{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T13:54:06Z","timestamp":1784555646498,"version":"3.55.0"},"reference-count":46,"publisher":"Public Library of Science (PLoS)","issue":"2","license":[{"start":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T00:00:00Z","timestamp":1677196800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"AIDS Trust Fund","award":["MSS 318R"],"award-info":[{"award-number":["MSS 318R"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>People living with HIV (PLWH) have increased risks of non-communicable diseases, especially cardiovascular diseases. Current HIV clinical management guidelines recommend regular cardiovascular risk screening, but the risk equation models are not specific for PLWH. Better tools are needed to assess cardiovascular risk among PLWH accurately.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods<\/jats:title>\n<jats:p>We performed a prospective study to determine the performance of automatic retinal image analysis in assessing coronary artery disease (CAD) in PLWH. We enrolled PLWH with \u22651 cardiovascular risk factor. All participants had computerized tomography (CT) coronary angiogram and digital fundus photographs. The primary outcome was coronary atherosclerosis; secondary outcomes included obstructive CAD. In addition, we compared the performances of three models (traditional cardiovascular risk factors alone; retinal characteristics alone; and both traditional and retinal characteristics) by comparing the area under the curve (AUC) of receiver operating characteristic curves.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>Among the 115 participants included in the analyses, with a mean age of 54 years, 89% were male, 95% had undetectable HIV RNA, 45% had hypertension, 40% had diabetes, 45% had dyslipidemia, and 55% had obesity, 71 (61.7%) had coronary atherosclerosis, and 23 (20.0%) had obstructive CAD. The machine-learning models, including retinal characteristics with and without traditional cardiovascular risk factors, had AUC of 0.987 and 0.979, respectively and had significantly better performance than the model including traditional cardiovascular risk factors alone (AUC 0.746) in assessing coronary artery disease atherosclerosis. The sensitivity and specificity for risk of coronary atherosclerosis in the combined model were 93.0% and 93.2%, respectively. For the assessment of obstructive CAD, models using retinal characteristics alone (AUC 0.986) or in combination with traditional risk factors (AUC 0.991) performed significantly better than traditional risk factors alone (AUC 0.777). The sensitivity and specificity for risk of obstructive CAD in the combined model were 95.7% and 97.8%, respectively.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>In this cohort of Asian PLWH at risk of cardiovascular diseases, retinal characteristics, either alone or combined with traditional risk factors, had superior performance in assessing coronary atherosclerosis and obstructive CAD.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec005\">\n<jats:title>Summary<\/jats:title>\n<jats:p>People living with HIV in an Asian cohort with risk factors for cardiovascular disease had a high prevalence of coronary artery disease (CAD). A machine-learning-based retinal image analysis could increase the accuracy in assessing the risk of coronary atherosclerosis and obstructive CAD.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0281701","type":"journal-article","created":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T18:32:11Z","timestamp":1677263531000},"page":"e0281701","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":12,"title":["An efficient approach to estimate the risk of coronary artery disease for people living with HIV using machine-learning-based retinal image analysis"],"prefix":"10.1371","volume":"18","author":[{"given":"Grace","family":"Lui","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ho Sang","family":"Leung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jack","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun Kwok","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinxin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mary","family":"Ho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vivian","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2120-7612","authenticated-orcid":true,"given":"Timothy","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tracy","family":"Ho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yin Yan","family":"Chan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1448-765X","authenticated-orcid":true,"given":"Shui Shan","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex PW","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ka