Key result
Cardiorespiratory signal features detect stress with ~86% accuracy but fail to identify anxiety.
Why the study?
Anxiety disorders alter cardiorespiratory physiology measurable by wearable biosensing systems, prompting investigation into whether synchronized ECG and respiration signals combined with Hilbert- and wavelet-derived features can classify anxiety-inducing stimulus conditions.
Do Hilbert- and wavelet-derived cardiorespiratory features from wearable ECG and respiration signals improve machine learning classification of anxiety-inducing stimulus conditions compared to conventional HRV and RRV features?
Observational (n=18)
Do Hilbert- and wavelet-derived cardiorespiratory features from wearable ECG and respiration signals improve machine learning classification of anxiety-inducing stimulus conditions compared to conventional HRV and RRV features?
While Hilbert- and wavelet-derived cardiorespiratory features capture discriminative physiological dynamics in within-subject analyses and external stress datasets (WESAD balanced accuracy 0.862), they failed to generalize across unseen individuals in the small 18-participant anxiety-stimulus cohort (balanced accuracy 0.532).
Answers are grounded in this paper and cite their sources.
Does not support participant-independent anxiety classification; leaves open generalization in larger stress or anxiety cohorts.
Anxiety disorders are associated with measurable alterations in cardiorespiratory physiology that can be captured using wearable biosensing systems. This study investigates the classification of anxiety-inducing stimulus conditions using synchronized electrocardiography (ECG) and respiration (RSP) signals combined with Hilbert- and wavelet-derived signal features. Data were collected from 18 participants during anxiety-inducing and non-anxiety-inducing video conditions. A multimodal feature extraction framework incorporating heart rate variability, respiration rate variability, instantaneous amplitude, circular phase, instantaneous frequency, and wavelet descriptors was developed and evaluated using multiple machine learning classifiers. The primary evaluation used participant-independent nested leave-one-subject-out validation. On the original cohort, combined ECG and RSP features yielded a balanced accuracy of 0.532, close to chance level, whereas on the independent WESAD stress-versus-baseline dataset the identical pipeline achieved a balanced accuracy of 0.862, showing that the feature representation retained discriminative information across unseen individuals in a related affective task. In an exploratory within-dataset analysis, in which windows from the same participant could appear in both partitions, the Extra Trees classifier reached an accuracy of 0.968 and a compact subset of eight Hilbert- and wavelet-derived features reached an accuracy of 0.964 with a Matthews correlation coefficient of 0.894; these window-level values are within-dataset estimates rather than measures of generalization to unseen participants. Reliable generalization to unseen individuals and to measured anxiety requires larger cohorts with validated state-anxiety measurements.
No takes yet. Share an insight, caveat, or question.
Elgendi et al. (2026) conducted an observational in Anxiety-inducing vs non-anxiety-inducing stimulus exposure (n=18). Machine learning classification using Hilbert- and wavelet-derived cardiorespiratory (ECG and RSP) features vs. Conventional heart rate variability (HRV) and respiration rate variability (RRV) features was evaluated on Participant-independent balanced accuracy for classifying anxiety-inducing versus non-anxiety-inducing stimulus conditions using nested leave-one-subject-out validation. Hilbert- and wavelet-derived ECG and respiration features achieved a participant-independent balanced accuracy of 0.532 on the anxiety cohort and 0.862 on the WESAD stress dataset.
Synapse has enriched 10 related papers. Consider them for comparative context: