Predicting Sarcopenia of Female Elderly from Physical Activity Performance Measurement Using Machine Learning Classifiers

• Published in: Clinical interventions in aging Vol. 16; pp. 1723 - 1733
• Main Authors: Ko, Jeong Bae, Kim, Kwang Bok, Shin, Young Sub, Han, Hun, Han, Sang Kuy, Jung, Duk Young, Hong, Jae Soo
• Format: Journal Article
• Language: English
• Published: New Zealand Dove Medical Press Limited 01.01.2021; Taylor & Francis Ltd; Dove; Dove Medical Press
• Subjects: Accelerometers; Activities of daily living; Aged; Aged women; Aged, 80 and over; Bioethics; Data collection; Exercise; Experiments; Female; Frailty; Geriatric assessment; Health aspects; Humans; inertial measurement unit; Machine Learning; Medical research; Methods; Muscle strength; Musculoskeletal system; Older people; Original Research; physical activity; Postural Balance; Risk factors; Sarcopenia; Sarcopenia - diagnosis; Time and Motion Studies; Velocity; Vertebrae; Walking; Women's fitness; Womens health; Working groups; South Korea; United States > US; inertial measurement unit; machine learning; physical activity; sarcopenia
• ISSN: 1178-1998; 1176-9092; 1178-1998
• DOI: 10.2147/CIA.S323761

Sarcopenia is a symptom in which muscle mass decreases due to decreasing in the number of muscle fibers and muscle cross-sectional area as aging. This study aimed to develop a machine learning classification model for predicting sarcopenia through a inertial measurement unit (IMU)-based physical performance measurement data of female elderly. Seventy-eight female subjects from an elderly population (aged: 78.8±5.7 years) volunteered to participate in this study. To evaluate the physical performance of the elderly, the experiment conducted timed-up-and-go test (TUG) and 6-minute walk test (6mWT) with worn a single IMU. Based on literature review, 132 features were extracted from collected data. Feature selection was performed through the Kruskal-Wallis test, and features datasets were constructed according to feature selection. Three major machine learning-based classification algorithms classified the sarcopenia group in each dataset, and the performance of classification models was compared. As a result of comparing the classification model performance for sarcopenia prediction, the k-nearest neighborhood algorithm (kNN) classification model using 40 major features of TUG and 6mWT showed the best performance at 88%. This study can be used as a basic research for the development of self-monitoring technology for sarcopenia.