JMIR Publications

ABSTRACT

Background:

Digital phenotyping refers to the objective measurement of human behavior via devices such as smartphones or watches and constitutes a promising advancement in personalized medicine. Digital phenotypes derived from heart rate, mobility, or sleep schedule data utilized in psychiatry to either diagnose individuals with psychotic disorders, or to predict relapse as a binary outcome. Machine learning models so far have achieved predictive accuracies that are significant but have not large enough for clinical applications. This could hinge on broad clinical definitions, which encompass heterogenous symptom and sign ensembles, thus hindering accurate classification. The five-factor model for the Positive and Negative Symptom Scale (PANNS), which entails five independently varying dimensions, is thought to better capture symptom variability. Utilizing the specific definitions of this refined clinical taxonomy in combination with digital phenotypes could yield more precise results.

Objective:

The present study aims to investigate potential links between digital phenotypes and each dimension of the five-factor PANNS model. We also assess whether clinical, demographic and medication variables confound said relations.

Methods:

In the E-prevention study, heart rate, accelerometer, gyroscope and sleep schedule data were continuously collected via smartwatch for a maximum of 24 months, in 38 patients with psychotic spectrum disorders. Obtaining the mean and standard deviation for each patient-month, resulted in a database consisting of more than 740 monthly data points. A linear mixed model analysis was used to ascertain connections between monthly aggregated heart rate and mobility features and the 5 symptom dimension scores of PANNS, obtained during monthly clinical interviews.

Results:

The positive symptom dimension was associated with increased sympathetic and decreased parasympathetic tone, while the negative dimension was mainly connected to decreased mobility during wakefulness. For the excitement/hostility and the depression/anxiety dimension we report an increase in motor activity during sleep while only excitement/hostility was related to increase in sympathetic heart activation and decreased sleep. The cognitive/disorganization dimension was related to decreased variability in sympathetic activation during wakefulness.

Conclusions:

This study provides evidence that biological changes assessed by continuous measurement of digital phenotypes could be characteristic of specific symptom clusters rather than entire diagnostic categories of psychotic disorders. These results support the use of digital phenotypes not only as means for remote patient monitoring, but as concrete targets for biomarker research in psychotic disorders.