Early ECG Warning for Chagas Patients: Implementation of TinyML for Low-Resource Areas in Peru

Abstract

Cardiovascular diseases (CVDs) are the leading cause of death globally, claiming approximately 17.9 million lives annually. These disorders, including coronary heart diseases, cerebrovascular diseases, and rheumatic heart diseases, predominantly affect low- and middle-income countries, where over 75% of deaths occur. In the Americas, CVDs are responsible for an estimated 2 million deaths per year. In Peru, cardiovascular diseases are the second leading cause of death. This study aims to develop an early warning system based on electrocardiography (ECG) for detecting high-risk Chagas disease patients, with potential applications to other cardiovascular conditions. We employ advanced signal processing and machine learning techniques, specifically wavelet transform feature extraction and Tiny Machine Learning (TinyML), to efficiently and cost-effectively identify specific patterns in the ECG signals of Chagas patients. This system aims to improve timely clinical intervention and reduce mortality rates associated with Chagas disease in low-resource settings.

Tasks

Reproductions