Accepted for/Published in: JMIR Research Protocols
Date Submitted: Apr 23, 2025
Date Accepted: Nov 19, 2025
Personalized Machine Learning Interventions to Improve Sleep Quality in Healthy Middle-Aged Mexico City Adults Using Wearable Technology: A Pilot Randomized Controlled Trial Protocol
ABSTRACT
Background:
Global sleep surveys reported in 2019 that 80% of adults want to improve their sleep quality, and in 2021, 45% were dissatisfied with their sleep. Domestic United States sleep surveys report in 2020 that 50% of all Americans are feeling sleepy throughout the day 3 times a week on average. In 2025, adults report 37% sleep dissatisfaction and 38% not energized after the sleep period. We need primary data acquisition and processing to measure our ability to improve the sleep quality score using technology for the healthy middle-aged active workforce adult population.
Objective:
This study aims to collect and process data for a single machine learning intervention to assess improvement in sleep quality score (target variable) in Mexico.
Methods:
This protocol outlines an experimental design with qualitative data from sleep surveys (Pittsburgh Sleep Quality Index) and quantitative data from off-the-shelf wearables (smartwatches) sensors. The target recruitment sample is an even number of 40 Mexican adults (between 30 and 60 years) without chronic sleep disorders. All participants will use the same wearable brand and model (Samsung Galaxy 4 [32]) for 60 days for sleep objective data input and fill out the Pittsburgh Sleep Quality Index (PSQI) questionnaire at the beginning, middle, and end for sleep subjective data input. Participants are assigned randomly and evenly to either the Control Group with no recommendations or the Experimental Group with recommendations from the machine learning models. The variable to manipulate in the research is the sleep quality score.
Results:
The study is currently in progress, and results will finish in December 2025 to (1) compare 1,200 nights from the control group with 1,200 nights from the experimental group to demonstrate enhanced sleep quality through machine learning and wearable technology; (2) generate a dataset from objective data for further analysis and model training; (3) correlate objective and subjective sleep quality metrics; and (4) set a framework for a proactive sleep quality approach.
Conclusions:
This study will provide valuable insights into the healthcare sector. By increasing middle-aged adults' capability to improve sleep quality, we can enhance their overall well-being by providing better mind and body rest.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.