A Method To Estimate Free-living Behaviors Using High-frequency Wrist Accelerometer Data: 633 May 27 1:30 PM - 1:45 PM

PURPOSE: To develop a novel method to estimate free-living sedentary behavior and activity intensity using high-frequency wrist accelerometer data. METHODS: Forty-nine participants (mean ± SD; age: 20.4±1.3 yrs, 45.8% male) completed four, 1-hour sessions of free-living behaviors in home, school, community, and exercise environments. Each session was video-recorded (DO) and participants wore an ActiGraph wGT3X-BT (AG) accelerometer on the non-dominant wrist. Videos were coded for whole body movement, contextual activity type, and activity intensity from the Compendium of Physical Activities (e.g. walking, shopping, 2.8 METs). The novel two-step method (SojWrist) first segments AG data into bouts, or “sojourns”, of inactivity (i.e. sedentary and standing behaviors) or activity using an acceleration standard deviation threshold and random forest model. The second step estimates the intensity of inactive (sedentary, light) and active (light, moderate, vigorous) sojourns. Separate inactive and active sojourn RF models were fit to estimate intensity using bout duration and time- and frequency-domain AG signal characteristics. A 90-10 sample split was used for SojWrist development (N = 44) and cross-validation (N=5). Percent agreement between DO and SojWrist was evaluated at each step using second-by-second data. RESULTS: In the cross-validation sample, 91.8% [95%CI: 87.0%, 96.5%] of inactive and active periods were classified correctly from step 1 of SojWrist. After step 2, overall percent agreement between DO and SojWrist was 86.9% [95%CI: 78.9%, 95.0%] across all intensity categories (Table). CONCLUSION: The new SojWrist performed well at estimating free-living activity intensity categories from a wrist worn accelerometer. Future work should strive to improve method performance for predicting activity intensity categories and test validity on a diverse, independent, free-living sample. Supported by NIH NIDDK 1R01DK110148