Acute psychological stress has a multifaceted impact on cardiovascular physiology, including increases in chronotropy, inotropy, and vascular tone. Chronic exposure to stress may greatly increase cardiovascular risk. To examine the cardiovascular impact of acute stress comprehensively, new multimodal portable monitoring solutions are needed. We examined the feasibility of using a compact multimodal wearable patch to measure laboratory-based stress-induced cardiovascular responses in a diverse sample with recent myocardial infarction (MI) and healthy participants (N = 37, 28 MI) during a protocol with a public-speaking stressor. Using the electrocardiogram, seismocardiogram, and photoplethysmogram captured from the device, we found several significant (p < 0.05) autonomic changes in the pooled sample suggesting stress activation: increases in heart rate, chest photoplethysmogram amplitude, and perfusion index and decreases in heart rate variability, left ventricular ejection time, pulse arrival time, and pulse transit time. We, thus, demonstrated that a single wearable device can capture stress-induced cardiovascular changes, enabling simultaneous examination of stress-induced inotropic, chronotropic, and vascular effects. This portable, wireless chest patch may be useful in comprehensively and unobtrusively examining stress-induced cardiovascular effects in-lab. Given the public health importance of psychological stress and cardiovascular disease, future studies should assess the device’s full clinical potential in larger groups with longer monitoring periods.

Opioid use disorder (OUD) is a significant global health issue, leading to severe physiological and psychological impacts and substantial societal costs. Current methods for assessing opioid withdrawal, primarily relying on subjective scales, suffer from limitations such as incomplete symptom capture, recall bias, and imprecision. Wearable sensor technologies offer a promising alternative for objective assessment, with previous studies demonstrating their ability to detect opioid use and measure related physiological changes. In this study we investigated the correlation between local cardio-mechanical variability quantified using dynamic time warping (DTW) distances of seismocardiogram (SCG) signals and subjective opioid withdrawal severity (SOWS) scores. In a 7-day in-patient protocol for individuals with OUD$(N=13)$, we found a statistically significant inverse correlation: shorter median DTW distances and reduced variance in SCG signals were associated with higher subjective withdrawal scores with statistically significant differences between the highest withdrawal bin and the two lowest bins ($\mathbf{p}=0.038$and$\mathbf{p}=0.044$, respectively). Our results suggests that local cardio-mechanical variability, as captured by wearable sensors and analyzed with DTW, can serve as a valuable indicator for quantifying opioid withdrawal severity, potentially enabling more timely and effective preventive care.

Seismocardiography is a potent non-invasive cardiovascular monitoring technique whose widespread adoption is currently limited in ambulatory settings due to its susceptibility to corruption from environmental noise. In the absence of a clean concurrently collected electrocardiogram (ECG) signal as a heartbeat reference, template matching paired with windowing methods can serve as a useful method by which to assess seismocardiogram (SCG) signal quality. However, windowing methods can introduce a time-shift in the segmentation of the SCG beats as compared to a template due to persistently adapting heart rate. In this study, we assess the performance of a state-of-the-art SCG signal quality assessment algorithm, dynamic time feature matching (DTFM), in ranking SCG beats by signal-to-noise ratio when introducing an artificial timedelay. We compare this performance against that of a novel methodology based on topological data analysis (TDA) using persistence diagrams. We found no significant difference$(p>0.05)$in ranking performance between topological data analysis (TDA) and dynamic time feature matching (DTFM) when SCG beats were segmented by true R-peak locations. However, we found that TDA significantly outperformed DTFM$(p<0.001)$when SCG beats were segmented 100, 200, or 300 ms earlier than the R-peak locations. These results suggest the potential promise of TDAbased methods for robust ECG-free SCG signal quality analysis. These advancements may facilitate the analysis of longitudinal SCG data taken in out-of-clinic settings in situations where ECG monitoring is not viable.

Atrial fibrillation (AF) is a common cardiac arrhythmia with serious health consequences if not detected and treated early. Detecting AF using wearable devices with photoplethysmography (PPG) sensors and deep neural networks has demonstrated some success using proprietary algorithms in commercial solutions. However, to improve continuous AF detection in ambulatory settings towards a population-wide screening use case, we face several challenges, one of which is the lack of large-scale labeled training data. To address this challenge, we propose to leverage AF alarms from bedside patient monitors to label concurrent PPG signals, resulting in the largest PPG-AF dataset so far (8.5 M 30-second records from 24,100 patients) and demonstrating a practical approach to build large labeled PPG datasets. Furthermore, we recognize that the AF labels thus obtained contain errors because of false AF alarms generated from imperfect built-in algorithms from bedside monitors. Dealing with label noise with unknown distribution characteristics in this case requires advanced algorithms. We, therefore, introduce and open-source a novel loss design, the cluster membership consistency (CMC) loss, to mitigate label errors. By comparing CMC with state-of-the-art methods selected from a noisy label competition, we demonstrate its superiority in handling label noise in PPG data, resilience to poor-quality signals, and computational efficiency.

