Chaabani, MohamedGuerreiro, NathanRibeiro, LuizLuiz, Luiz E.Slim, MohamedTeixeira, João Paulo2026-05-182026-05-182025Chaabani, Mohamed; Guerreiro, Nathan; Ribeiro, Luiz; Luiz, Luiz E.; Slim, Mohamed; Teixeira, João P.aulo (2025). Binary classification of cardiac pathologies using deep learning: a PTB-XL dataset approach. In International Conference on Demographic Transition, Health and Technologies, ICDTHT 2025. Salinas. p. 83-92. ISBN 978-303194900-5DOI: 10.1007/978-3-031-94901-2_7978-303194900-5http://hdl.handle.net/10198/36715Cardiovascular diseases, such as myocardial infarction, are among the leading causes of death worldwide. Accuracy and time are crucial for diagnosing these conditions and for effective treatment, usually requiring time-consuming manual analysis of clinical-grade electrocardiogram (ECG). This paper presents a novel deep learning-based method for binary classification of cardiac patholo-gies using the PTB-XL dataset. The model integrates EfficientNetB3 for spatial feature extraction and a Linformer block to capture long-range dependencies be-tween leads. Preprocessing involves converting RGBA ECG images to RGB for-mat and normalizing them to meet the requirements of the inputs of the layers. Initial experiments have shown promising results, achieving an AUC (Area Un-der the Curve) of 86.06%. Further work includes tests to optimize the model's performance based on different key metrics, including accuracy and precision.engconference object10.1007/978-3-031-94901-2_7