Better than counting seconds: Identifying fallers among healthy elderly using fusion of accelerometer features and dual-task Timed Up and Go

• Published in: PloS one Vol. 12; no. 4; p. e0175559
• Main Authors: Ponti, Moacir, Bet, Patricia, Oliveira, Caroline L, Castro, Paula C
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 27.04.2017; Public Library of Science (PLoS)
• Subjects: Accelerometers; Accelerometry - instrumentation; Accidental Falls - prevention & control; Aged; Biology and Life Sciences; Clinical trials; Cognitive ability; Cognitive tasks; Comparative analysis; Disability; Engineering and Technology; Epidemiology; Falls; Feature extraction; Female; Geriatrics; Gerontology; Health care; Humans; Identification; Long-term care; Male; Medicine and Health Sciences; Monitoring, Physiologic - instrumentation; Monitoring, Physiologic - methods; Older people; People and Places; Physical therapy; Postural Balance; Quantitative psychology; Segmentation; Sensors; Signal processing; Signal Processing, Computer-Assisted; Social Sciences; Society; Studies; Brazil
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0175559

Devices and sensors for identification of fallers can be used to implement actions to prevent falls and to allow the elderly to live an independent life while reducing the long-term care costs. In this study we aimed to investigate the accuracy of Timed Up and Go test, for fallers' identification, using fusion of features extracted from accelerometer data. Single and dual tasks TUG (manual and cognitive) were performed by a final sample (94% power) of 36 community dwelling healthy older persons (18 fallers paired with 18 non-fallers) while they wear a single triaxial accelerometer at waist with sampling rate of 200Hz. The segmentation of the TUG different trials and its comparative analysis allows to better discriminate fallers from non-fallers, while conventional functional tests fail to do so. In addition, we show that the fusion of features improve the discrimination power, achieving AUC of 0.84 (Sensitivity = Specificity = 0.83, 95% CI 0.62-0.91), and demonstrating the clinical relevance of the study. We concluded that features extracted from segmented TUG trials acquired with dual tasks has potential to improve performance when identifying fallers via accelerometer sensors, which can improve TUG accuracy for clinical and epidemiological applications.