{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T04:20:46Z","timestamp":1793766046177,"version":"4.6.1"},"reference-count":35,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T00:00:00Z","timestamp":1713139200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100004325","name":"AstraZeneca","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004325","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dom-pubs.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Diabetes Obesity Metabolism"],"published-print":{"date-parts":[[2024,7]]},"abstract":"Abstract<\/jats:title>\n \n Aim<\/jats:title>\n Hypertension and diabetes mellitus (DM) are major causes of morbidity and mortality, with growing burdens in low\u2010income countries where they are underdiagnosed and undertreated. Advances in machine learning may provide opportunities to enhance diagnostics in settings with limited medical infrastructure.<\/jats:p>\n <\/jats:sec>\n \n Materials and Methods<\/jats:title>\n A non\u2010interventional study was conducted to develop and validate a machine learning algorithm to estimate cardiovascular clinical and laboratory parameters. At two sites in Kenya, digital retinal fundus photographs were collected alongside blood pressure (BP), laboratory measures and medical history. The performance of machine learning models, originally trained using data from the UK Biobank, were evaluated for their ability to estimate BP, glycated haemoglobin, estimated glomerular filtration rate and diagnoses from fundus images.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n In total, 301 participants were enrolled. Compared with the UK Biobank population used for algorithm development, participants from Kenya were younger and would probably report Black\/African ethnicity, with a higher body mass index and prevalence of DM and hypertension. The mean absolute error was comparable or slightly greater for systolic BP, diastolic BP, glycated haemoglobin and estimated glomerular filtration rate. The model trained to identify DM had an area under the receiver operating curve of 0.762 (0.818 in the UK Biobank) and the hypertension model had an area under the receiver operating curve of 0.765 (0.738 in the UK Biobank).<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n In a Kenyan population, machine learning models estimated cardiovascular parameters with comparable or slightly lower accuracy than in the population where they were trained, suggesting model recalibration may be appropriate. This study represents an incremental step toward leveraging machine learning to make early cardiovascular screening more accessible, particularly in resource\u2010limited settings.<\/jats:p>\n <\/jats:sec>","DOI":"10.1111\/dom.15587","type":"journal-article","created":{"date-parts":[[2024,4,15]],"date-time":"2024-04-15T06:04:00Z","timestamp":1713161040000},"page":"2722-2731","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Prediction of cardiovascular risk factors from retinal fundus photographs: Validation of a deep learning algorithm in a prospective non\u2010interventional study in Kenya"],"prefix":"10.1111","volume":"26","author":[{"given":"Tom","family":"White","sequence":"first","affiliation":[{"name":"Data Science and Advanced Analytics Data Science & Artificial Intelligence, R&D, AstraZeneca Cambridge UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3662-7494","authenticated-orcid":false,"given":"Viknesh","family":"Selvarajah","sequence":"additional","affiliation":[{"name":"Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM) BioPharmaceuticals R&D, AstraZeneca Cambridge UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7148-4144","authenticated-orcid":false,"given":"Fredrik","family":"Wolfhagen\u2010Sand","sequence":"additional","affiliation":[{"name":"Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM) BioPharmaceuticals R&D, AstraZeneca Cambridge UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nils","family":"Svang\u00e5rd","sequence":"additional","affiliation":[{"name":"Data Science and Advanced Analytics Data Science & Artificial Intelligence, R&D, AstraZeneca Gothenburg Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gayathri","family":"Mohankumar","sequence":"additional","affiliation":[{"name":"Centre for Artificial Intelligence Data Science & Artificial Intelligence, R&D, AstraZeneca Gaithersburg Maryland USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Fenici","sequence":"additional","affiliation":[{"name":"School of Medicine and Surgery Catholic University Rome Italy"},{"name":"Biomagnetism and Clinical Physiology International Center (BACPIC) Rome Italy"},{"name":"AstraZeneca, Medical Affairs, BioPharmaceuticals, AstraZeneca Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kathryn","family":"Rough","sequence":"additional","affiliation":[{"name":"IQVIA Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nelson","family":"Onyango","sequence":"additional","affiliation":[{"name":"IQVIA Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kendall","family":"Lyons","sequence":"additional","affiliation":[{"name":"IQVIA Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christina","family":"Mack","sequence":"additional","affiliation":[{"name":"IQVIA Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Videlis","family":"Nduba","sequence":"additional","affiliation":[{"name":"Kenya Medical Research Institute Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mansoor","family":"Noorali Saleh","sequence":"additional","affiliation":[{"name":"Clinical Research Unit Aga Khan University Hospital Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Innocent","family":"Abayo","sequence":"additional","affiliation":[{"name":"Clinical Research Unit Aga Khan University Hospital Nairobi Kenya"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Afrah","family":"Siddiqui","sequence":"additional","affiliation":[{"name":"BioPharmaceuticals Medical AstraZeneca Cambridge UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Malgorzata","family":"Majdanska\u2010Strzalka","sequence":"additional","affiliation":[{"name":"CVRM Clinical Operations, Biopharmaceuticals R&D, AstraZeneca Warsaw Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katarzyna","family":"Kaszubska","sequence":"additional","affiliation":[{"name":"CVRM Clinical Operations, Biopharmaceuticals R&D, AstraZeneca Warsaw Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tove","family":"Hegelund\u2010Myrback","sequence":"additional","affiliation":[{"name":"Global Portfolio & Project Management Early CVRM&NS, R&D, AstraZeneca Gothenburg Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Russell","family":"Esterline","sequence":"additional","affiliation":[{"name":"Research and Late Development, Cardiovascular, Renal and Metabolism (CVRM) BioPharmaceuticals R&D, AstraZeneca Gaithersburg USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antonio","family":"Manzur","sequence":"additional","affiliation":[{"name":"Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM) BioPharmaceuticals R&D, AstraZeneca Cambridge UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2706-2669","authenticated-orcid":false,"given":"Victoria E. R.","family":"Parker","sequence":"additional","affiliation":[{"name":"Research and Early Development, Cardiovascular, Renal and Metabolism (CVRM) BioPharmaceuticals R&D, AstraZeneca Cambridge UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,4,15]]},"reference":[{"key":"e_1_2_11_2_1","unstructured":"World Health Organization.The top 10 causes of death.2020Accessed February 21 2022.https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/the-top-10-causes-of-death"},{"key":"e_1_2_11_3_1","unstructured":"World Health Organization.Global Health Estimates.2019Accessed February 21 2022.https:\/\/www.who.int\/data\/gho\/data\/themes\/mortality-and-global-health-estimates\/ghe-leading-causes-of-death"},{"key":"e_1_2_11_4_1","unstructured":"World Health Organization.More than 700 million people with untreated hypertension.2021."},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.3949\/ccjm.82.s2.06"},{"key":"e_1_2_11_6_1","unstructured":"World Health Organization.Global report on diabetes. WHO library cataloguing\u2010in\u2010publication data global report on diabetes.2016."},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra1111610"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12913\u2010022\u201007655\u20106"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589\u20107500(20)30060\u20101"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589\u20107500(19)30004\u20104"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376718"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471\u20102415\u201014\u201060"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010020\u201065794\u20104"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551\u2010018\u20100195\u20100"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589\u20107500(20)30216\u20108"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0233166"},{"issue":"9","key":"e_1_2_11_18_1","first-page":"1456","article-title":"Estimation of Haemoglobin A1c from retinal photographs via deep learning","volume":"60","author":"Tham YC","year":"2019","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3052477"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551\u2010021\u201000745\u20106"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0230111"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1097\/MAJ.0000000000000308"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1161\/01.STR.29.10.2061"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.110.005645"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.3390\/DIAGNOSTICS13010068"},{"key":"e_1_2_11_26_1","unstructured":"UK Biobank.2023. Accessed February 21 2023.https:\/\/www.ukbiobank.ac.uk\/learn-more-about-uk-biobank\/about-us."},{"key":"e_1_2_11_27_1","unstructured":"National Kidney Foundation.eGFR calculator. Accessed March 1 2022.https:\/\/www.kidney.org\/professionals\/kdoqi\/gfr_calculator"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0139148"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589\u20107500(22)00017\u20106"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1714229"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0132321"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/S2589\u20107500(19)30009\u20103"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1097\/JTO.0b013e3181ec173d"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/hr.2010.241"}],"container-title":["Diabetes, Obesity and Metabolism"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dom-pubs.pericles-prod.literatumonline.com\/doi\/pdf\/10.1111\/dom.15587","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T00:10:45Z","timestamp":1761869445000},"score":1,"resource":{"primary":{"URL":"https:\/\/dom-pubs.pericles-prod.literatumonline.com\/doi\/10.1111\/dom.15587"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,15]]},"references-count":35,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["10.1111\/dom.15587"],"URL":"https:\/\/doi.org\/10.1111\/dom.15587","archive":["Portico"],"relation":{"has-review":[{"id-type":"doi","id":"10.1111\/DOM.15587\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1111\/DOM.15587\/v2\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1111\/DOM.15587\/v1\/review3","asserted-by":"object"},{"id-type":"doi","id":"10.1111\/DOM.15587\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1111\/DOM.15587\/v2\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1111\/DOM.15587\/v1\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1111\/DOM.15587\/v1\/review1","asserted-by":"object"}]},"ISSN":["1462-8902","1463-1326"],"issn-type":[{"value":"1462-8902","type":"print"},{"value":"1463-1326","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,15]]},"assertion":[{"value":"2023-12-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}