Machine learning-derived algorithm in the identification of referable diabetic retinopathy: A multicenter study with cost-effectiveness analysis

• Grant number: 25/00335-0
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: April 01, 2025
• End date: March 31, 2026
• Field of knowledge: Health Sciences - Medicine - Medical Clinics
• Principal Investigator: Philippe Olivier Alexandre Navaux
• Grantee: Bianca Carvalho de Souza
• Host Institution: Instituto de Ciências Exatas (ICEx). Universidade Federal de Minas Gerais (UFMG). Ministério da Educação (Brasil). Belo Horizonte , SP, Brazil
• Company: Universidade Federal de Minas Gerais (UFMG). Instituto de Ciências Exatas (ICEx)
• Associated research grant: 20/09866-4 - Artificial Intelligence Innovation Center for Health (CIIA-Health), AP.PCPE

Abstract

The prevalence of diabetes mellitus (DM) worldwide and in Brazil has been steadily increasing over recent decades. Due to the growing incidence of cases, this number is expected to reach 643 million by the year 2030 and 783 million by 2045. DM contributes to 11.3% of deaths worldwide among adults aged 20 to 79, with significant disparity among countries. Representative Brazilian data on DM prevalence, covering the population of nine capital cities, date back to the 1980s, where a prevalence of 7.6% was estimated for Brazilians aged 30 to 69. More current estimates on DM prevalence in Brazil have been made through the Risk Factor Surveillance System for Chronic Diseases by Telephone Survey (VIGITEL), where 8.2% of respondents over 18 reported having DM. The IDF 2021 estimates for Brazil indicate 15.7 million people, or a prevalence of 10.5%, in the 20 to 79 age group, with a projected increase of 48% by 2045. The considerable burden of non-communicable chronic diseases was highlighted in the Global Burden of Disease Study in Brazil, where DM accounted for 5.1% of disability-adjusted life years lost. In addition to health impacts, the negative effect on productivity, income, and financial costs of this disease-along with its associated complications and disabilities-poses a risk to the country's socioeconomic development. This study aims to estimate, through a cross-sectional multicenter survey, the prevalence of two important DM complications: diabetic retinopathy and nephropathy. This will be conducted by assessing patients from public health services at various levels of care in 7 centers (Porto Alegre, São Paulo, Belo Horizonte, Rio de Janeiro, Goiânia, Belém do Pará, and Aracaju) across all geographical regions of the country.