{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T14:46:30Z","timestamp":1785509190930,"version":"3.56.0"},"reference-count":28,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T00:00:00Z","timestamp":1742342400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Department of Health and Human Services under NIH SBIR","award":["R43NS102100"],"award-info":[{"award-number":["R43NS102100"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Stroke is a leading cause of death and disability in developed countries. We validated an AI-based prediction model for incident stroke using sensors such as fundus cameras and ophthalmoscopes for retinal images, along with socio-demographic data and traditional risk factors. The model was trained on a proprietary dataset of over 6500 participants, including 171 with 5-year incident strokes and 242 with 10-year incident strokes. The model provides separate 5-year and 10-year risk scores. The model was externally validated on the UK Biobank dataset (3000 subjects with 5-year incident strokes). Using retinal imaging, our models identified individuals with 5-year incident strokes with 80% sensitivity, 82% specificity, and an AUC of 0.83, and predicted 10-year incidents with 72% sensitivity, 78% specificity, and an AUC of 0.79. In comparison, for the 10-year model, the AUC for the Framingham score was 0.73, and the CHADS2 score was 0.74. On the Biobank external dataset, our 5-year model (without retinal features) demonstrated moderate but lower sensitivity (69.3%) and specificity (66.4%) compared to its performance on the proprietary dataset (with retinal features). Using a multi-ethnic dataset, we developed and validated a prediction model that improves stroke risk identification for 5-year and 10-year incidences by incorporating retinal features.<\/jats:p>","DOI":"10.3390\/s25061917","type":"journal-article","created":{"date-parts":[[2025,3,19]],"date-time":"2025-03-19T07:48:37Z","timestamp":1742370517000},"page":"1917","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A Machine Learning Prediction Model to Identify Individuals at Risk of 5-Year Incident Stroke Based on Retinal Imaging"],"prefix":"10.3390","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7458-5361","authenticated-orcid":false,"given":"Arun","family":"Govindaiah","sequence":"first","affiliation":[{"name":"iHealthScreen Inc., Richmond Hill, NY 11418, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tasin","family":"Bhuiyan","sequence":"additional","affiliation":[{"name":"iHealthScreen Inc., Richmond Hill, NY 11418, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1693-943X","authenticated-orcid":false,"given":"R. Theodore","family":"Smith","sequence":"additional","affiliation":[{"name":"Biomolecular Retinal Imaging, Department of Ophthalmology, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mandip S.","family":"Dhamoon","sequence":"additional","affiliation":[{"name":"Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alauddin","family":"Bhuiyan","sequence":"additional","affiliation":[{"name":"iHealthScreen Inc., Richmond Hill, NY 11418, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,19]]},"reference":[{"key":"ref_1","unstructured":"CDC-Stroke (2024, June 30). CDC: Stroke Facts, Available online: https:\/\/www.cdc.gov\/Stroke\/about\/index.html."},{"key":"ref_2","unstructured":"Medscape (2016, August 23). CDC: One Fourth of CVD Deaths Avoidable. Medscape., Available online: http:\/\/www.medscape.com\/viewarticle\/810371."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1161\/01.STR.22.3.312","article-title":"Probability of stroke: A risk profile from the Framingham Study","volume":"22","author":"Wolf","year":"1991","journal-title":"Stroke"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"925","DOI":"10.1111\/j.1365-2362.2007.01888.x","article-title":"Assessing risk of myocardial infarction and stroke: New data from the Prospective Cardiovascular M\u00fcnster (PROCAM) study","volume":"37","author":"Assmann","year":"2007","journal-title":"Eur. J. Clin. Investig."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"145","DOI":"10.4236\/wjcd.2017.75014","article-title":"Risk Factors and Prediction of Stroke in a Population with High Prevalence of Diabetes: The Strong Heart Study","volume":"7","author":"Wang","year":"2017","journal-title":"World J. Cardiovasc. Dis."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.cmpb.2017.10.007","article-title":"The development and implementation of stroke risk prediction model in National Health Insurance Service\u2019s personal health record","volume":"153","author":"Lee","year":"2018","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1159\/000334473","article-title":"Developing and Validating a Predictive Model for Stroke Progression","volume":"1","author":"Craig","year":"2011","journal-title":"Cerebrovasc. Dis. Extra"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1858","DOI":"10.1161\/STROKEAHA.110.586222","article-title":"Constructing the prediction model for the risk of stroke in a Chinese population: Report from a cohort study in Taiwan","volume":"41","author":"Chien","year":"2010","journal-title":"Stroke"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1267","DOI":"10.1136\/bmj.327.7426.1267","article-title":"Predictive