."},{"key":"2026091203100611000_13.2.e004228.5","doi-asserted-by":"crossref","DOI":"10.1186\/s12916-019-1340-7","article-title":"Performance of the Framingham risk models and pooled cohort equations for predicting 10-year risk of cardiovascular disease: a systematic review and meta-analysis","volume":"17","author":"Damen","year":"2019","journal-title":"BMC Med"},{"key":"2026091203100611000_13.2.e004228.6","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0174944","article-title":"Can machine-learning improve cardiovascular risk prediction using routine clinical data?","volume":"12","author":"Weng","year":"2017","journal-title":"PLoS One"},{"key":"2026091203100611000_13.2.e004228.7","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph18063187","article-title":"Predicting Australian Adults at High Risk of Cardiovascular Disease Mortality Using Standard Risk Factors and Machine Learning","volume":"18","author":"Sajeev","year":"2021","journal-title":"Int J Environ Res Public Health"},{"key":"2026091203100611000_13.2.e004228.8","doi-asserted-by":"publisher","DOI":"10.1503\/cmaj.190848"},{"key":"2026091203100611000_13.2.e004228.9","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.117.029652"},{"key":"2026091203100611000_13.2.e004228.10","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0213653","article-title":"Cardiovascular disease risk prediction using automated machine learning: A prospective study of 423,604 UK Biobank participants","volume":"14","author":"Alaa","year":"2019","journal-title":"PLoS ONE"},{"key":"2026091203100611000_13.2.e004228.11","doi-asserted-by":"crossref","DOI":"10.1136\/bmjopen-2022-067638","article-title":"Social bias in artificial intelligence algorithms designed to improve cardiovascular risk assessment relative to the Framingham Risk Score: a protocol for a systematic review","volume":"13","author":"Garcha","year":"2023","journal-title":"BMJ Open"},{"key":"2026091203100611000_13.2.e004228.12","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1000097","article-title":"Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement","volume":"6","author":"Moher","year":"2009","journal-title":"PLoS Med"},{"key":"2026091203100611000_13.2.e004228.13","doi-asserted-by":"publisher","DOI":"10.7326\/M18-1377"},{"key":"2026091203100611000_13.2.e004228.14","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2021.100364","article-title":"Selection of 51 predictors from 13,782 candidate multimodal features using machine learning improves coronary artery disease prediction","volume":"2","author":"Agrawal","year":"2021","journal-title":"Patterns (N Y)"},{"key":"2026091203100611000_13.2.e004228.15","doi-asserted-by":"crossref","first-page":"3045","DOI":"10.1016\/S0735-1097(21)04400-4","article-title":"Artificial intelligence applied to ECG improves heart failure prediction accuracy","volume":"77","author":"Akbilgic","year":"2021","journal-title":"J Am Coll Cardiol"},{"key":"2026091203100611000_13.2.e004228.16","doi-asserted-by":"crossref","first-page":"105209","DOI":"10.1016\/j.ijmedinf.2023.105209","article-title":"Cardiometabolic risk estimation using exposome data and machine learning","volume":"179","author":"Atehort\u00faa","year":"2023","journal-title":"Int J Med Inform"},{"key":"2026091203100611000_13.2.e004228.17","doi-asserted-by":"crossref","first-page":"8886","DOI":"10.1038\/s41598-021-88257-w","article-title":"Pre-existing and machine learning-based models for cardiovascular risk prediction","volume":"11","author":"Cho","year":"2021","journal-title":"Sci Rep"},{"key":"2026091203100611000_13.2.e004228.18","doi-asserted-by":"crossref","first-page":"1687","DOI":"10.1007\/s10072-023-06610-5","article-title":"Stroke prevention in rural residents: development of a simplified risk assessment tool with artificial intelligence","volume":"44","author":"Ding","year":"2023","journal-title":"Neurol Sci"},{"key":"2026091203100611000_13.2.e004228.19","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.2217\/epi-2021-0123","article-title":"External validation of integrated genetic-epigenetic biomarkers for predicting incident coronary heart disease","volume":"13","author":"Dogan","year":"2021","journal-title":"Epigenomics"},{"key":"2026091203100611000_13.2.e004228.20","doi-asserted-by":"crossref","DOI":"10.1007\/s13755-024-00310-w","article-title":"Machine-learning-based prediction of cardiovascular events for hyperlipidemia population with lipid variability and remnant cholesterol as biomarkers","volume":"12","author":"Du","year":"2024","journal-title":"Health Inf Sci Syst"},{"key":"2026091203100611000_13.2.e004228.21","doi-asserted-by":"crossref","first-page":"244","DOI":"10.1097\/QMH.0000000000000309","article-title":"Improvement in the