Tak","family":"Wong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7238-845X","authenticated-orcid":true,"given":"Benny","family":"Zee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,2,24]]},"reference":[{"key":"pone.0281701.ref001","article-title":"Global Burden of Atherosclerotic Cardiovascular Disease in People Living with the Human Immunodeficiency Virus: A Systematic Review and Meta-Analysis","author":"ASV Shah","year":"2018","journal-title":"Circulation"},{"key":"pone.0281701.ref002","article-title":"Incidence of cardiometabolic diseases in people living with and without HIV in the UK: a population-based matched cohort study","author":"TE Gooden","year":"2021","journal-title":"J Infect Dis"},{"issue":"14","key":"pone.0281701.ref003","doi-asserted-by":"crossref","first-page":"e012241","DOI":"10.1161\/JAHA.119.012241","article-title":"HIV Infection and Incidence of Cardiovascular Diseases: An Analysis of a Large Healthcare Database","volume":"8","author":"A Alonso","year":"2019","journal-title":"Journal of the American Heart Association"},{"key":"pone.0281701.ref004","article-title":"Managing cardiovascular risk in people living with HIV in Asia\u2014where are we now?","author":"JY Choi","year":"2021","journal-title":"HIV Med."},{"key":"pone.0281701.ref005","article-title":"update of the European AIDS Clinical Society Guidelines for treatment of people living with HIV version 10.0.","author":"L Ryom","year":"2019","journal-title":"HIV Medicine.n\/a(n\/a)"},{"issue":"2","key":"pone.0281701.ref006","doi-asserted-by":"crossref","first-page":"e98","DOI":"10.1161\/CIR.0000000000000695","article-title":"Characteristics, Prevention, and Management of Cardiovascular Disease in People Living With HIV: A Scientific Statement From the American Heart Association","volume":"140","author":"MJ Feinstein","year":"2019","journal-title":"Circulation"},{"issue":"Suppl 3","key":"pone.0281701.ref007","doi-asserted-by":"crossref","first-page":"S362","DOI":"10.1093\/infdis\/jis196","article-title":"Sr. Cardiovascular risk estimation in 2012: lessons learned and applicability to the HIV population","volume":"2053","author":"RB D\u2019Agostino","year":"2012","journal-title":"J Infect Dis"},{"issue":"5","key":"pone.0281701.ref008","doi-asserted-by":"crossref","first-page":"439","DOI":"10.1097\/ICU.0000000000000784","article-title":"Systemic retinal biomarkers","volume":"32","author":"TM Ranchod","year":"2021","journal-title":"Current opinion in ophthalmology"},{"issue":"3","key":"pone.0281701.ref009","doi-asserted-by":"crossref","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":"R Poplin","year":"2018","journal-title":"Nature biomedical engineering"},{"key":"pone.0281701.ref010","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/j.atherosclerosis.2017.10.008","article-title":"A spectrum of retinal vasculature measures and coronary artery disease","volume":"268","author":"SB Wang","year":"2018","journal-title":"Atherosclerosis"},{"key":"pone.0281701.ref011","doi-asserted-by":"crossref","first-page":"19053","DOI":"10.1038\/srep19053","article-title":"Retinal Information is Independently Associated with Cardiovascular Disease in Patients with Type 2 diabetes","volume":"6","author":"VY Guo","year":"2016","journal-title":"Sci Rep"},{"issue":"5","key":"pone.0281701.ref012","doi-asserted-by":"crossref","first-page":"e0233166","DOI":"10.1371\/journal.pone.0233166","article-title":"Prediction of hypertension, hyperglycemia and dyslipidemia from retinal fundus photographs via deep learning: A cross-sectional study of chronic diseases in central China.","volume":"15","author":"L Zhang","year":"2020","journal-title":"PLoS One."},{"issue":"1","key":"pone.0281701.ref013","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.ophtha.2018.07.022","article-title":"Retinal Vasculometry Associations with Cardiometabolic Risk Factors in the European Prospective Investigation of Cancer-Norfolk Study","volume":"126","author":"CG Owen","year":"2019","journal-title":"Ophthalmology"},{"issue":"18","key":"pone.0281701.ref014","doi-asserted-by":"crossref","first-page":"1328","DOI":"10.1161\/CIRCULATIONAHA.116.023425","article-title":"Retinal Vessel Calibers in Predicting Long-Term Cardiovascular Outcomes: The Atherosclerosis Risk in Communities Study","volume":"134","author":"SB Seidelmann","year":"2016","journal-title":"Circulation"},{"key":"pone.0281701.ref015","article-title":"Deep Learning of the Retina Enables Phenome- and Genome-wide Analyses of the Microvasculature","author":"SM Zekavat","year":"2021","journal-title":"Circulation"},{"issue":"1","key":"pone.0281701.ref016","doi-asserted-by":"crossref","first-page":"e25","DOI":"10.4081\/idr.2012.3853","article-title":"Human immunodeficiency virus and its effects on the visual system.","volume":"4","author":"MW Stewart","year":"2012","journal-title":"Infect Dis