Adequate sleep is crucial for mood regulation and injury prevention in high school female athletes, yet insufficient sleep is prevalent in this demographic. This study aimed to evaluate the feasibility and preliminary effects of an AI-supported mobile health (mHealth) intervention that provided personalized sleep feedback to high school female soccer players.
The pilot randomized controlled trial involved 25 participants from a single soccer team. The study began with a briefing and system setup on August 18, 2025, and was registered with the University Hospital Medical Information Network on April 7, 2026. Participants were stratified by median baseline total sleep time and Pittsburgh Sleep Quality Index score, then randomly assigned to either the intervention group (n=12) or the control group (n=13).
During the intervention phase, which lasted from weeks 6 to 9, the intervention group received personalized feedback generated by GPT-4o via the LINE messaging application, based on their previous night’s sleep data collected from Fitbit devices. In contrast, the control group received nonpersonalized sleep information.
The primary outcome measured was sleep efficiency, while secondary outcomes included total sleep time (TST), wake after sleep onset (WASO), subjective sleep quality, sleep difficulty, and daytime sleepiness. Exploratory outcomes included mood state and sports injury severity.
Results indicated that all participants completed the trial successfully, with 100% message delivery success and questionnaire completion in both groups. The median valid Fitbit wear nights were higher in the intervention group (26 nights) compared to the control group (22 nights). Importantly, no major technical issues or adverse events were reported.
The primary efficacy outcome, sleep efficiency, showed a favorable change in the intervention group, with a Hodges-Lehmann between-group difference of 2% (95% CI 0.50%-4%; P=.046; r=0.35). Additionally, nominal differences were noted in the Pittsburgh Sleep Quality Index (PSQI-J) total score and sleep difficulty score, as well as exploratory outcomes related to REM sleep duration.
What this study does not show
While the study demonstrates feasibility and preliminary effects, it does not establish long-term benefits or health outcomes resulting from the AI-generated sleep feedback intervention.
Evidence scorecard
- Analytic validity: established
- Clinical validity: established
- Clinical utility: partial
This evidence is based on a human randomized controlled trial.