Adequate sleep is crucial for mood regulation and injury prevention, particularly in high school female athletes. However, many in this demographic experience insufficient sleep. This study aimed to assess the feasibility and preliminary effects of an AI-supported mobile health (mHealth) intervention that provided personalized sleep feedback based on data from wearable devices.
Study Overview
The pilot randomized controlled trial involved 25 high school female soccer players from a single team. Participants were randomly assigned to either an intervention group, which received AI-generated personalized sleep feedback, or a control group, which received nonpersonalized sleep information. The study was conducted over a period of several weeks, with the intervention group receiving feedback based on data from Fitbit devices.
Methods
The trial began with a baseline period of four weeks, followed by random allocation to the two groups. The intervention group received personalized feedback via the LINE messaging app, while the control group received generic sleep information. The primary outcome measured was sleep efficiency, with secondary outcomes including total sleep time (TST), wake after sleep onset (WASO), subjective sleep quality, and daytime sleepiness.
Results
All participants completed the trial, demonstrating high rates of message delivery success and questionnaire completion (100% in both groups). The median valid Fitbit wear nights were 26 for the intervention group and 22 for the control group. Notably, the intervention group showed a favorable change in sleep efficiency, with a Hodges-Lehmann between-group difference of 2% (95% CI 0.50%-4%; P=.046; r=0.35). Additionally, nominal differences were observed in the Pittsburgh Sleep Quality Index (PSQI-J) total score and sleep difficulty score.
Discussion
This study indicates that an AI-generated personalized sleep feedback intervention is feasible and may improve sleep efficiency among high school female soccer players. The absence of major technical issues or adverse events further supports the viability of using AI in sleep interventions for athletes.
What this study does not show
While the study indicates preliminary efficacy in sleep efficiency, it does not establish long-term benefits or impacts on athletic performance or injury rates.
Evidence scorecard
- Analytic validity: established
- Clinical validity: established
- Clinical utility: partial
The evidence class is human_rct, supporting the feasibility and preliminary effects of the intervention.