Are Machine Learning Models on Wrist Accelerometry Robust against Differences in Physical Performance among Older Adults?

Sensors

Ramon Casanova¹  Santiago Saldana¹  Amal A. Wanigatunga²  Todd M. Manini³  Chen Bai³  Mamoun T. Mardini³ 

[1] Department of Biostatistics and Data Science, School of Medicine, Wake Forest University, Winston-Salem, NC 27101, USA;Department of Epidemiology, Bloomberg School of Public Health, Johns Hopkins University, Baltimore, MD 21205, USA;Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL 32610, USA;

关键词: wrist;    accelerometer;    short physical performance battery;    physical activity;    energy expenditure;    eXtreme Gradient Boosting;   

DOI  :  10.3390/s22083061

来源: DOAJ

【 摘 要 】

Sufficient physical activity (PA) reduces the risk of a myriad of diseases and preserves physical capabilities in later life. While there have been significant achievements in mapping accelerations to real-life movements using machine learning (ML), errors continue to be common, particularly for wrist-worn devices. It remains unknown whether ML models are robust for estimating age-related loss of physical function. In this study, we evaluated the performance of ML models (XGBoost and LASSO) to estimate the hallmark measures of PA in low physical performance (LPP) and high physical performance (HPP) groups. Our models were built to recognize PA types and intensities, identify each individual activity, and estimate energy expenditure (EE) using wrist-worn accelerometer data (33 activities per participant) from a large sample of participants (n = 247, 57% females, aged 60+ years). Results indicated that the ML models were accurate in recognizing PA by type and intensity while also estimating EE accurately. However, the models built to recognize individual activities were less robust. Across all tasks, XGBoost outperformed LASSO. XGBoost obtained F1-Scores for sedentary (0.932 $\pm$ 0.005), locomotion (0.946 $\pm$ 0.003), lifestyle (0.927 $\pm$ 0.006), and strength flexibility exercise (0.915 $\pm$ 0.017) activity type recognition tasks. The F1-Scores for recognizing low, light, and moderate activity intensity were (0.932$\pm$0.005), (0.840 $\pm$ 0.004), and (0.869 $\pm$ 0.005), respectively. The root mean square error for EE estimation was 0.836 $\pm$ 0.059 METs. There was no evidence showing that splitting the participants into the LPP and HPP groups improved the models’ performance on estimating the hallmark measures of physical activities. In conclusion, using features derived from wrist-worn accelerometer data, machine learning models can accurately recognize PA types and intensities and estimate EE for older adults with high and low physical function.

【 授权许可】

Unknown