JMIR Publications

ABSTRACT

Background:

Physiological signals such as heart rate and electrodermal activity can provide insight into an individual’s mental state, which is invaluable information for mental health care. Using recordings of physiological signals from wearable devices in-the-wild can facilitate objective monitoring of symptom severity and evaluation of treatment progress.

Objective:

We designed a study to test the feasibility of predicting obsessive-compulsive disorder (OCD) events from physiological signals recorded using wrist-worn devices in-the-wild. Here, we present an analysis plan for the study to document our a-priori hypotheses and increase the robustness of the findings of our planned study.

Methods:

Time-domain and frequency-domain features are extracted from the heart rate, skin conductivity, and skin temperature signals within sliding windows. The features are used to predict the distress event logged by participants during data collection. We will test the prediction models within participants across time and across multiple participants. Model selection and estimation using two-layer cross-validation is outlined for both scenarios.

Results:

Physiological signals from 18 participants (nine diagnosed with OCD and nine controls) between the ages of 8 and 17 years are collected using wrist-worn devices during waking hours for up to eight weeks. For the nine participants with an OCD diagnosis and the severity of the diagnosis, number of, and type of symptoms has been graded using the CY-BOCS.

Conclusions:

A major strength of the planned study is the investigation of predictions of OCD events in-the-wild. A major challenge of the study is the inherent noise of in-the-wild data and the lack of contextual knowledge associated with the recorded signals. This pre-registered analysis plan may help reduce interpretation bias of the upcoming results. Clinical Trial: ClinicalTrials.gov: NCT05064527, registered October 1, 2021.