Key result
Single-feature HRV model outperforms multi-feature classifiers for CHF detection with an AUC of ~0.88.
Why the study?
The cross-database transferability of interpretable single-feature threshold models for detecting CHF from short-term HRV, and their performance relative to optimized multi-feature classifiers, required evaluation.
Does an interpretable single-feature threshold model improve congestive heart failure detection from short-term heart rate variability compared to optimized multi-feature classifiers across five databases?
Observational
Does an interpretable single-feature threshold model improve congestive heart failure detection from short-term heart rate variability compared to optimized multi-feature classifiers across five databases?
An interpretable single-feature threshold model using the short-term detrended fluctuation analysis scaling exponent (f14) demonstrated strong discrimination between congestive heart failure and normal sinus rhythm across five databases, outperforming complex multi-feature classifiers.
Single-feature DFA threshold model may aid short-term HRV-based CHF detection; leaves open prospective validation before clinical adoption.
Objective To evaluate the transferability of interpretable single-feature threshold models across the five evaluated databases for congestive heart failure (CHF) detection from short-term heart rate variability (HRV), and to compare their performance with optimized multi-feature classifiers. Approach Twenty HRV features from 60-second inter-beat interval windows in five databases were evaluated using leave-one-database-pair-out nested cross-validation with six outer-test sets and their corresponding outer-development sets. Within each outer-development set, directions and thresholds were fitted on inner-train sets, and features were selected according to mean inner-validation F1 score. The selected model was refitted on the complete outer-development set. The most frequently selected feature was further evaluated across the six outer-test sets with separately fitted directions and thresholds. Eight multi-feature classifiers were optimized and evaluated using the same data splits. Performance was assessed using record-balanced window-level metrics and database-stratified recording-level bootstrap confidence intervals. Main results The short-term detrended fluctuation analysis scaling exponent (f14) was selected most frequently. The f14 threshold model achieved the highest mean test AUC (0.881 ± 0.038), F1 score (0.718 ± 0.079), and sensitivity among the evaluated single-feature and multi-feature models. Among the eight multi-feature classifiers, Random Forest achieved the highest mean test AUC (0.858 ± 0.067). Significance An interpretable single-feature threshold model showed strong CHF–Normal Sinus Rhythm (NSR) discrimination in the five evaluated databases. f14 was the strongest candidate in this evaluation, although its thresholds varied across outer-development sets and its clinical specificity requires further validation.
No takes yet. Share an insight, caveat, or question.
Song et al. (2026) conducted an observational in Congestive Heart Failure (CHF). Single-feature threshold model using short-term detrended fluctuation analysis scaling exponent (f14) vs. Eight optimized multi-feature classifiers (including Random Forest) was evaluated on Congestive heart failure vs. Normal Sinus Rhythm discrimination (mean test AUC and F1 score) (Mean test AUC 0.881 ± 0.038, F1 score 0.718 ± 0.079). The single-feature f14 threshold model achieved a higher mean test AUC (0.881 vs 0.858 for Random Forest) and F1 score (0.718) than multi-feature classifiers for CHF detection from short-term HRV.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: