Effectiveness of a Smartphone App With a Wearable Activity Tracker in Preventing the Recurrence of Mood Disorders: Prospective Case-Control Study

Abstract

Background: Smartphones and wearable devices can be used to obtain diverse daily log data related to circadian rhythms. For patients with mood disorders, giving feedback via a smartphone app with appropriate behavioral correction guides could play an important therapeutic role in the real world.

Objective: We aimed to evaluate the effectiveness of a smartphone app named Circadian Rhythm for Mood (CRM), which was developed to prevent mood episodes based on a machine learning algorithm that uses passive digital phenotype data of circadian rhythm behaviors obtained with a wearable activity tracker. The feedback intervention for the CRM app consisted of a trend report of mood prediction, H-score feedback with behavioral guidance, and an alert system triggered when trending toward a high-risk state.

Methods: In total, 73 patients with a major mood disorder were recruited and allocated in a nonrandomized fashion into 2 groups: the CRM group (14 patients) and the non-CRM group (59 patients). After the data qualification process, 10 subjects in the CRM group and 33 subjects in the non-CRM group were evaluated over 12 months. Both groups were treated in a similar manner. Patients took their usual medications, wore a wrist-worn activity tracker, and checked their eMoodChart daily. Patients in the CRM group were provided with daily feedback on their mood prediction and health scores based on the algorithm. For the CRM group, warning alerts were given when irregular life patterns were observed. However, these alerts were not given to patients in the non-CRM group. Every 3 months, mood episodes that had occurred in the previous 3 months were assessed based on the completed daily eMoodChart for both groups. The clinical course and prognosis, including mood episodes, were evaluated via face-to-face interviews based on the completed daily eMoodChart. For a 1-year prospective period, the number and duration of mood episodes were compared between the CRM and non-CRM groups using a generalized linear model.

Results: The CRM group had 96.7% fewer total depressive episodes (n/year; exp β=0.033, P=.03), 99.5% shorter depressive episodes (total; exp β=0.005, P<.001), 96.1% shorter manic or hypomanic episodes (exp β=0.039, P<.001), 97.4% fewer total mood episodes (exp β=0.026, P=.008), and 98.9% shorter mood episodes (total; exp β=0.011, P<.001) than the non-CRM group. Positive changes in health behaviors due to the alerts and in wearable device adherence rates were observed in the CRM group.

Conclusions: The CRM app with a wearable activity tracker was found to be effective in preventing and reducing the recurrence of mood disorders, improving prognosis, and promoting better health behaviors. Patients appeared to develop a regular habit of using the CRM app.

Trial registration: ClinicalTrials.gov NCT03088657; https://ichgcp.net/clinical-trials-registry/NCT03088657.

Keywords: circadian rhythm; digital therapeutics; mood disorder; recurrence prevention; smartphone app; wearable activity tracker.

Conflict of interest statement

Conflicts of Interest: None declared.

©Chul-Hyun Cho, Taek Lee, Jung-Been Lee, Ju Yeon Seo, Hee-Jung Jee, Serhim Son, Hyonggin An, Leen Kim, Heon-Jeong Lee. Originally published in JMIR Mental Health (http://mental.jmir.org), 05.08.2020.

Figures

Figure 1

Comparison of the distributions of changes in individual features after receiving warning alerts in the CRM and non-CRM groups. The vertical axis refers to the delta of gradient change (DGC). If the median of the box plot (the green horizontal line inside the box) is near zero, this means that there was no significant change in the feature before and after the warning alert. If the median is greater than zero, this means that the feature value tended to increase after the alert. If it is less than zero, this means that the feature value tended to decrease after the alert. For example, if a patient with low activity during the day received a warning alert and the median of the distribution of the DGC value outcome for the feature steps_during_daytime moves in a positive direction, then we can assume that the patient tried to increase their activity. To compare the DGC distributions of the CRM group and non-CRM group for key features related to the H-score, DGCs were calculated based on each of the time points t at which alarms were activated during the experiment. The system logs for the warning alert calculations recorded the past feedback point t of the alert receivers. The actual warning alert was not delivered to the non-CRM group at time t but delivered only to the subjects in the CRM group at time t. In the comparison analysis, patients whose features could not be calculated due to a lack of data were omitted. CRM: Circadian Rhythm for Mood; KST: Kolmogorov-Smirnov test; MWT: Mann-Whitney U test.

Figure 2

Changes in the Fitbit wearing rate in the CRM and non-CRM groups. A moving average technique was used to report the trend lines by abbreviating the raw time series data (window size=6 days). The time unit on the horizontal axis is 30 days, which means that the number of total wearing hours for 30 days was measured and plotted at each time point. The thin solid lines on the top area are individual trend lines of the change in the Fitbit wearing rate of each patient, and the thick solid line is an average trend line of the individual lines. The lines in the bottom area are the standard deviation trend line (MSD) of the change in the wearing rate. Increasing moving average and decreasing MSD might be positive.