John A. Berkebile

To enable timely intervention and reduce risk of returning to use in individuals with opioid use disorder (OUD), there is a need to monitor opioid withdrawal severity using physiological biomarkers. However, in the context of opioid withdrawal, prior studies have relied on data recorded in controlled lab settings over short periods of time and have only focused on a limited set of biomarkers. To address these limitations, using multimodal wearable signals, we extracted and characterized 32 cardiorespiratory features from 16 individuals with OUD experiencing varying levels of withdrawal severity over a 7-day period. Across all participants, we found statistically significant ( p < 0.05) differences in 6 features between high and low withdrawal. For machine learning-based classification of high vs. low withdrawal, we found that performance improved when leveraging respiratory-focused and sex-/BMI-stratified models (highest macro F1 of 0.812). Finally, in 14 out of 16 participants, at least 1 feature statistically significantly ( p < 0.1) tracked changes in withdrawal scores over the 7-day period. Therefore, our analyses of these features uncovered substantial phenotype sensitivity and physiological heterogeneity across the study cohort. These findings underscore the need for phenotype-aware and personalized modeling approaches for continuous, sensor-based monitoring of withdrawal severity in the future.

Background: Asthma remains one of the most serious chronic diseases of childhood. Individuals with severe asthma experience sudden episodes of breathlessness due to acute airflow obstruction, leading to recurrent pediatric intensive care unit (PICU) admissions that often result in mechanical ventilation and even death. Existing clinical assessments lack temporal resolution to effectively track the rapidly changing physiology. Objective: This study aimed to evaluate the feasibility of quantifying respiratory health during acute asthma in children using wearable multimodal sensing. Methods: Wearable-based impedance pneumography (IP) and multichannel lung sounds (LSs) were measured on 17 children admitted to the PICU with an acute asthma attack and on 9 healthy controls. Short-term multimodal measurements were obtained throughout hospitalization, specifically at PICU admission (T1) and discharge (T2). Measurements were also obtained from controls without any signs of acute asthma or otherwise healthy. Statistical and clustering analyses were performed to identify trends in IP- and LS-derived respiratory markers from T1 to T2 across all patients with paired time points (n=13), as well as across the matched cohort (T1: n=10 and T2: n=7), who were compared against controls (n=9). Five features were computed from the IP signal: respiratory rate, inspiration time (Ti), expiration time (Te), expiration-to-inspiration time ratio (Te:Ti), and the normalized Ti by interbreath interval (Ti/IBI). Leveraging the breathing context provided by the IP signal, 4 spectral integrated intensity (SI) acoustic features were computed in 4 different subbands for the inspiration and expiration phases. Results: Within the patient group (n=13), we found that respiratory rate decreased (W(12)=79; P=.02), whereas Te (W(12)=12; P=.02) and Ti (W(12)=13; P=.02) lengthened. Meanwhile, the SIs for the lowest subband (100-300 Hz) decreased for both inspiration and expiration phases (P<.01), while they increased for the highest subband (800-1000 Hz) for both inspiration and expiration phases (P<.01). Significant differences also existed between T1 and control and T2 and control of the matched cohort. We found that all features were significantly different between T1 and control (P<.05), and all SIs together with Te:Ti and Ti/IBI were significantly different between T2 and control (P<.05), all exhibiting trends toward normalcy. Conclusions: These results demonstrate the feasibility of quantifying and tracking respiratory health in children with acute asthma using wearable multimodal sensing, specifically with the fusion of IP- and LS-derived markers. Such technology may provide a new adjunctive clinical tool for real-time respiratory monitoring and enable timely titration of care, thereby improving patient outcomes.

Objective: Memory function underlies mental and behavioral health. While the role of the central nervous system (CNS) during episodic memory encoding and retrieval is well researched, the interplay between the CNS and the autonomic nervous system (ANS) during these processes is not. We addressed this gap by analyzing fluctuations in CNS-ANS network coupling during an episodic memory task (EMT). Methods: Sixty-seven healthy adults completed an EMT consisting of three stages: Encoding, Retrieval 1, and Retrieval 2. From electroencephalogram (EEG) recordings, we estimated time-varying CNS indices via alpha and theta power. Simultaneously, from electrocardiogram (ECG) and seismocardiogram (SCG) recordings, we estimated time-varying parasympathetic and sympathetic indices via cardiac vagal index (CVI) and pre-ejection period, respectively (PEP). Using time delay stability and surrogate data analysis, for each protocol condition, we assessed coverage, the percentage of significant coupling links, over the CVI-Neural and PEP-Neural networks. Results: Median coverage of CVI-Neural and PEP-Neural increased from Baseline to Encoding (+13.2%, $p$$p$$p$$p$$p$$p$<0.05). Conclusion: This is the first work to integrate EEG, ECG, and SCG time series to elucidate CNS-ANS interactions during an EMT. We demonstrated that healthy adults experienced parallel changes in CNS-parasympathetic and CNS-sympathetic network coverage during the task. Significance: In the future, measuring neural and cardiomechanical signals to estimate CNS-ANS coupling while probing memory function in clinical populations may help derive new mental health screening biomarkers.

