Digital biomarkers of anxiety disorder symptom changes: Personalized deep learning models using smartphone sensors accurately predict anxiety symptoms from ecological momentary assessments.

Citation metadata

Date: Feb. 2022
Publisher: Elsevier Science Publishers
Document Type: Report; Brief article
Length: 330 words

Document controls

Main content

Abstract :

Keywords Passive sensing; Digital phenotyping; Anxiety disorders; Ecological momentary assessment; Generalized anxiety disorder; Social anxiety disorder Highlights * Smartphones can capture social interaction, movement, physiology, and the environment. * Smartphone data and deep learning can predict rapid changes in avoidance and anxiety. * Deep learning models and smartphones may promote just-in-time adaptive interventions. Abstract Smartphones are capable of passively capturing persons' social interactions, movement patterns, physiological activation, and physical environment. Nevertheless, little research has examined whether momentary anxiety symptoms can be accurately assessed using these methodologies. In this research, we utilize smartphone sensors and personalized deep learning models to predict future anxiety symptoms among a sample reporting clinical anxiety disorder symptoms. Participants (N = 32) with generalized anxiety disorder and/or social anxiety disorder (based on self-report) installed a smartphone application and completed ecological momentary assessment symptoms assessing their anxiety and avoidance symptoms hourly for the course of one week (T = 2007 assessments). During the same period, the smartphone app collected information about physiological activation (heart rate and heart rate variability), exposure to light, social contact, and GPS location. GPS locations were coded to reveal the type of location and the weather information. Personalized deep learning models using the smartphone sensor data were capable of predicting the majority of total variation in anxiety symptoms (R.sup.2 = 0.748) and predicting a large proportion of within-person variation at the hour-by-hour level (mean R.sup.2 = 0.385). These results suggest that personalized deep learning models using smartphone sensor data are capable of accurately predicting future anxiety disorder symptom changes. Author Affiliation: (a) Center for Technology and Behavioral Health, Departments of Biomedical Data Science and Psychiatry, Geisel School of Medicine, Dartmouth College, 46 Centerra Parkway; Suite 300, Office # 333S, Lebanon, NH, 03766, USA (b) Dartmouth College, 46 Centerra Parkway; Suite 300, Office # 333S, Lebanon, NH, 03766, USA * Corresponding author. Article History: Received 22 April 2021; Revised 29 November 2021; Accepted 6 December 2021 Byline: Nicholas C. Jacobson [] (a,*), Sukanya Bhattacharya (b)

Source Citation

Source Citation   

Gale Document Number: GALE|A690387992