Wearable sensors can assist in PTSD diagnosis

Webb, Andrea; Vincent, A.; Jin, Alvin; Pollack, Mark H.

doi:10.1109/bsn.2013.6575525

Cited by 7 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, Hinrichs et al [37] analyzed skin conductance signals captured with electrodes via a mobile device to show the existence of a positive correlation between skin conductance and PTSD symptoms. Webb et al [78] used virtual reality videos to trigger subjects while evaluating physiology to identify subjects with and without PTSD. Nonetheless, to the best of our knowledge, this is the first work that employs a multimodal machine-learning-based approach using CSE-T questionnaires and skin conductance to predict changes in PTSD symptom severity.…”

Section: Related Workmentioning

confidence: 99%

A Multimodal Approach for Predicting Changes in PTSD Symptom Severity

Mallol-Ragolta

Dhamija

Boult

2018

Proceedings of the 20th ACM International Conference on Multimodal Interaction

View full text Add to dashboard Cite

The rising prevalence of mental illnesses is increasing the demand for new digital tools to support mental wellbeing. Numerous collaborations spanning the fields of psychology, machine learning and health are building such tools. Machine-learning models that estimate effects of mental health interventions currently rely on either user self-reports or measurements of user physiology. In this paper, we present a multimodal approach that combines selfreports from questionnaires and skin conductance physiology in a web-based trauma-recovery regime. We evaluate our models on the EASE multimodal dataset and create PTSD symptom severity change estimators at both total and cluster-level. We demonstrate that modeling the PTSD symptom severity change at the total-level with self-reports can be statistically significantly improved by the combination of physiology and self-reports or just skin conductance measurements. Our experiments show that PTSD symptom cluster severity changes using our novel multimodal approach are significantly better modeled than using self-reports and skin conductance alone when extracting skin conductance features from triggers modules for avoidance, negative alterations in cognition & mood and alterations in arousal & reactivity symptoms, while it performs statistically similar for intrusion symptom.

show abstract

Section: Related Workmentioning

confidence: 99%

A Multimodal Approach for Predicting Changes in PTSD Symptom Severity

Mallol-Ragolta

Dhamija

Boult

2018

Proceedings of the 20th ACM International Conference on Multimodal Interaction

View full text Add to dashboard Cite

show abstract

“…For this work, we use data from a pilot-scaled study examining physiological response of PSTD by presenting the subjects with virtual reality videos (Webb et al 2013). In particular, male veteran subjects were shown two non-idiographic videos generated with the Virtual Iraq software originally designed for treatment applications 1 .…”

Section: Ptsd Study and Pre-processingmentioning

confidence: 99%

“…The IBI and GSR signals were segmented into 20 second windows, called response curves, beginning at each video event. Eleven (11) features commonly used to study various psychological concepts, including peak amplitude, standard deviation, and area to full recovery were extracted from each of the ten (10) response curves (for a total of 110 features per subject) (Kircher and Raskin 1988;Webb et al 2013). Fifty-seven (D = 57) features remained for use in learning a score after preliminary class-wise analyses (Webb et al 2013).…”

Section: Ptsd Study and Pre-processingmentioning

confidence: 99%

“…Linearity Prior work has suggested that linear models using a standard set of features works well for the binary diagnosis problem (Webb et al 2013). As an application, as encapsulated by our solution desideratum of parsimony, it is important to provide a solution that is human interpretable, so that users will trust it (Giraud-Carrier 1998; Rudin and Wagstaff 2014); linear models fulfill this objective.…”

Section: Learning Desideratamentioning

confidence: 99%

“…based on patient self-reports after a time consuming and expensive process, so a more objective, easier to administer diagnostic tool is sought. Although definitive physiological bases have yet to be characterized well enough to build a test, prior work has demonstrated that measurements of peripheral physiology can be used to predict diagnostic class assigned by the clinician (Orr, Metzger, and Pitman 2002;Webb et al 2013;Pitman et al 1987). We seek to advance this line of work by producing a score which provides a finer degree of granularity, necessary for treatment planning and monitoring.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Sparse Combined Regression-Classification Formulation for Learning a Physiological Alternative to Clinical Post-Traumatic Stress Disorder Scores

Brown

Webb

Mangoubi

et al. 2015

AAAI

View full text Add to dashboard Cite

Current diagnostic methods for mental pathologies, including Post-Traumatic Stress Disorder (PTSD), involve a clinician-coded interview, which can be subjective. Heart rate and skin conductance, as well as other peripheral physiology measures, have previously shown utility in predicting binary diagnostic decisions. The binary decision problem is easier, but misses important information on the severity of the patient’s condition. This work utilizes a novel experimental set-up that exploits virtual reality videos and peripheral physiology for PTSD diagnosis. In pursuit of an automated physiology-based objective diagnostic method, we propose a learning formulation that integrates the description of the experimental data and expert knowledge on desirable properties of a physiological diagnostic score. From a list of desired criteria, we derive a new cost function that combines regression and classification while learning the salient features for predicting physiological score. The physiological score produced by Sparse Combined Regression-Classification (SCRC) is assessed with respect to three sets of criteria chosen to reflect design goals for an objective, physiological PTSD score: parsimony and context of selected features, diagnostic score validity, and learning generalizability. For these criteria, we demonstrate that Sparse Combined Regression-Classification performs better than more generic learning approaches.

show abstract