{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T18:28:46Z","timestamp":1790792926847,"version":"4.1.0"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T00:00:00Z","timestamp":1742169600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:p>Over 64 million people worldwide are affected by heart failure (HF), a condition that significantly raises mortality and medical expenses. In this study, we explore the potential of retinal optical coherence tomography (OCT) features as non-invasive biomarkers for the classification of heart failure subtypes: left ventricular heart failure (LVHF), congestive heart failure (CHF), and unspecified heart failure (UHF). By analyzing retinal measurements from the left eye, right eye, and both eyes, we aim to investigate the relationship between ocular indicators and heart failure using machine learning (ML) techniques. We conducted nine classification experiments to compare normal individuals against LVHF, CHF, and UHF patients, using retinal OCT features from each eye separately and in combination. Our analysis revealed that retinal thickness metrics, particularly ISOS-RPE and macular thickness in various regions, were significantly reduced in heart failure patients. Logistic regression, CatBoost, and XGBoost models demonstrated robust performance, with notable accuracy and area under the curve (AUC) scores, especially in classifying CHF and UHF. Feature importance analysis highlighted key retinal parameters, such as inner segment-outer segment to retinal pigment epithelium (ISOS-RPE) and inner nuclear layer to the external limiting membrane (INL-ELM) thickness, as crucial indicators for heart failure detection. The integration of explainable artificial intelligence further enhanced model interpretability, shedding light on the biological mechanisms linking retinal changes to heart failure pathology. Our findings suggest that retinal OCT features, particularly when derived from both eyes, have significant potential as non-invasive tools for early detection and classification of heart failure. These insights may aid in developing wearable, portable diagnostic systems, providing scalable solutions for personalized healthcare, and improving clinical outcomes for heart failure patients.<\/jats:p>","DOI":"10.3389\/fmed.2025.1551557","type":"journal-article","created":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T03:18:18Z","timestamp":1742181498000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Prediction of heart failure risk factors from retinal optical imaging via explainable machine learning"],"prefix":"10.3389","volume":"12","author":[{"given":"Sona M.","family":"Al Younis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samit Kumar","family":"Ghosh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hina","family":"Raja","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feryal A.","family":"Alskafi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siamak","family":"Yousefi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahsan H.","family":"Khandoker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,3,17]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"2372","DOI":"10.1016\/j.jacc.2022.11.001","article-title":"Global burden of cardiovascular diseases and risks collaboration, 1990-2021","volume":"80","author":"Lindstrom","year":"2022","journal-title":"J Am Coll Cardiol"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"e06","DOI":"10.15420\/cfr.2023.24","article-title":"Evaluating biomarkers as tools for early detection and prognosis of heart failure: a comprehensive review","volume":"10","author":"Alzaabi","year":"2024","journal-title":"Card Fail Rev"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"e0295653","DOI":"10.1371\/journal.pone.0295653","article-title":"Investigating automated regression models for estimating left ventricular ejection fraction levels in heart failure patients using circadian ECG features","volume":"18","author":"Al Younis","year":"2023","journal-title":"PLoS One"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1261022","DOI":"10.3389\/fbioe.2023.1261022","article-title":"Non-invasive technologies for heart failure, systolic and diastolic dysfunction modeling: a scoping review","volume":"11","author":"Al Younis","year":"2023","journal-title":"Front Bioeng Biotechnol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"854","DOI":"10.1002\/ejhf.3112","article-title":"The role of multimorbidity in patients with heart failure across the left ventricular ejection fraction spectrum: data from the Swedish Heart failure registry","volume":"26","author":"Tomasoni","year":"2024","journal-title":"Eur J Heart Fail"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"113982","DOI":"10.1016\/j.dss.2023.113982","article-title":"Human-machine collaboration for feature selection and integration to improve congestive Heart failure risk prediction","volume":"172","author":"Ben-Assuli","year":"2023","journal-title":"Decis Support Syst"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"e0302639","DOI":"10.1371\/journal.pone.0302639","article-title":"Prediction