Prediction of Coronary Heart Disease Risk by Using Artificial Neural Networks","volume":"30","author":"Goldman","year":"2021","journal-title":"Qual Manag Health Care"},{"key":"2026091203100611000_13.2.e004228.22","doi-asserted-by":"crossref","DOI":"10.1186\/s12938-024-01273-5","article-title":"Improving cardiovascular risk prediction with machine learning: a focus on perivascular adipose tissue characteristics","volume":"23","author":"He","year":"2024","journal-title":"Biomed Eng Online"},{"key":"2026091203100611000_13.2.e004228.23","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1001\/jama.2022.24683","article-title":"Predictive Accuracy of Stroke Risk Prediction Models Across Black and White Race, Sex, and Age Groups","volume":"329","author":"Hong","year":"2023","journal-title":"JAMA"},{"key":"2026091203100611000_13.2.e004228.24","doi-asserted-by":"crossref","first-page":"586","DOI":"10.1177\/10815589231169689","article-title":"Framingham risk score conventional risk factors are potent to predict all-cause mortality using machine learning algorithms: a population-based prospective cohort study over 40 years in China","volume":"71","author":"Huang","year":"2023","journal-title":"J Investig Med"},{"key":"2026091203100611000_13.2.e004228.25","doi-asserted-by":"crossref","DOI":"10.1136\/fmch-2023-002340","article-title":"Development and validation of multicentre study on novel Artificial Intelligence-based Cardiovascular Risk Score (AICVD)","volume":"12","author":"Jalepalli","year":"2024","journal-title":"Fam Med Com Health"},{"key":"2026091203100611000_13.2.e004228.26","doi-asserted-by":"crossref","first-page":"818","DOI":"10.2214\/AJR.19.22578","article-title":"Prognostic Implications of Coronary CT Angiography: 12-Year Follow-Up of 6892 Patients","volume":"215","author":"Johnson","year":"2020","journal-title":"AJR Am J Roentgenol"},{"key":"2026091203100611000_13.2.e004228.27","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0271723","article-title":"An evolutionary machine learning algorithm for cardiovascular disease risk prediction","volume":"17","author":"Ordikhani","year":"2022","journal-title":"PLoS One"},{"key":"2026091203100611000_13.2.e004228.28","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0232414","article-title":"Machine learning provides evidence that stroke risk is not linear: The non-linear Framingham stroke risk score","volume":"15","author":"Orfanoudaki","year":"2020","journal-title":"PLoS One"},{"key":"2026091203100611000_13.2.e004228.29","doi-asserted-by":"crossref","first-page":"136758","DOI":"10.1109\/ACCESS.2023.3338369","article-title":"Forecasting Coronary Heart Disease Risk With a 2-Step Hybrid Ensemble Learning Method and Forward Feature Selection Algorithm","volume":"11","author":"Patra","year":"2023","journal-title":"IEEE Access"},{"key":"2026091203100611000_13.2.e004228.30","doi-asserted-by":"crossref","DOI":"10.1186\/s12889-023-15630-x","article-title":"Study on the prediction model of atherosclerotic cardiovascular disease in the rural Xinjiang population based on survival analysis","volume":"23","author":"Qian","year":"2023","journal-title":"BMC Public Health"},{"key":"2026091203100611000_13.2.e004228.31","doi-asserted-by":"crossref","first-page":"967097","DOI":"10.3389\/fcvm.2022.967097","article-title":"Development and validation of a cardiovascular diseases risk prediction model for Chinese males (CVDMCM)","volume":"9","author":"Shan","year":"2022","journal-title":"Front Cardiovasc Med"},{"key":"2026091203100611000_13.2.e004228.32","doi-asserted-by":"crossref","DOI":"10.2196\/38040","article-title":"The Impact of Time Horizon on Classification Accuracy: Application of Machine Learning to Prediction of Incident Coronary Heart Disease","volume":"6","author":"Simon","year":"2022","journal-title":"JMIR Cardio"},{"key":"2026091203100611000_13.2.e004228.33","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1007\/s00330-020-07083-2","article-title":"Improved long-term prognostic value of coronary CT angiography-derived plaque measures and clinical parameters on adverse cardiac outcome using machine learning","volume":"31","author":"Tesche","year":"2021","journal-title":"Eur Radiol"},{"key":"2026091203100611000_13.2.e004228.34","doi-asserted-by":"crossref","DOI":"10.1155\/2016\/3016245","article-title":"Development of Health Parameter Model for Risk Prediction of CVD Using SVM","volume":"2016","author":"Unnikrishnan","year":"2016","journal-title":"Comput Math Methods Med"},{"key":"2026091203100611000_13.2.e004228.35","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0092840","article-title":"Lipoprotein Metabolism Indicators Improve Cardiovascular Risk Prediction","volume":"9","author":"van