5 - (SYM 38) Prolonged Exposure Collective Sensing System: Pilot Data on a Ubiquitous Computing System That Facilitates Communication About Between-session Exposures and Enhances Patient Engagement

Most evidence-based exposure therapies require patients to engage in exposure between sessions. However, patient-clinician discussions about between-session exposures are limited by patient-generated data that is subjective, retrospective, unreliable, and narrow. Often, both patients and clinicians are unclear if the patient is sufficiently engaging in exposures and if the assigned exposures are resulting in adaptive, new learning. Clinicians would benefit from the collection of several continuous, noninvasive, and objective data streams during between-session exposures to efficiently track and respond to their patients’ engagement. Similarly, patients would benefit from timely and objective feedback about how to improve their engagement. To address these needs, we (1) developed a ubiquitous computing system that allows patient data transfer and information extraction during between-session exposures and (2) designed system interfaces to facilitate continuous monitoring for both clinicians and patients and to enable efficient clinician-patient communication at the point of care. Our first use case of this computational toolkit is prolonged exposure (PE) therapy for PTSD. This system, called the PE Collective Sensing System (PECSS), includes a mobile app for patients and an online dashboard for clinicians. PECSS includes active data collection (e.g., the patient’s ratings of distress during exposures and qualitative notes) and several streams of passive data collected via smartphone and wearable sensors: location, body movement, ambient noise, use of other mobile apps, duration, and heart rate. We will present findings from a deployment of PECSS with military veterans diagnosed with PTSD and receiving care at Emory Healthcare Veterans Program. Strong indicators of system usefulness and usability are evidenced by quantitative data using clinical outcome measures (PTSD Checklist for DSM-5; Patient Health Questionnaire – 9) and the System Usability Scale, as well as qualitative data using structured post-treatment interviews. We will discuss next research steps including future use cases and the development of computational models using system sensors to provide automated suggestions within the ubiquitous computing ecosystem to facilitate clinical decision-making.