Scholarlink

Abstract Purpose <p>This study presents a machine learning methodology to automatically classify heart failure severity in Chagas disease (CD) patients using non-invasive 24-hour ECG-Holter signals.</p> Methods <p>Following American Heart Association (AHA) guidelines, the cohort was stratified into three Left Ventricular Ejection Fraction (LVEF)-based severity groups: Normal (LVEF ≥ 0.50, n=197), Moderate (0.40 ≤ LVEF &lt; 0.50, n=106), and Severe (LVEF &lt; 0.40, n=77), totaling N=380 patients. From short 10-second ECG segments, we extracted eleven spectral features derived from the power spectral density (PSD). Class imbalance was addressed through oversampling applied to the training folds. All classifiers were evaluated over 50 random stratified train-test splits (80/20) across three pairwise tasks (Normal vs. Moderate, Normal vs. Severe, Moderate vs. Severe).</p> Results <p>Analysis revealed a consistent leftward shift in PSD, with increased low-frequency power in more severe cases, consistent with morphological ECG changes including P-wave attenuation, QRS alterations, and ST-segment shifts. Using this spectral biomarker, the best models achieved mean <i>AUC/PR-AUC</i> values of 0.79/0.76 for Normal vs. Severe and 0.83/0.85 for Moderate vs. Severe across 50 random states. The Normal vs. Moderate task showed moderate separability (<i>AUC</i> = 0.75, <i>PR-AUC</i> = 0.72).</p> Conclusion <p>These findings highlight the potential of power spectral ECG analysis as a low-cost, fully automated tool for risk stratification in CD. The methodology shows promise for improving triage and clinical decision-making in resource-limited settings where CD remains highly prevalent.</p> Graphical abstract <p></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Machine learning-based stratification of chagas heart failure severity using ECG power spectral biomarkers

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月15日

查看全文
  • Pedro Ribeiro,
  • João Alexandre Lobo Marques,
  • Maria Inês Barbosa,
  • Roberto C. Pedrosa,
  • João Paulo do Vale Madeiro,
  • Pedro Miguel Rodrigues

摘要

Abstract Purpose

This study presents a machine learning methodology to automatically classify heart failure severity in Chagas disease (CD) patients using non-invasive 24-hour ECG-Holter signals.

Methods

Following American Heart Association (AHA) guidelines, the cohort was stratified into three Left Ventricular Ejection Fraction (LVEF)-based severity groups: Normal (LVEF ≥ 0.50, n=197), Moderate (0.40 ≤ LVEF < 0.50, n=106), and Severe (LVEF < 0.40, n=77), totaling N=380 patients. From short 10-second ECG segments, we extracted eleven spectral features derived from the power spectral density (PSD). Class imbalance was addressed through oversampling applied to the training folds. All classifiers were evaluated over 50 random stratified train-test splits (80/20) across three pairwise tasks (Normal vs. Moderate, Normal vs. Severe, Moderate vs. Severe).

Results

Analysis revealed a consistent leftward shift in PSD, with increased low-frequency power in more severe cases, consistent with morphological ECG changes including P-wave attenuation, QRS alterations, and ST-segment shifts. Using this spectral biomarker, the best models achieved mean AUC/PR-AUC values of 0.79/0.76 for Normal vs. Severe and 0.83/0.85 for Moderate vs. Severe across 50 random states. The Normal vs. Moderate task showed moderate separability (AUC = 0.75, PR-AUC = 0.72).

Conclusion

These findings highlight the potential of power spectral ECG analysis as a low-cost, fully automated tool for risk stratification in CD. The methodology shows promise for improving triage and clinical decision-making in resource-limited settings where CD remains highly prevalent.

Graphical abstract