Schalkwijk","year":"2014","journal-title":"PLoS ONE"},{"key":"2026091203100611000_13.2.e004228.36","doi-asserted-by":"crossref","DOI":"10.2196\/30277","article-title":"Accurate Prediction of Stroke for Hypertensive Patients Based on Medical Big Data and Machine Learning Algorithms: Retrospective Study","volume":"9","author":"Yang","year":"2021","journal-title":"JMIR Med Inform"},{"key":"2026091203100611000_13.2.e004228.37","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1093\/ehjdh\/ztad023","article-title":"Cardiovascular disease risk assessment using a deep-learning-based retinal biomarker: a comparison with existing risk scores","volume":"4","author":"Yi","year":"2023","journal-title":"Eur Heart J Digit Health"},{"key":"2026091203100611000_13.2.e004228.38","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1016\/j.amjcard.2018.11.044","article-title":"Usefulness of a Coronary Artery Disease Predictive Algorithm to Predict Global Risk for Cardiovascular Disease and Acute Coronary Syndrome","volume":"123","author":"Younus","year":"2019","journal-title":"Am J Cardiol"},{"key":"2026091203100611000_13.2.e004228.39","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1007\/s13167-018-0142-x","article-title":"A new non-invasive diagnostic tool in coronary artery disease: artificial intelligence as an essential element of predictive, preventive, and personalized medicine","volume":"9","author":"Zellweger","year":"2018","journal-title":"EPMA J"},{"key":"2026091203100611000_13.2.e004228.40","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1186\/s13148-022-01232-8","article-title":"A deep learning model for early risk prediction of heart failure with preserved ejection fraction by DNA methylation profiles combined with clinical features","volume":"14","author":"Zhao","year":"2022","journal-title":"Clin Epigenet"},{"key":"2026091203100611000_13.2.e004228.41","doi-asserted-by":"publisher","DOI":"10.7326\/M14-0698"},{"key":"2026091203100611000_13.2.e004228.42","doi-asserted-by":"crossref","DOI":"10.1136\/openhrt-2025-003874","article-title":"When cardiology forgets to ask why","volume":"12","author":"Tona","year":"2025","journal-title":"Open Heart"},{"key":"2026091203100611000_13.2.e004228.43","doi-asserted-by":"publisher","DOI":"10.1093\/eurheartj\/ehac238"},{"key":"2026091203100611000_13.2.e004228.44","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.amjcard.2023.04.011","article-title":"Comprehensive Prediction of Subclinical Coronary Atherosclerosis in Subjects Without Traditional Cardiovascular Risk Factors","volume":"198","author":"Park","year":"2023","journal-title":"Am J Cardiol"},{"key":"2026091203100611000_13.2.e004228.45","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.e3502","article-title":"Preventing overdiagnosis: how to stop harming the healthy","volume":"344","author":"Moynihan","year":"2012","journal-title":"BMJ"},{"key":"2026091203100611000_13.2.e004228.46","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.327.7426.1267"},{"key":"2026091203100611000_13.2.e004228.47","doi-asserted-by":"publisher","DOI":"10.1111\/j.1471-1842.2009.00848.x"},{"key":"2026091203100611000_13.2.e004228.48","doi-asserted-by":"crossref","unstructured":"Corian\u00f2 M , Lanera C , Masci PG , et al . A pipeline for developing deep learning prognostic prediction models in cardiac magnetic resonance image analysis. Eur Heart J Digit Health 2026;7. doi:10.1093\/ehjdh\/ztaf101","DOI":"10.1093\/ehjdh\/ztaf101"},{"key":"2026091203100611000_13.2.e004228.49","unstructured":"Heikkil\u00e4 M . AI medical tools downplay symptoms in women and ethnic minorities. Financial Times; 2025."},{"key":"2026091203100611000_13.2.e004228.50","doi-asserted-by":"crossref","first-page":"e953","DOI":"10.1161\/CIR.0000000000001401","article-title":"Criteria to Assess the Predictive and Clinical Utility of Novel Models, Biomarkers, and Tools for Risk of Cardiovascular Disease: A Scientific Statement From the American Heart Association","volume":"153","author":"Khan","year":"2026","journal-title":"Circulation"}],"container-title":["Open Heart"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/openhrt-2026-004228","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:10:20Z","timestamp":1789207820000},"score":1,"resource":{"primary":{"URL":"https:\/\/openheart.bmj.com\/lookup\/doi\/10.1136\/openhrt-2026-004228"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":50,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,9,12]]},"published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1136\/openhrt-2026-004228"],"URL":"https:\/\/doi.org\/10.1136\/openhrt-2026-004228","relation":{},"ISSN":["2053-3624"],"issn-type":[{"value":"2053-3624","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7]]}}}