We investigate the use of audio-inspired features to characterize ECG-derived skin sympathetic nerve activity (SKNA). Building on concepts from audio signal processing, we designed a set of SKNA-optimized spectral and energy-related features tailored to the transient, burst-like nature of sympathetic activation. High-frequency ECG signals were recorded from 20 participants during rest and during cognitive stress induced by the Stroop Color and Word Test. Applied to this two-phase protocol, the proposed features captured consistent differences between baseline and stress, achieving robust classification performance using support vector machines with leave-one-subject-out cross-validation. Results demonstrate that audio-inspired features, when physiologically constrained, provide a powerful and interpretable representation of SKNA dynamics, highlighting their promise for noninvasive assessment of autonomic function.

Accurate estimation of sleepiness levels is crucial for managing sleep-related health risks and preventing cognitive degradation that can lead to accidents in the workplace. However, using machine learning (ML) to estimate these levels from speech remains challenging, with reported weak correlations (<0.40) with ground-truth sleepiness levels. Developing effective ML models requires high-quality sleepiness data from noticeably sleepy individuals, but collecting such data through prolonged sleep deprivation is both risky and costly. We propose that acted (feigned) sleepy speech can effectively represent realistic sleepiness and be used to train ML models for estimating sleepiness levels and detecting sleepiness-associated cognitive performance degradation. Our study demonstrates that: (1) human listeners perceive acted sleepy speech as sleepier than both non-sleepy and genuinely sleepy speech, and (2) ML models trained on acted speech can accurately estimate sleepiness levels in individuals who have been awake for 25 hours, achieving a correlation of 0.54 with ground-truth sleepiness levels while using fewer samples. Furthermore, the acted sleepy speech-based ML model detects cognitive performance degradation (F1 score = 0.80) in sleep-deprived individuals, outperforming models trained on real sleepy speech (F1 score = 0.32). Our approach provides efficient, effective, and scalable solutions to not only update benchmarks but also enhance the capabilities of real-world AI applications, from voice assistants to AI agents, ultimately supporting human health, workplace safety, and daily tasks.

The sympathetic nervous system (SNS) is pivotal in cardiovascular regulation. Skin sympathetic nerve activity (SKNA), extracted from electrocardiogram (ECG), is an innovative noninvasive metric for assessing SNS, traditionally evaluated via electrodermal activity (EDA). Identifying sparse drivers—markers of neural discharge onsets in EDA or SKNA signals—enhances SNS analysis. We employed the SparsEDA algorithm to identify SKNA drivers and compared them with EDA phasic drivers derived from cvxEDA and SparsEDA algorithms. Our evaluation included burst detection performance and temporal features: stimulus-to-response time and recovery time. In a thermal grill pain experiment with sixteen subjects, each undergoing six SNS stimulations, we concurrently recorded EDA and SKNA signals. SKNA demonstrated superior performance with a 97% hit rate, 100% recovery rate, and minimal false alarms during control (0.20±0.77) and interstimulus periods (1.27±1.44). In contrast, EDA drivers had hit and recovery rates below 80% and 50%, respectively, and a higher number of false alarms during interstimulus times (SparsEDA: 11.36±5.24; cvxEDA: 10.00±5.88). SKNA drivers closely matched annotated labels, achieving a root mean square error (RMSE) of 0.42 s, outperforming SparsEDA (RMSE: 5.09 s) and cvxEDA (RMSE: 3.73 s) drivers. The SKNA recovery time averaged 5.59±2.44 seconds, closely aligning with the actual pain stimulus duration (∼5 s), whereas EDA recovery times were nearly three times longer. The superior accuracy of SKNA drivers may result from directly measuring nerve activity, unlike EDA signals influenced by sweat pore hydrodynamics. Therefore, SKNA, with its precise onset response and quicker recovery time, holds promise for diverse applications in SNS assessment.

