Explainable artificial intelligence for predicting cardiovascular events in hospitalised COVID-19 patients
Despite moderate AUROC and high accuracy, both AI models demonstrated limited ability to detect cardiovascular events due to class imbalance. The persistently low F1 score for the minority class underscores this limitation. Traditional rebalancing techniques produced only small gains, mostly improving recall occurring at the expense of precision. Age, urea levels, platelet count, and SatO2/FiO2 were identified as the most relevant predictors of cardiovascular complications in this cohort.
Authors
- Isabella Viana Gomes Schettini (ORCID: https://orcid.org/0000-0002-3180-6619)
- Guilherme Fonseca (ORCID: https://orcid.org/0009-0000-7862-8701)
- Bruno Barbosa Miranda de Paiva (ORCID: https://orcid.org/0000-0001-8378-3650)
- Milena Soriano Marcolino (ORCID: https://orcid.org/0000-0003-4278-3771)
- Leonardo Rocha (ORCID: https://orcid.org/0000-0002-4913-4902)
- Marcos André Gonçalves
Institutions
- Universidade Federal de Minas Gerais (BR)
- Conselho Nacional de Desenvolvimento Científico e Tecnológico (BR)
- Federal University of São João del-Rei (BR)
Publication Details
- Journal
- BMC Infectious Diseases
- Published
- 2025-11-13
- DOI
- https://doi.org/10.1186/s12879-025-11465-6
- Primary Topic
- COVID-19 diagnosis using AI
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Fundação de Amparo à Pesquisa do Estado de São Paulo
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- Fundação de Amparo à Pesquisa do Estado de Minas Gerais