Multimodal Machine Learning Framework for Cardiovascular Risk Stratification in Adult Obesity: A Cross-sectional Study
Cardiovascular diseases account for approximately 80% of all deaths caused by known medical conditions, making them the leading cause of mortality worldwide. The present study investigates the use of electrocardiogram (ECG) non-linear features and different topological medical features (heart rate, anthropometry, blood, glucose, and lipid profile, and heart rate variability) to discriminate between different Framingham Cardiovascular Risk Scale status groups in adult obesity using machine learning.
Authors
- Camila Ferreira Leite (ORCID: https://orcid.org/0000-0001-6375-8845)
- Pedro Ribeiro (ORCID: https://orcid.org/0000-0001-8236-2563)
- João Alexandre Lôbo Marques (ORCID: https://orcid.org/0000-0002-6472-8784)
- Octávio Barbosa Neto (ORCID: https://orcid.org/0000-0003-1909-1515)
- Martim Brandão (ORCID: https://orcid.org/0000-0002-2003-0675)
- Pedro Henrique Fernandes Rodrigues (ORCID: https://orcid.org/0000-0002-5381-6615)
Publication Details
- Journal
- Exploratory Research and Hypothesis in Medicine
- Published
- 2025-11-06
- DOI
- https://doi.org/10.14218/erhm.2025.00037
- Primary Topic
- Heart Rate Variability and Autonomic Control
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Fundação para a Ciência e a Tecnologia