Continuous monitoring of non-invasive skin sympathetic nerve activity (SKNA) holds promise for understanding the sympathetic nervous system (SNS) dynamics in various physiological and pathological conditions. However, muscle noise artifacts present a challenge in accurate SKNA analysis, particularly in real-life scenarios. This study proposes a deep convolutional neural network (CNN) approach to detect and remove muscle noise from SKNA recordings obtained via ECG electrodes. Twelve healthy participants underwent controlled experimental protocols involving cognitive stress induction and voluntary muscle movements, while collecting SKNA data. Power spectral analysis revealed significant muscle noise interference within the SKNA frequency band (500–1000 Hz). A 2D CNN model was trained on the spectrograms of the data segments to classify them into baseline, stress-induced SKNA, and muscle noise-contaminated periods, achieving an average accuracy of 89.85% across all subjects. Our findings underscore the importance of addressing muscle noise for accurate SKNA monitoring, advancing towards wearable SKNA sensors for real-world applications.

Pain is typically viewed as an internal perception that is difficult to objectively measure. Current methods attempt to quantify pain intensity using self-reported scores, but these are often subjective or difficult to administer. Three primary sensory nerve fibers carry pain and tactile information: AP- and Ad-flbers carrying short touch and acute pain, respectively, and C-fibers carrying dull prolonged pain. Electrodermal activity (EDA), previously shown to be highly sensitive to pain and stress responses, may allow us to distinguish these different pain signals to more fully express measured pain. In this work, we use machine learning to classify EDA responses associated with these fibers during sine wave transcutaneous electrical nerve stimulation. Using several derived EDA features, we are able to develop models that obtain high accuracy (>75%) of classification across all three fiber types in this multiclass classification task. The ability to measure fiber-specific activation may help greatly improve pain detection and treatment research.

Recently, it has been shown that skin sympathetic nerve activity (SKNA) can be obtained using electrocardiogram (ECG) signals at a high sampling rate. More importantly, recent studies have demonstrated that SKNA can be used as a surrogate noninvasive measure for assessing the sympathetic nervous system (SNS) activity. The electrodermal activity (EDA), which is a measure of changes in skin conductance due to sympathetic innervation, has also been shown to be a noninvasive physiomarker of SNS. For example, EDA has successfully shown its sensitivity and classification accuracy in detecting sympathetic elevation due to pain and emotion arousals. Given these two distinct approaches to noninvasive assessment of SNS, we directly compared and evaluated the effectiveness of ECG-derived SKNA and EDA in assessing SNS activity. Moreover, we examined if there is a direct correlation between SKNA and EDA given that both measurements provide SNS information. To this end, nine participants were recruited for Valsalva maneuver (VM) and thermal grill pain tests, while simultaneously recording ECG and EDA. Four features were derived from each of the integral area of rectified SKNA (iSKNA) and the phasic component of EDA signals (EDAphasic): peak amplitude, average amplitude, energy, and standard deviation. We then calculated Fisher’s ratio and area under the receiver operating characteristic curve (AUROC) for each feature. Peak amplitude and standard deviation of iSKNA showed significant difference between baseline and post-stimulation. Standard deviation of iSKNA showed a higher Fisher’s ratio and AUROC than any other EDA and SKNA features. EDAphasicshowed a delay of 4+ seconds from the onset of the stimulation, compared to SKNA. Moreover, by applying a larger window to extract iSKNA, we obtained Pearson correlation coefficient value of 0.78±0.22 between iSKNA and EDAphasicin VM test. In conclusion, SKNA was a better discriminative measure than EDA in obtaining SNS information. In addition, EDA dynamics can be derived from SKNA with the latter providing better onset and endpoint of SNS dynamics than the former.