of heart failure patients with distinct left ventricular ejection fraction levels using circadian ECG features and machine learning","volume":"19","author":"Al Younis","year":"2024","journal-title":"PLoS One"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"102164","DOI":"10.1016\/j.eclinm.2023.102164","article-title":"Prognosis, characteristics, and provision of care for patients with the unspecified heart failure electronic health record phenotype: a population-based linked cohort study of 95262 individuals","volume":"63","author":"Nakao","year":"2023","journal-title":"EClinicalMedicine"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"e0164095","DOI":"10.1371\/journal.pone.0164095","article-title":"Optical coherence tomography in the UK biobank study\u2013rapid automated analysis of retinal thickness for large population-based studies","volume":"11","author":"Keane","year":"2016","journal-title":"PLoS One"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1161\/CIRCRESAHA.115.305364","article-title":"The human microcirculation: regulation of flow and beyond","volume":"118","author":"Gutterman","year":"2016","journal-title":"Circ Res"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"945245","DOI":"10.3389\/fmed.2022.945245","article-title":"Diabetic retinopathy as a predictor of cardiovascular morbidity and mortality in subjects with type 2 diabetes","volume":"9","author":"Barrot","year":"2022","journal-title":"Front Med"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12933-018-0728-6","article-title":"Prevalence of cardiovascular disease in type 2 diabetes: a systematic literature review of scientific evidence from across the world in 2007\u20132017","volume":"17","author":"Einarson","year":"2018","journal-title":"Cardiovasc Diabetol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"10458","DOI":"10.1038\/s41598-024-58502-z","article-title":"Association of diabetic retinopathy on all-cause and cause-specific mortality in older adults with diabetes: National Health and nutrition examination survey, 2005\u20132008","volume":"14","author":"Liang","year":"2024","journal-title":"Sci Rep"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12872-020-01763-z","article-title":"Diabetic retinopathy predicts cardiovascular mortality in diabetes: a meta-analysis","volume":"20","author":"Xu","year":"2020","journal-title":"BMC Cardiovasc Disord"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1016\/j.ajo.2019.01.009","article-title":"Acute vascular ischemic events in patients with central retinal artery occlusion in the United States: a nationwide study 2003-2014","volume":"200","author":"Mir","year":"2019","journal-title":"Am J Ophthalmol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"2386","DOI":"10.1097\/HJH.0b013e3283310f7e","article-title":"Retinal vessel diameters and risk of hypertension: the multiethnic study of atherosclerosis","volume":"27","author":"Kawasaki","year":"2009","journal-title":"J Hypertens"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1161\/01.HYP.0000140772.40322.ec","article-title":"Retinal arteriolar narrowing is associated with 5-year incident severe hypertension: the Blue Mountains eye study","volume":"44","author":"Smith","year":"2004","journal-title":"Hypertension"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1007\/s00125-022-05745-y","article-title":"Retinal microvascular associations with cardiometabolic risk factors differ by diabetes status: results from the UK biobank","volume":"65","author":"Tapp","year":"2022","journal-title":"Diabetologia"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"101095","DOI":"10.1016\/j.preteyeres.2022.101095","article-title":"Retinal vessel diameters and function in cardiovascular risk and disease","volume":"91","author":"Hanssen","year":"2022","journal-title":"Prog Retin Eye Res"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1177\/2047487319880367","article-title":"Physical activity may drive healthy microvascular ageing via downregulation of p66Shc","volume":"27","author":"Streese","year":"2020","journal-title":"Eur J Prev Cardiol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"9432","DOI":"10.1038\/s41598-020-65794-4","article-title":"Age and sex affect deep learning prediction of cardiometabolic risk factors from retinal images","volume":"10","author":"Gerrits","year":"2020","journal-title":"Sci Rep"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"4310","DOI":"10.3390\/s22124310","article-title":"Cardiovascular disease diagnosis from DXA scan and retinal images using deep learning","volume":"22","author":"Al-Absi","year":"2022","journal-title":"Sensors"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.cvdhj.2023.12.004","article-title":"Development and validation of a deep-learning model to predict 10-year atherosclerotic cardiovascular disease risk from retinal images using the UK biobank and EyePACS 10K datasets","volume":"5","author":"Vaghefi","year":"2024","journal-title":"Cardiovasc Digit Health J"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11042-024-18810-y","article-title":"Res-Unet based blood vessel segmentation and cardio vascular disease prediction using chronological chef-based optimization algorithm based deep residual network from retinal fundus images","author":"Kadry","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou","year":"2023","journal-title":"Nature"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1892","DOI":"10.3390\/jcm13071892","article-title":"Retinal vascular changes in Heart failure with preserved ejection fraction using optical coherence tomography angiography","volume":"13","author":"Weerts","year":"2024","journal-title":"J Clin Med"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"140767","DOI":"10.1109\/ACCESS.2020.3007599","article-title":"OCT image recognition of cardiovascular vulnerable plaque based on CNN","volume":"8","author":"Wang","year":"2020","journal-title":"IEEE Access"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1207","DOI":"10.1002\/ejhf.1564","article-title":"The association of retinal vessel calibres with heart failure and long-term alterations in cardiac structure and function: the atherosclerosis risk in communities (ARIC) study","volume":"21","author":"Chandra","year":"2019","journal-title":"Eur J Heart Fail"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","article-title":"Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning","volume":"2","author":"Poplin","year":"2018","journal-title":"Nat Biomed Eng"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1016\/j.jchf.2022.07.004","article-title":"Retinal microvasculature: a potential window into heart failure prevention","volume":"10","author":"Chaikijurajai","year":"2022","journal-title":"Heart Fail"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"5467","DOI":"10.1038\/s41598-023-32751-w","article-title":"Microvascular and structural analysis of the retina and choroid in heart failure patients with reduced ejection fraction","volume":"13","author":"Khalilipur","year":"2023","journal-title":"Sci Rep"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1093\/eurheartj\/ehx565","article-title":"Retinal microvascular dysfunction in heart failure","volume":"39","author":"Naegele","year":"2018","journal-title":"Eur Heart J"},{"key":"ref33","volume-title":"UK biobank: protocol for a large-scale prospective epidemiological resource","author":"Collins","year":"2007"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"e1001779","DOI":"10.1371\/journal.pmed.1001779","article-title":"UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age","volume":"12","author":"Sudlow","year":"2015","journal-title":"PLoS Med"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.ophtha.2016.07.033","article-title":"Associations with retinal pigment epithelium thickness measures in a large cohort: results from the UK biobank","volume":"124","author":"Ko","year":"2017","journal-title":"Ophthalmology"},{"key":"ref36","volume-title":"Data mining with decision trees: theory and applications","author":"Maimon","year":"2014"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"9:1","DOI":"10.1147\/JRD.2017.2709578","article-title":"An effective algorithm for hyperparameter optimization of neural networks","volume":"61","author":"Diaz","year":"2017","journal-title":"IBM J Res Dev"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"5245","DOI":"10.1038\/s41598-020-62133-5","article-title":"Study of cardiovascular disease prediction model based on random forest in eastern China","volume":"10","author":"Yang","year":"2020","journal-title":"Sci Rep"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"889378","DOI":"10.3389\/fgene.2022.889378","article-title":"Clinical prediction of heart failure in hemodialysis patients: based on the extreme gradient boosting method","volume":"13","author":"Wang","year":"2022","journal-title":"Front Genet"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"119648","DOI":"10.1016\/j.eswa.2023.119648","article-title":"Risk assessment of cardiovascular disease based on SOLSSA-CatBoost model","volume":"219","author":"Wei","year":"2023","journal-title":"Expert Syst Appl"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.gltp.2022.04.008","article-title":"Logistic regression technique for prediction of cardiovascular disease","volume":"3","author":"Ambrish","year":"2022","journal-title":"Global Trans Proc"},{"key":"ref42","first-page":"2079","article-title":"On over-fitting in model selection and subsequent selection bias in performance evaluation","volume":"11","author":"Cawley","year":"2010","journal-title":"J Machine Learn Res"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1551557\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,17]],"date-time":"2025-03-17T03:18:22Z","timestamp":1742181502000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1551557\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,17]]},"references-count":42,"alternative-id":["10.3389\/fmed.2025.1551557"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1551557","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,17]]},"article-number":"1551557"}}