BACKGROUND: Posttraumatic stress disorder (PTSD) causes heightened fight-or-flight responses to traumatic memories (i.e., hyperarousal). Although hyperarousal is hypothesized to cause irregular breathing (i.e., respiratory variability), no quantitative markers of respiratory variability have been shown to correspond with PTSD symptoms in humans. OBJECTIVE: In this study, we define interpretable markers of respiration pattern variability (RPV) and investigate whether these markers respond during traumatic memories, correlate with PTSD symptoms, and differ in patients with PTSD. METHODS: We recruited 156 veterans from the Vietnam-Era Twin Registry to participate in a trauma recall protocol. From respiratory effort and electrocardiogram measurements, we extracted respiratory timings and rate using a robust quality assessment and fusion approach. We then quantified RPV using the interquartile range and compared RPV between baseline and trauma recall conditions, correlated PTSD symptoms to the difference between trauma recall and baseline RPV (i.e., ∆RPV), and compared ∆RPV between patients with PTSD and trauma-exposed controls. Leveraging a subset of 116 paired twins, we then uniquely controlled for factors shared by co-twins via within-pair analysis for further validation. RESULTS: We found RPV was increased during traumatic memories (p .001), ∆ RPV was positively correlated with PTSD symptoms (p .05), and patients with PTSD exhibited higher ∆ RPV than trauma-exposed controls (p . 05). CONCLUSIONS: This paper is the first to elucidate RPV markers that respond during traumatic memories, especially in patients with PTSD, and correlate with PTSD symptoms. SIGNIFICANCE: These findings encourage future studies outside the clinic, where interpretable markers of respiratory variability are used to track hyperarousal.

Transcutaneous cervical vagal nerve stimulation (tcVNS) devices are attractive alternatives to surgical implants, and can be applied for a number of conditions in ambulatory settings, including stress-related neuropsychiatric disorders. Transferring tcVNS technologies to at-home settings brings challenges associated with the assessment of therapy response. The ability to accurately detect whether tcVNS has been effectively delivered in a remote setting such as the home has never been investigated. We designed and conducted a study in which 12 human subjects received active tcVNS and 14 received sham stimulation in tandem with traumatic stress, and measured continuous cardiopulmonary signals including the electrocardiogram (ECG), photoplethysmogram (PPG), seismocardiogram (SCG), and respiratory effort (RSP). We extracted physiological parameters related to autonomic nervous system activity, and created a feature set from these parameters to: 1) detect active (vs. sham) tcVNS stimulation presence with machine learning methods, and 2) determine which sensing modalities and features provide the most salient markers of tcVNS-based changes in physiological signals. Heart rate (ECG), vasomotor activity (PPG), and pulse arrival time (ECG+PPG) provided sufficient information to determine target engagement (compared to sham) in addition to other combinations of sensors. resulting in 96% accuracy, precision, and recall with a receiver operator characteristics area of 0.96. Two commonly utilized sensing modalities (ECG and PPG) that are suitable for home use can provide useful information on therapy response for tcVNS. The methods presented herein could be deployed in wearable devices to quantify adherence for at-home use of tcVNS technologies.

Heart failure (HF) is one of the leading causes of mortality in the United States with a high economic burden due to readmissions. We present a novel approach to remotely monitor quality of life in patients with HF using a smartphone app and a scalable cloud-based architecture. In a preliminary study, we assess continuous data from 10 HF subjects over a period of up to a year. Over 680 million samples of physical movement data, 9,000 geographic location updates, and 11,000 individual social networking events in the form of phone calls were captured from the app. Personalized models were constructed from these data to estimate self-reported quality of life using the Kansas City Cardiomyopathy Questionnaire (KCCQ), which has been shown to be a reliable health status measure for HF patients. Generalized linear models using only activity features were shown to reliably estimate the KCCQ score with an out of sample mean absolute error of 5.71%. Personalized models for estimating the HF severity as mild or severe were also built as a proof of concept to detect when a subject's data indicated a clinical deterioration. Average out of sample accuracy was 83% for this binary classification problem. Creation of personalized models from passive smartphone data collected `in-the-wild' to identify changes in HF severity appears possible. This new approach holds promise as a low burden and accurate method of monitoring HF symptoms, which could aid clinicians in early assessment and prevention of adverse outcomes.

Transcutaneous vagus nerve stimulation (t-VNS) is a promising technology for modulating brain function and possibly treating disorders of the central nervous system. While handheld devices are available for t-VNS, stimulation efficacy can only be quantified using expensive imaging or blood biomarker analyses. Additionally, the parameters and "dosage" recommendations for t-VNS are typically fixed, as there are limited biomarkers that can assess downstream effects of the stimulation outside of clinical settings. In this proof-of-concept study, we evaluated non-invasive peripheral cardiovascular measurements as physiological biomarkers of t-VNS efficacy. Specifically, we hypothesized two physiological biomarkers: (1) the pre-ejection period (PEP) of the heart - a parameter closely linked to sympathetic tone - and (2) the amplitude of peripheral photoplethysmogram (PPG) waveforms - representing changes in vasomotor tone and thus parasympathetic / sympathetic activation. A total of six healthy human subjects participated in the multi-day study, half each undergoing active or sham t-VNS stimulus. The three subjects receiving t-VNS had no decrease in PEP and an increase in PPG amplitude following t-VNS, while the subjects receiving sham stimulus had a decrease in PEP and no change in PPG amplitude. When combined with mental stress (a traumatic script being read back to the subjects), the group with t-VNS had no decrease in PEP and only a slight decrease in PPG amplitude following stimulus, while the group receiving sham stimulus had a decrease in PEP and also a slight decrease in PPG amplitude. These studies suggest that PEP and PPG amplitude measures may provide non-invasive physiological biomarkers of t-VNS efficacy, including in the presence of mental stress.

Detection of atrial fibrillation (AF), a type of cardiac arrhythmia, is difficult since many cases of AF are usually clinically silent and undiagnosed. In particular paroxysmal AF is a form of AF that occurs occasionally, and has a higher probability of being undetected. In this work, we present an attention based deep learning framework for detection of paroxysmal AF episodes from a sequence of windows. Time-frequency representation of 30 seconds recording windows, over a 10 minute data segment, are fed sequentially into a deep convolutional neural network for image-based feature extraction, which are then presented to a bidirectional recurrent neural network with an attention layer for AF detection. To demonstrate the effectiveness of the proposed framework for transient AF detection, we use a database of 24 hour Holter Electrocardiogram (ECG) recordings acquired from 2850 patients at the University of Virginia heart station. The algorithm achieves an AUC of 0.94 on the testing set, which exceeds the performance of baseline models. We also demonstrate the cross-domain generalizablity of the approach by adapting the learned model parameters from one recording modality (ECG) to another (photoplethysmogram) with improved AF detection performance. The proposed high accuracy, low false alarm algorithm for detecting paroxysmal AF has potential applications in long-term monitoring using wearable sensors.

The development of an aggregate view of the procurement spend across an enterprise using transactional data is increasingly becoming a very important and strategic activity. Not only does it provide a complete and accurate picture of what the enterprise is buying and from whom, it also allows it to consolidate suppliers, as well as negotiate better prices. The importance, as well as the complexity, of this cleansing exercise is further magnified by the increasing popularity of Business Transformation Outsourcing (BTO) wherein enterprises are turning over non-core activities, such as indirect procurement, to third parties, who now need to develop an integrated view of spend across multiple enterprises in order to optimize procurement and generate maximum savings. However, the creation of such an integrated view of procurement spend requires the creation of a homogeneous data repository from disparate (heterogeneous) data sources across various geographic and functional organizations throughout the enterprise(s). Such repositories get transactional data from various sources such as invoices, purchase orders, account ledgers. As such, the transactions are not cross-indexed, refer to the same suppliers by different names, and use different ways of representing information about the same commodities. Before an aggregated spend view can be developed, this data needs to be cleansed, primarily to normalize the supplier names and correctly map each transaction to the appropriate commodity code. Commodity mapping, in particular, is made more difficult by the fact that it has to be done on the basis of unstructured text descriptions found in the various data sources. We describe an on-demand system to automatically perform this cleansing activity using techniques from information retrieval and machine learning. Built on standard integration and application infrastructure software, this system provides enterprises with a fast, reliable, accurate and on-demand way of cleansing transactional data and generating an integrated view of spend. This system is currently in the process of being deployed by IBM for use in its BTO practice.