JMIR Publications

ABSTRACT

Background:

The demand for sleep interventions is high and steadily growing. Digital therapeutics (DTx) can be a way to tackle this challenge for at least a portion of the patients. Mobile applications can help individuals improve their sleep remotely, over an extended time, and with less effort from medical professionals. The severity of obstructive sleep apnea (OSA), as one of the most prevalent and consequential sleep disorders, can be reduced with health-supporting behavioral changes such as physical exercise and weight loss and, therefore, acts as a promising application for DTx.

Objective:

We aimed to analyze a digital intervention from a medical and technological perspective by moving beyond clinical markers and exploring deeper how the DTx application was used and how that may be related to the study outcome. We introduced a way of using unsupervised machine learning to analyze the participants’ sleep, behavior, and engagement with the DTx application on a day-to-day level.

Methods:

A lifestyle intervention study (n=55) targeted at adults with mild-to-moderate OSA aimed to reduce their OSA severity using a DTx application over a study period of 12 weeks. The participants’ OSA severity was assessed through a polysomnography at the beginning and at the end of the study period and the participants tracked their sleep with a digital sleep diary and a smartwatch over the course of the entire study. The DTx application furthermore provided data on when and how the participants pursued the proposed lifestyle interventions. This multimodal data was explored through descriptive statistics, and association rules were derived using the apriori algorithm.

Results:

Analyzing the interaction of the participants with the application showed which lifestyle interventions they pursued and how their behavior and sleep changed over time. The participants with reduced OSA severity showed higher engagement with the DTx application, particularly the food-related interventions. The association rules showed that changes in awakenings during the night, staying awake in bed in the morning, and sleep quality frequently co-occurred with the education and movement missions.

Conclusions:

The study showed that DTx can be an effective treatment approach for some participants, particularly those who showed active engagement with the DTx application. We furthermore showed the richness of the different data sources offered in a digital intervention using wearables and how they can be employed to get an in-depth understanding of the study.