BACKGROUND Asthma remains one of the most serious chronic diseases of childhood. Individuals with severe asthma experience sudden episodes of breathlessness due to acute airflow obstruction, leading to recurrent pediatric intensive care unit (PICU) admissions that often result in mechanical ventilation and even death. Existing clinical assessments lack temporal resolution to effectively track the rapidly changing physiology. OBJECTIVE This study aimed to evaluate the feasibility of quantifying respiratory health during acute asthma in children using wearable multimodal sensing. METHODS Wearable-based impedance pneumography (IP) and multichannel lung sounds (LSs) were measured on 17 children admitted to the PICU with an acute asthma attack and on 9 healthy controls. Short-term multimodal measurements were obtained throughout hospitalization, specifically at PICU admission (T1) and discharge (T2). Measurements were also obtained from controls without any signs of acute asthma or otherwise healthy. Statistical and clustering analyses were performed to identify trends in IP- and LS-derived respiratory markers from T1 to T2 across all patients with paired time points (n=13), as well as across the matched cohort (T1: n=10 and T2: n=7), who were compared against controls (n=9). Five features were computed from the IP signal: respiratory rate, inspiration time (Ti), expiration time (Te), expiration-to-inspiration time ratio (Te:Ti), and the normalized Ti by interbreath interval (Ti/IBI). Leveraging the breathing context provided by the IP signal, 4 spectral integrated intensity (SI) acoustic features were computed in 4 different subbands for the inspiration and expiration phases. RESULTS Within the patient group (n=13), we found that respiratory rate decreased (W(12)=79; P=.02), whereas Te (W(12)=12; P=.02) and Ti (W(12)=13; P=.02) lengthened. Meanwhile, the SIs for the lowest subband (100-300 Hz) decreased for both inspiration and expiration phases (P<.01), while they increased for the highest subband (800-1000 Hz) for both inspiration and expiration phases (P<.01). Significant differences also existed between T1 and control and T2 and control of the matched cohort. We found that all features were significantly different between T1 and control (P<.05), and all SIs together with Te:Ti and Ti/IBI were significantly different between T2 and control (P<.05), all exhibiting trends toward normalcy. CONCLUSIONS These results demonstrate the feasibility of quantifying and tracking respiratory health in children with acute asthma using wearable multimodal sensing, specifically with the fusion of IP- and LS-derived markers. Such technology may provide a new adjunctive clinical tool for real-time respiratory monitoring and enable timely titration of care, thereby improving patient outcomes.

In neurodegenerative conditions like Parkinson’s disease (PD) and multiple system atrophy (MSA), cardiovascular autonomic dysfunction (CVAD) is associated with several poor longterm health outcomes. CVAD commonly manifests as orthostatic hypotension (OH), a sustained drop in blood pressure upon standing that can cause syncope and falls. Conventional screening methods for OH are suboptimal and formal autonomic testing is limited to specialized centers. This study explores a multimodal wearable sensing patch for remote monitoring of CVAD. We collected wave-form data during clinical autonomic testing and a 24-hour period at home from 20 participants with synucleinopathies (12 with OH) and 6 healthy controls. We developed an automated posture detection pipeline that identified 103 at-home orthostatic events. Then, physiomarkers related to heart rate variability, cardiac mechanics, and vasomotor function were derived during the supine and standing periods associated with clinical and at-home orthostatic transitions. Comparisons of baroreflex-related supine physiomarkers revealed significant differences between those with and without OH. We characterized cardiovascular autonomic dynamics while standing, leveraging low-dimensional representations, and found marked differences in the aggregate responses between groups. We also observed significantly higher within-subject similarity between the at-home responses of the OH group. Finally, we examined the discriminative power of the patch’s physiomarkers and demonstrated accurate classification of persons with OH during the clinical stand testing (F1=0.83). This study is the first to couple orthostatic event detection with machine learning analysis of wearable-derived physiomarkers, illustrating that wearable sensing can accurately classify OH and provide novel insights into CVAD outside the clinic.

Chronic respiratory diseases affect millions and are leading causes of death in the US and worldwide. Pulmonary auscultation provides clinicians with critical respiratory health information through the study of Lung Sounds (LS) and the context of the breathing-phase and chest location in which they are measured. Existing auscultation technologies, however, do not enable the simultaneous measurement of this context, thereby potentially limiting computerized LS analysis. In this work, LS and Impedance Pneumography (IP) measurements were obtained from 10 healthy volunteers while performing normal and forced expiratory (FE) breathing maneuvers using our wearable IP and respiratory sounds(WIRS) system. Simultaneous auscultation was performed with the Eko CORE stethoscope (EKO). The breathing phase context was extracted from the IP signals and used to compute phase-by-phase (Inspiratory (I), expiratory (E), and their ratio (I:E)) and breath-by-breath acoustic features. Their individual and added value was then elucidated through machine learning analysis. We found that the phase-contextualized features effectively captured the underlying acoustic differences between deep and FE breaths, yielding a maximum F1 Score of 84.1±11.4% with the phase-by-phase features as the strongest contributors to this performance. Further, the individual phase-contextualized models outperformed the traditional breath-by-breath models in all cases. The validity of the results was demonstrated for the LS obtained with WIRS, EKO, and their combination. These results suggest that incorporating breathing-phase context may enhance computerized LS analysis. Hence, multimodal sensing systems that enable this, such as WIRS, have the potential to advance LS clinical utility beyond traditional manual auscultation and improve patient care