Rep"},{"issue":"8","key":"pone.0281701.ref017","doi-asserted-by":"crossref","first-page":"1179","DOI":"10.1097\/00002030-200305230-00010","article-title":"Cardiovascular disease risk factors in HIV patients\u2014association with anti-retroviral therapy. Results from the DAD study","volume":"17","author":"N Friis-Moller","year":"2003","journal-title":"AIDS"},{"issue":"9403","key":"pone.0281701.ref018","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/S0140-6736(03)15268-3","article-title":"Appropriate body-mass index for Asian populations and its implications for policy and intervention strategies.","volume":"363","author":"Consultation WHOE","year":"2004","journal-title":"Lancet"},{"issue":"18","key":"pone.0281701.ref019","doi-asserted-by":"crossref","first-page":"1837","DOI":"10.1161\/01.CIR.97.18.1837","article-title":"Prediction of coronary heart disease using risk factor categories","volume":"97","author":"D Wilson PW","year":"1998","journal-title":"Circulation"},{"key":"pone.0281701.ref020","doi-asserted-by":"crossref","first-page":"j2099","DOI":"10.1136\/bmj.j2099","article-title":"Development and validation of QRISK3 risk prediction algorithms to estimate future risk of cardiovascular disease: prospective cohort study","volume":"357","author":"J Hippisley-Cox","year":"2017","journal-title":"BMJ"},{"issue":"25 Pt B","key":"pone.0281701.ref021","first-page":"2935","article-title":"American College of Cardiology\/American Heart Association Task Force on Practice G. 2013 ACC\/AHA guideline on the assessment of cardiovascular risk: a report of the American College of Cardiology\/American Heart Association Task Force on Practice Guidelines","volume":"63","author":"DC jr Goff","year":"2014","journal-title":"J Am Coll Cardiol"},{"issue":"2","key":"pone.0281701.ref022","doi-asserted-by":"crossref","first-page":"214","DOI":"10.1177\/2047487315579291","article-title":"An updated prediction model of the global risk of cardiovascular disease in HIV-positive persons: The Data-collection on Adverse Effects of Anti-HIV Drugs (D:A:D) study.","volume":"23","author":"N Friis-Moller","year":"2016","journal-title":"Eur J Prev Cardiol."},{"issue":"4","key":"pone.0281701.ref023","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1016\/0735-1097(90)90282-T","article-title":"Quantification of coronary artery calcium using ultrafast computed tomography","volume":"15","author":"AS Agatston","year":"1990","journal-title":"J Am Coll Cardiol"},{"issue":"5","key":"pone.0281701.ref024","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1016\/j.jcct.2014.07.003","article-title":"SCCT guidelines for the interpretation and reporting of coronary CT angiography: a report of the Society of Cardiovascular Computed Tomography Guidelines Committee.","volume":"8","author":"J Leipsic","year":"2014","journal-title":"J Cardiovasc Comput Tomogr"},{"issue":"4","key":"pone.0281701.ref025","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1016\/j.jstrokecerebrovasdis.2017.01.020","article-title":"Prediction Factors of Recurrent Stroke among Chinese Adults Using Retinal Vasculature Characteristics","volume":"26","author":"Y Zhuo","year":"2017","journal-title":"J Stroke Cerebrovasc Dis"},{"key":"pone.0281701.ref026","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"ER DeLong","year":"1988","journal-title":"Biometrics"},{"key":"pone.0281701.ref027","unstructured":"He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. \"Deep residual learning for image recognition.\" In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778. 2016. https:\/\/arxiv.org\/pdf\/1512.03385v1.pdf"},{"key":"pone.0281701.ref028","article-title":"\u201cMethod and device for retinal image analysis\u201d, Patent No","author":"B Zee","year":"2014","journal-title":"US8787638 B2, granted on"},{"key":"pone.0281701.ref029","first-page":"1889","article-title":"\u201cWorking set selection using second order information for training support vector machines.\u201d","volume":"6","author":"R.-E. Fan","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"pone.0281701.ref030","volume-title":"The Elements of Statistical Learning, Second Edition.","author":"Springer","year":"2008"},{"key":"pone.0281701.ref031","volume-title":"Learning with Kernels: Support Vector Machines, Regularization, Optimization and Beyond, Adaptive Computation and Machine Learning.","author":"B. Scholkopf","year":"2002"},{"issue":"3","key":"pone.0281701.ref032","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1111\/hiv.12687","article-title":"Cardiovascular disease-related mortality and factors associated with cardiovascular events in the TREAT Asia HIV Observational Database (TAHOD).","volume":"20","author":"R Bijker","year":"2019","journal-title":"HIV Med"},{"issue":"21","key":"pone.0281701.ref033","doi-asserted-by":"crossref","first-page":"2203","DOI":"10.1161\/CIRCULATIONAHA.117.028975","article-title":"Cardiovascular Risk Prediction Functions Underestimate Risk in HIV Infection","volume":"137","author":"VA Triant","year":"2018","journal-title":"Circulation"},{"issue":"4","key":"pone.0281701.ref034","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1111\/hiv.12300","article-title":"Cardiovascular risk prediction in HIV-infected patients: comparing the Framingham, atherosclerotic cardiovascular disease risk score (ASCVD), Systematic Coronary Risk Evaluation for the Netherlands (SCORE-NL) and Data Collection on Adverse Events of Anti-HIV Drugs (D:A:D) risk prediction models.","volume":"17","author":"M Krikke","year":"2016","journal-title":"HIV Med."