<abstract><p>About 6.5 million people are infected with Chagas disease (CD) globally, and WHO estimates that $ &gt; million people worldwide suffer from ChHD. Sudden cardiac death (SCD) represents one of the leading causes of death worldwide and affects approximately 65% of ChHD patients at a rate of 24 per 1000 patient-years, much greater than the SCD rate in the general population. Its occurrence in the specific context of ChHD needs to be better exploited. This paper provides the first evidence supporting the use of machine learning (ML) methods within non-invasive tests: patients' clinical data and cardiac restitution metrics (CRM) features extracted from ECG-Holter recordings as an adjunct in the SCD risk assessment in ChHD. The feature selection (FS) flows evaluated 5 different groups of attributes formed from patients' clinical and physiological data to identify relevant attributes among 57 features reported by 315 patients at HUCFF-UFRJ. The FS flow with FS techniques (variance, ANOVA, and recursive feature elimination) and Naive Bayes (NB) model achieved the best classification performance with 90.63% recall (sensitivity) and 80.55% AUC. The initial feature set is reduced to a subset of 13 features (4 Classification; 1 Treatment; 1 CRM; and 7 Heart Tests). The proposed method represents an intelligent diagnostic support system that predicts the high risk of SCD in ChHD patients and highlights the clinical and CRM data that most strongly impact the final outcome.</p></abstract>

A doença de Chagas (DC) afeta cerca de 7 milhões de pessoas no mundo e pode levar à Morte Súbita Cardíaca (MSC) do paciente por cardiomiopatia, cuja evolução pode ser controlada com diagnóstico precoce. Neste artigo, foram utilizados 7 algoritmos de aprendizagem de máquina com uma base de dados clínicos de pacientes chagásicos, objetivando a classificação em alta ou baixa predisposição do paciente à MSC, com seleção de atributos e balanceamento dos dados. Os melhores resultados indicam AUC:85.35 e F1:75.79 para o algoritmo K-Vizinhos Mais Próximos. Devido ao forte impacto nos modelos de aprendizagem de máquina, sugerimos o uso da Taquicardia Ventricular Não Sustentada e Extrassístole Ventricular Total como indicadores de MSC iminente.