Key result
SCG-based classification of aortic stenosis using Linear SVM achieved an accuracy of 0.780 and macro F1 score of 0.755, while GCG achieved the highest mean macro F1 score across all VHDs (0.518).
Why the study?
Valvular heart disease remains a major clinical burden with limited simple signal-based screening methods available.
Can nonlinear heart rate variability indices from concurrent ECG, SCG, and GCG differentiate specific valvular heart disease lesions?
Can nonlinear heart rate variability indices from concurrent ECG, SCG, and GCG differentiate specific valvular heart disease lesions?
Nonlinear HRV indices from SCG and GCG provide interpretable benchmarks and may outperform ECG for lesion-oriented classification of valvular heart diseases.
Answers are grounded in this paper and cite their sources.
Multimodal nonlinear HRV may aid VHD differentiation; leaves open clinical utility pending larger prospective validation.
Valvular heart disease (VHD) remains a major clinical burden, while simple signal-based screening methods are limited. This study tested whether nonlinear heart rate variability (HRV) indices from concurrent electrocardiograms (ECG), seismocardiograms (SCG), and gyrocardiograms (GCG) can differentiate five VHD labels: aortic regurgitation (AR), aortic stenosis (AS), mitral regurgitation (MR), mitral stenosis (MS), and tricuspid regurgitation (TR). Because the public dataset contains only VHD patients, the task was lesion-oriented classification rather than healthy-control versus VHD screening. Nonlinear HRV features from interbeat intervals were classified with eight machine-learning models using grid search and 5-fold patient-level crossvalidation. Macro F1 score was prioritized over accuracy because several imbalanced tasks showed inflated accuracy. The best result was obtained for SCG-based AS classification with Linear SVM (accuracy: 0.780 ± 0.081, macro F1 score: 0.755 ± 0.109). Averaged across classifiers and VHDs, GCG achieved the highest mean macro F1 score (0.518), followed by SCG (0.503) and ECG (0.491). Nonlinear HRV indices therefore provide an interpretable benchmark for comparing ECG, SCG, and GCG in VHD-oriented classification.
No takes yet. Share an insight, caveat, or question.
Szymon Siecinski (2026) studied Valvular heart disease (VHD). Nonlinear heart rate variability (HRV) indices from concurrent ECG, SCG, and GCG vs. Comparison between ECG, SCG, and GCG was evaluated on Classification of five VHD labels measured by macro F1 score and accuracy. SCG-based classification of aortic stenosis using Linear SVM achieved an accuracy of 0.780 and macro F1 score of 0.755, while GCG achieved the highest mean macro F1 score across all VHDs (0.518).
Synapse has enriched 10 related papers. Consider them for comparative context: