Banca de QUALIFICAÇÃO: WALTER SOARES BARBOSA ROCHA FILHO

Uma banca de QUALIFICAÇÃO de DOUTORADO foi cadastrada pelo programa.
STUDENT : WALTER SOARES BARBOSA ROCHA FILHO
DATE: 18/09/2025
TIME: 09:00
LOCAL: Laboratório de Inovação Tecnológica em Saúde (LAIS)
TITLE:

CardIA: AN ARTIFICIAL INTELLIGENCE-BASED ALGORITHM FOR AUTOMATED ANALYSIS OF ELECTROCARDIOGRAMS TO SUPPORT MEDICAL DIAGNOSIS

KEY WORDS:

Electrocardiogram (ECG); Artificial Intelligence; Biomedical Signal Processing; Computer-Aided Diagnosis; Public Health; Telemedicine; PNTD.

PAGES: 50
BIG AREA: Engenharias
AREA: Engenharia Biomédica
SUMMARY:

Cardiovascular diseases are the leading cause of mortality worldwide, accounting for approximately 17.9 million deaths annually, according to the World Health Organization (WHO). Myocardial ischemia and stroke are the most significant, accounting for 13% and 10% of total deaths worldwide, respectively. Since the 2000s, cardiovascular diseases have been on the rise, and because they are non-communicable diseases, they have generated worldwide alerts and a search for technological solutions and public policies that can reduce these deaths. In Brazil, the situation is equally alarming, aggravated by inequalities in access to health services, especially in regions far from large urban centers.

In this context, this doctoral research aims to develop CardIA, a Python algorithm based on artificial intelligence (AI) capable of analyzing electrocardiogram (ECG) signals and generating technical reports based on the automated extraction of electrocardiographic parameters. CardIA is not intended to replace medical professionals, but rather to act as a diagnostic support tool, contributing to greater agility and accuracy in the analysis of cardiology exams.

The algorithm's validation process involves comparing automatically extracted parameters with those present in previously prepared medical reports in unstructured natural language, which are interpreted using AI-enabled natural language processing (NLP) techniques. The database used in the research was obtained from the National Telediagnosis Platform (PNTD), a strategic initiative of the Ministry of Health aimed at expanding access to diagnostic exams for vulnerable populations and regions with a shortage of specialists. It has already processed more than 1.5 million ECG exams from over 1,300 municipalities across various regions of the country.

By promoting greater accuracy in the analysis of ECG signals, CardIA seeks to contribute not only to technological innovation in healthcare but also to promoting equity in access to quality cardiology services, especially in a country marked by profound socioeconomic inequalities. Thus, this research is positioned at the intersection of data science, medicine, and social justice, proposing technological solutions aimed at reducing morbidity and mortality from cardiovascular diseases and strengthening the Unified Health System.

COMMITTEE MEMBERS:
Presidente - 2488270 - RICARDO ALEXSANDRO DE MEDEIROS VALENTIM
Interno - 1153006 - LUIZ AFFONSO HENDERSON GUEDES DE OLIVEIRA
Externo à Instituição - ANTONIO HIGOR FREIRE DE MORAIS - IFRN
Externo à Instituição - FELIPE RICARDO DOS SANTOS FERNANDES
Externa à Instituição - INGRIDY MARINA PIERRE BARBALHO - UFRN