Adequate sleep is crucial for mood regulation and injury prevention in high school female athletes, yet many in this population experience insufficient sleep. This study, published in JMIR Formative Research, explores the feasibility and preliminary effects of an AI-supported mobile health intervention that provides personalized sleep feedback to high school female soccer players.
Study Overview
The pilot randomized controlled trial involved 25 high school female soccer players from a single team. The study aimed to evaluate the technical and operational feasibility of delivering personalized sleep feedback based on daily sleep data collected via wearable devices. The primary efficacy outcome was sleep efficiency, while secondary outcomes included total sleep time (TST), wake after sleep onset (WASO), subjective sleep quality, and daytime sleepiness.
Participants were randomly allocated to either the intervention group, which received AI-generated feedback, or a control group that received non-personalized sleep information. The trial was conducted over several weeks, with the baseline period followed by the intervention phase.
Results
All 25 participants completed the trial, demonstrating high engagement with a 100% message delivery success rate and questionnaire completion. The intervention group had a median of 26 valid Fitbit wear nights compared to 22 in the control group. Notably, the change in sleep efficiency favored 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 observed in the Pittsburgh Sleep Quality Index (PSQI-J) total score and sleep difficulty score, as well as exploratory outcomes like REM sleep duration. These findings suggest that the AI-generated feedback may have a positive impact on sleep efficiency and related sleep metrics.
What this study does not show
While the study indicates feasibility and preliminary effects, it does not establish long-term benefits or health outcomes resulting from improved sleep efficiency or personalized feedback.
Evidence scorecard
- Analytic validity: Established
- Clinical validity: Established
- Clinical utility: Partial
The evidence class is human_rct, indicating that the study was a randomized controlled trial involving human participants.