Validation of a deep-learning-based retinal biomarker (Reti-CVD) in the prediction of cardiovascular disease: data from UK Biobank

Journal article

ABSTRACT BACKGROUND: Cardiovascular disease (CVD) and stroke are among the leading causes of death worldwide. OBJECTIVE: This article presents a review of the application of artificial intelligence in identifying biomarkers for CVD and stroke. DESIGN AND SETTING: Narrative review conducted by a research group at the Universidade Federal de São Paulo, São Paulo, Brazil. METHODS: A literature search was conducted to identify the main applications of artificial intelligence in ophthalmology, using the keywords “artificial intelligence,” “prediction,” “biomarker,” “cardiovascular disease,” “retina,” and “stroke,” covering the period from January 1, 2018, to July 3, 2023. The Medical Literature Analysis and Retrieval System Online (MEDLINE, via PubMed) and the Latin American and Caribbean Literature in Health Sciences (Literatura Latino-Americana e do Caribe em Ciências da Saúde, LILACS, via the Virtual Health Library) were used to identify relevant articles. RESULTS: A total of 30 references were retrieved, of which 14 were considered eligible for intensive review and critical analysis. CONCLUSIONS: Artificial intelligence has proven effective in identifying non-invasive biomarkers through the analysis of patients’ retinal examinations. These findings contribute to a better understanding of the pathophysiology of CVD and stroke

Authors: Tseng, RMWW; Rim, TH; Shantsila, E; Yi, JK; Park, S

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: BioMed Central
• Journal: BMC Medicine
• Volume: 21
• Issue: 1
• Pages: 28-28
• Article number: 28
• Publication date: 2023-01-24
• DOI: 10.1186/s12916-022-02684-8
• EISSN: 1741-7015
• ISSN: 1741-7015
• Language: English
• Keywords: Medicine; Biomarker; Ophthalmology; Disease; Biobank; Bioinformatics; Retinal; Internal medicine