},{"issue":"8","key":"pone.0281701.ref035","first-page":"510","article-title":"Cardiovascular risk assessment in persons with HIV infection in the developing world: comparing three risk equations in a cohort of HIV-infected Thais.","volume":"12","author":"N Edwards-Jackson","year":"2011"},{"issue":"4","key":"pone.0281701.ref036","doi-asserted-by":"crossref","first-page":"549","DOI":"10.1016\/j.jmii.2019.03.006","article-title":"Estimated risk of cardiovascular disease among the HIV-positive patients aged 40 years or older in Taiwan.","volume":"52","author":"PY Wu","year":"2019","journal-title":"J Microbiol Immunol Infect"},{"issue":"2","key":"pone.0281701.ref037","doi-asserted-by":"crossref","first-page":"e010893","DOI":"10.1136\/heartasia-2017-010893","article-title":"Cardiovascular risk in an HIV-infected population in India.","volume":"9","author":"IP Marbaniang","year":"2017","journal-title":"Heart Asia"},{"issue":"3","key":"pone.0281701.ref038","doi-asserted-by":"crossref","first-page":"e368","DOI":"10.1111\/aos.14598","article-title":"Retinal microvascular complexity comparing mono- and multifractal dimensions in relation to cardiometabolic risk factors in a Middle Eastern population.","volume":"99","author":"T Van Craenendonck","year":"2021","journal-title":"Acta ophthalmologica."},{"issue":"1","key":"pone.0281701.ref039","doi-asserted-by":"crossref","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":"N Gerrits","year":"2020","journal-title":"Sci Rep."},{"issue":"5","key":"pone.0281701.ref040","doi-asserted-by":"crossref","first-page":"e306","DOI":"10.1016\/S2589-7500(21)00043-1","article-title":"Deep-learning-based cardiovascular risk stratification using coronary artery calcium scores predicted from retinal photographs","volume":"3","author":"TH Rim","year":"2021","journal-title":"The Lancet Digital health"},{"issue":"4","key":"pone.0281701.ref041","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1093\/eurheartj\/ehq431","article-title":"Fractal analysis of retinal microvasculature and coronary heart disease mortality","volume":"32","author":"G Liew","year":"2011","journal-title":"Eur Heart J"},{"issue":"1","key":"pone.0281701.ref042","doi-asserted-by":"crossref","first-page":"16718","DOI":"10.1038\/s41598-020-73861-z","article-title":"Vascular density with optical coherence tomography angiography and systemic biomarkers in low and high cardiovascular risk patients.","volume":"10","author":"MA Hannappe","year":"2020","journal-title":"Sci Rep"},{"key":"pone.0281701.ref043","article-title":"Retinal microvasculature impairments in patients with coronary artery disease: An optical coherence tomography angiography study.","author":"P Zhong","year":"2021","journal-title":"Acta ophthalmologica"},{"key":"pone.0281701.ref044","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/j.ajo.2020.03.027","article-title":"Association of Cardiovascular Mortality and Deep Learning-Funduscopic Atherosclerosis Score derived from Retinal Fundus Images","volume":"217","author":"J Chang","year":"2020","journal-title":"American journal of ophthalmology"},{"issue":"5","key":"pone.0281701.ref045","doi-asserted-by":"crossref","first-page":"3650","DOI":"10.1167\/iovs.12-11126","article-title":"Racial differences in retinal vessel geometric characteristics: a multi-ethnic study in healthy Asians","volume":"54","author":"X Li","year":"2013","journal-title":"Invest Ophthalmol Vis Sci"},{"key":"pone.0281701.ref046","article-title":"Optical coherence tomography angiography changes in cardiovascular systemic diseases and risk factors: A Review.","author":"I Monteiro-Henriques","year":"2021","journal-title":"Acta ophthalmologica."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0281701","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T18:32:39Z","timestamp":1677263559000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0281701"}},"subtitle":[],"editor":[{"given":"Yoshihiro","family":"Fukumoto","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,2,24]]},"references-count":46,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,2,24]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0281701","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,24]]}}}