Sleep deprivation is known to impair cognitive performance and contribute to workplace accidents. Bio-signal-based sleepiness detection approaches, facilitated by mobile healthcare systems, have emerged as a promising tool for preventing such accidents. However, due to the wide-ranging effects of sleep deprivation on human physiology and the sympathetic nervous system, accurately determining sleepiness remains challenging. In this study, we hypothesize that speaking loudly could increase the sensitivity of electrothermal activity (EDA) to sleep deprivation, as EDA measures changes in sympathetic nervous system activity. To validate our hypothesis, twenty participants underwent 25 hours of prolonged wakefulness, during which they vocalized loudly and completed a cognitive performance test, 10-min Psychomotor Vigilance Test (PVT) to measure their prolonged reaction time. Two EDA measures retrieved in speaking versus PVT tasks were compared. As result, EDA obtained during the speaking activity exhibited a stronger group correlation of ~-0.96 and individual correlation of ~-0.53 with sleep deprived indicators (i.e., reaction time) compared to the EDA acquired during the PVT task. We found a feasibility of performance degradation can be predictive by capturing the activity of the sympathetic nervous system precisely during the speaking activity. Moreover, the study emphasizes the importance of speaking activity in investigating sleepiness detection approaches based on speech, which have gained significant attention in recent research.

The current method for assessing pain in clinical practice is subjective and relies on self-reported scales. An objective and accurate method of pain assessment is needed for physicians to prescribe the proper medication dosage, which could reduce addiction to opioids. Hence, many works have used electrodermal activity (EDA) as a suitable signal for detecting pain. Previous studies have used machine learning and deep learning to detect pain responses, but none have used a sequence-to-sequence deep learning approach to continuously detect acute pain from EDA signals, as well as accurate detection of pain onset. In this study, we evaluated deep learning models including 1-dimensional convolutional neural networks (1D-CNN), long short-term memory networks (LSTM), and three hybrid CNN-LSTM architectures for continuous pain detection using phasic EDA features. We used a database consisting of 36 healthy volunteers who underwent pain stimuli induced by a thermal grill. We extracted the phasic component, phasic drivers, and time-frequency spectrum of the phasic EDA (TFS-phEDA), which was found to be the most discerning physiomarker. The best model was a parallel hybrid architecture of a temporal convolutional neural network and a stacked bi-directional and uni-directional LSTM, which obtained a F1-score of 77.8% and was able to correctly detect pain in 15-second signals. The model was evaluated using 37 independent subjects from the BioVid Heat Pain Database and outperformed other approaches in recognizing higher pain levels compared to baseline with an accuracy of 91.5%. The results show the feasibility of continuous pain detection using deep learning and EDA.

Two parameters that a breathing status monitor should provide include tidal volume (VT ) and respiration rate (RR). Recently, we implemented an optical monitoring approach that tracks chest wall movements directly on a smartphone. In this paper, we explore the use of such noncontact optical monitoring to obtain a volumetric surrogate signal, via analysis of intensity changes in the video channels caused by the chest wall movements during breathing, in order to provide not only average RR but also information about VT and to track RR at each time instant (IRR). The algorithm, implemented on an Android smartphone, is used to analyze the video information from the smartphone's camera and provide in real time the chest movement signal from N = 15 healthy volunteers, each breathing at VT ranging from 300 mL to 3 L. These measurements are performed separately for each volunteer. Simultaneous recording of volume signals from a spirometer is regarded as reference. A highly linear relationship between peak-to-peak amplitude of the smartphone-acquired chest movement signal and spirometer VT is found (r2= 0.951 ± 0.042, mean ± SD). After calibration on a subject-by-subject basis, no statistically significant bias is found in terms of VT estimation; the 95% limits of agreement are -0.348 to 0.376 L, and the rootmean-square error (RMSE) was 0.182 ± 0.107 L. In terms of IRR estimation, a highly linear relation between smartphone estimates and the spirometer reference was found (r2= 0.999 ± 0.002). The bias, 95% limits of agreement, and RMSE are -0.024 breaths-per-minute (bpm), -0.850 to 0.802 bpm, and 0.414 ±0.178 bpm, respectively. These promising results show the feasibility of developing an inexpensive and portable breathing monitor, which could provide information about IRR as well as VT, when calibrated on an individual basis, using smartphones. Further studies are required to enable practical implementation of the proposed approach.