Understanding Heart Rate Reactions to Post-Traumatic Stress Disorder (PTSD) Among Veterans: A Naturalistic Study

Heart Rate Variability in Psychiatric Disorders: A Systematic Review

Introduction

Heart rate variability (HRV) is a measure of the fluctuation in time interval between consecutive heart beats. Decreased heart rate variability has been shown to have associations with autonomic dysfunction in psychiatric conditions such as depression, substance abuse, anxiety, and schizophrenia, although its use as a prognostic tool remains highly debated. This study aims to review the current literature on heart rate variability as a diagnostic and prognostic tool in psychiatric populations.

Methods

A literature search was conducted using the MEDLINE, EMBASE, Cochrane, and PsycINFO libraries to identify full-text studies involving adult psychiatric populations that reported HRV measurements. From 1647 originally identified, 31 studies were narrowed down through an abstract and full-text screen. Studies were excluded if they enrolled adolescents or children, used animal models, enrolled patients with another primary diagnosis other than psychiatric as outlined by the diagnostic and statistical manual of mental disorders (DSM) V, or if they assessed HRV in the context of treatment rather than diagnosis. Study quality assessment was conducted using a modified Downs and Blacks quality assessment tool for observational rather than interventional studies. Data were reported in four tables: 1) summarizing study characteristics, 2) methods of HRV detection, 3) key findings and statistics, and 4) quality assessment.

Results

There is significant variability between studies in their methodology of recording as well as reporting HRV, which makes it difficult to meaningfully interpret data that is clinically applicable due to the presence of significant bias in existing studies. The presence of an association between HRV and the severity of various psychiatric disorders, however, remains promising.

Conclusion

Future studies should be done to further explore how HRV parameters may be used to enhance the diagnosis and prognosis of several psychiatric disorders.

Wearable technologies for health research: Opportunities, limitations, and practical and conceptual considerations

One of the most notable limitations of laboratory-based health research is its inability to continuously monitor health-relevant physiological processes as individuals go about their daily lives. As a result, we have generated large amounts of data with unknown generalizability to real-world situations and also created a schism between where data are collected (i.e., in the lab) and where we need to intervene to prevent disease (i.e., in the field). Devices using noninvasive wearable technology are changing all of this, however, with their ability to provide high-frequency assessments of peoples' ever-changing physiological states in daily life in a manner that is relatively noninvasive, affordable, and scalable. Here, we discuss critical points that every researcher should keep in mind when using these wearables in research, spanning device and metric decisions, hardware and software selection, and data quality and sampling rate issues, using research on stress and health as an example throughout. We also address usability and participant acceptability issues, and how wearable "digital biomarker" and behavioral data can be integrated to enhance basic science and intervention studies. Finally, we summarize 10 key questions that should be addressed to make every wearable study as strong as possible. Collectively, keeping these points in mind can improve our ability to study the psychobiology of human health, and to intervene, precisely where it matters most: in peoples' daily lives.

Posttraumatic stress disorder hyperarousal event detection using smartwatch physiological and activity data

Posttraumatic Stress Disorder (PTSD) is a psychiatric condition affecting nearly a quarter of the United States war veterans who return from war zones. Treatment for PTSD typically consists of a combination of in-session therapy and medication. However; patients often experience their most severe PTSD symptoms outside of therapy sessions. Mobile health applications may address this gap, but their effectiveness is limited by the current gap in continuous monitoring and detection capabilities enabling timely intervention. The goal of this article is to develop a novel method to detect hyperarousal events using physiological and activity-based machine learning algorithms. Physiological data including heart rate and body acceleration as well as self-reported hyperarousal events were collected using a tool developed for commercial off-the-shelf wearable devices from 99 United States veterans diagnosed with PTSD over several days. The data were used to develop four machine learning algorithms: Random Forest, Support Vector Machine, Logistic Regression and XGBoost. The XGBoost model had the best performance in detecting onset of PTSD symptoms with over 83% accuracy and an AUC of 0.70. Post-hoc SHapley Additive exPlanations (SHAP) additive explanation analysis showed that algorithm predictions were correlated with average heart rate, minimum heart rate and average body acceleration. Findings show promise in detecting onset of PTSD symptoms which could be the basis for developing remote and continuous monitoring systems for PTSD. Such systems may address a vital gap in just-in-time interventions for PTSD self-management outside of scheduled clinical appointments.

A Predictive Analysis of Heart Rates Using Machine Learning Techniques

Heart disease, caused by low heart rate, is one of the most significant causes of mortality in the world today. Therefore, it is critical to monitor heart health by identifying the deviation in the heart rate very early, which makes it easier to detect and manage the heart’s function irregularities at a very early stage. The fast-growing use of advanced technology such as the Internet of Things (IoT), wearable monitoring systems and artificial intelligence (AI) in the healthcare systems has continued to play a vital role in the analysis of huge amounts of health-based data for early and accurate disease detection and diagnosis for personalized treatment and prognosis evaluation. It is then important to analyze the effectiveness of using data analytics and machine learning to monitor and predict heart rates using wearable device (accelerometer)-generated data. Hence, in this study, we explored a number of powerful data-driven models including the autoregressive integrated moving average (ARIMA) model, linear regression, support vector regression (SVR), k-nearest neighbor (KNN) regressor, decision tree regressor, random forest regressor and long short-term memory (LSTM) recurrent neural network algorithm for the analysis of accelerometer data to make future HR predictions from the accelerometer’s univariant HR time-series data from healthy people. The performances of the models were evaluated under different durations. Evaluated on a very recently created data set, our experimental results demonstrate the effectiveness of using an ARIMA model with a walk-forward validation and linear regression for predicting heart rate under all durations and other models for durations longer than 1 min. The results of this study show that employing these data analytics techniques can be used to predict future HR more accurately using accelerometers.