89 Predictors of variability in Apple Watch step count data from a 3-year prospective cohort

Abstract

Objectives/Goals: Physical activity (PA) is a well-documented protective factor against many cardiovascular diseases. PA guidelines to reduce these risks and the impact of variability are unclear, and most studies only examine a 7-day activity window. This study aimed to examine factors related to variability in step counts in a 3-year study of adults aged ≥18 years. Methods/Study Population: Included were 6,525 participants from the Michigan Predictive Ability and Clinical Trajectories study, a prospective cohort of community-dwelling adults enrolled between 8/14/2018 and 12/19/2019 who received care at Michigan Medicine and were followed for 3 years. Data were collected from Apple Watches provided to participants via the HealthKit. This secondary analysis included those with ≥4 valid weeks of data (≥4 days with at least 8 hours of wear time). Season was defined as Spring (March 20–June 20), Summer (June 21–September 21), Fall (September 22–December 20), and Winter (December 21–March 19). GEE models against the outcome of variability, defined as weekly standard deviation of step counts, and the predictor of season were adjusted for age, sex, race/ethnicity, weekly average step count, diabetes, and body mass index. Results/Anticipated Results: The average (standard deviation (SD) step counts by season were 7101 (3434) in Spring, 7263 (3354) in Summer, 6863 (3236) in Fall, and 6555 (3211) in Winter. Compared to winter, there was statistically significantly higher variability in all other seasons (p Discussion/Significance of Impact: In this cohort of community-dwelling adults, we found significant differences in variability of physical activity by season, age, and BMI. Future work will examine how this variability impacts the risk of development of cardiovascular disease, incorporating the impact and recovery trajectories of COVID-19 and other acute respiratory infections.