Potential sources of inaccuracy in the Apple watch series 4 energy expenditure estimation algorithm during wheelchair propulsion

Abstract

Background The Apple Watch (AW) was the frst smartwatch to provide wheelchair user (WCU) specifc information on energy expenditure (EE), but was found to be inaccurate (i.e., it underestimated) and imprecise (i.e., the underestimation was variable). Insight is therefore needed into where these inaccuracies/imprecisions originate. Accordingly, the aim of this study was to investigate how much of the variation in AW EE is explained by heart rate (HR), in addition to other factors such as body mass and height, sex, age, physical activity level and disability.

Methods Forty participants (20 WCU, 20 non-disabled) performed three 4-min treadmill wheelchair propulsion stages at diferent speed-incline combinations, on three separate days, while wearing an AW series 4 (setting: “outdoor push walking pace”). Linear mixed model analyses investigated how much of the variation in AW EE (kcal·min−1) is explained by the fxed efects AW HR (beats·min−1), body mass and height, sex, age, physical activity level and disability. Participant-ID was included as random-intercept efect. The same mixed model analyses were conducted for criterion EE and HR. Marginal R2 (R2 m; fxed efects only) and conditional R2 (R2 c; fxed and random efects) values were computed. An R2 m close to zero indicates that the fxed efects alone do not explain much variation.

Results Although criterion HR explained a signifcant amount of variation in criterion EE (R2 m: 0.44, R2 c: 0.92, p<0.001), AW HR explained little variation in AW EE (R2 m: 0.06, R2 c: 0.86, p<0.001). In contrast, body mass and sex explained a signifcant amount of variation in AW EE (R2 m: 0.74, R2 c: 0.79, p<0.001). No further improvements in ft were achieved by adding body height, age, physical activity level or disability to the AW EE model (R2 m: 0.75, R2 c: 0.79, p=0.659).

Conclusion Our results remain inconclusive on whether AW heart rate is used as factor to adjust for exercise intensity in the black box AW EE estimation algorithms. In contrast, body mass explained much of the variation in AW EE, indicating that the AW EE estimation algorithm is very reliant on this factor. Future investigations should explore better individualization of EE estimation algorithms.