accuracy of the Framingham coronary risk score in British men: Prospective cohort study","volume":"327","author":"Brindle","year":"2003","journal-title":"BMJ"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1752","DOI":"10.1136\/hrt.2006.087932","article-title":"Accuracy and impact of risk assessment in the primary prevention of cardiovascular disease: A systematic review","volume":"92","author":"Brindle","year":"2006","journal-title":"Heart"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1161\/STROKEAHA.113.004166","article-title":"Retinal Microvascular Abnormalities Predict Progression of Brain Microvascular Disease\u2014An Atherosclerosis Risk in Communities Magnetic Resonance Imaging Study","volume":"45","author":"Hanff","year":"2014","journal-title":"Stroke"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1001\/jama.288.1.67","article-title":"Cerebral white matter lesions, retinopathy, and incident clinical stroke","volume":"288","author":"Wong","year":"2002","journal-title":"Jama"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.cmpb.2013.02.004","article-title":"Retinal Artery-Vein Caliber Grading Using Color Fundus Imaging","volume":"111","author":"Bhuiyan","year":"2013","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"3194","DOI":"10.1109\/TBME.2013.2271035","article-title":"An Automated Method for Retinal Arteriovenous Nicking Quantification from Colour Fundus Images","volume":"60","author":"Nguyen","year":"2013","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"398","DOI":"10.1161\/01.STR.0000254547.91276.50","article-title":"Is diabetic retinopathy an independent risk factor for ischemic stroke?","volume":"38","author":"Cheung","year":"2007","journal-title":"Stroke"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1161\/01.CIR.103.1.163","article-title":"Primary prevention of ischemic stroke: A statement for healthcare professionals from the stroke council of the American Heart Association","volume":"103","author":"Goldstein","year":"2001","journal-title":"Circulation"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1026","DOI":"10.1093\/aje\/kwx246","article-title":"Comparison of sociodemographic and health-related characteristics of UK Biobank participants with those of the general population","volume":"186","author":"Fry","year":"2017","journal-title":"Am. J. Epidemiol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Dietterich, T.G. (2000). Ensemble Methods in Machine Learning. International Workshop on Multiple Classifier Systems, Springer.","DOI":"10.1007\/3-540-45014-9_1"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1167\/tvst.9.2.25","article-title":"Artificial Intelligence to Stratify Severity of Age-Related Macular Degeneration (AMD) and Predict Risk of Progression to Late AMD","volume":"9","author":"Bhuiyan","year":"2020","journal-title":"Transl. Vis. Sci. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e1249","DOI":"10.1002\/widm.1249","article-title":"Ensemble learning: A survey","volume":"8","author":"Sagi","year":"2018","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"ref_22","first-page":"41","article-title":"A Comparison of Event Models for Naive Bayes Text Classification","volume":"Volume 752","author":"McCallum","year":"1998","journal-title":"AAAI-98 Workshop on Learning for Text Categorization"},{"key":"ref_23","unstructured":"Rennie, J.D., Shih, L., Teevan, J., and Karger, D.R. (2003, January 21\u201324). Tackling the Poor Assumptions of Naive Bayes Text Classifiers. Proceedings of the Twentieth International Conference on Machine Learning (ICML-2003), Washington, DC, USA."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/s10994-005-0466-3","article-title":"Logistic model trees","volume":"95","author":"Landwehr","year":"2005","journal-title":"Mach. Learn."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Hosmer, D.W., Lemeshow, S., and Sturdivant, R.X. (2013). Applied Logistic Regression, John Wiley & Sons.","DOI":"10.1002\/9781118548387"},{"key":"ref_26","unstructured":"Haykin, S. (1999). Neural Networks: A Comprehensive Foundation, Prentice Hall."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Domingos, P., and Hulten, G. (2000, January 20\u201323). Mining high-speed data streams. Proceedings of the Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Boston, MA, USA.","DOI":"10.1145\/347090.347107"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2864","DOI":"10.1001\/jama.285.22.2864","article-title":"Validation of clinical classification schemes for predicting stroke: Results from the National Registry of Atrial Fibrillation","volume":"285","author":"Gage","year":"2001","journal-title":"JAMA"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/6\/1917\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T16:56:33Z","timestamp":1760028993000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/25\/6\/1917"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,19]]},"references-count":28,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,3]]}},"alternative-id":["s25061917"],"URL":"https:\/\/doi.org\/10.3390\/s25061917","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,19]]}}}