Evaluation of Falls Risk in Community-Dwelling Older Adults Using Body-Worn Sensors

摘要: Background: Falls are the most common cause of injury and hospitalization one principal causes death disability in older adults worldwide. This study aimed to determine if a method based on body-worn sensor data can prospectively predict falls community-dwelling adults, compare its prediction performance two standard methods same set. Methods: Data were acquired using sensors, mounted left right shanks, from 226 (mean age 71.5 ± 6.7 years, 164 female) quantify gait lower limb movement while performing 'Timed Up Go' (TUG) test geriatric research clinic. Participants contacted by telephone 2 years following their initial assessment they had fallen. These outcome used create statistical models falls. Results: Results obtained through cross-validation yielded mean classification accuracy 79.69% 95% CI: 77.09-82.34) identifying participants that fell during follow-up period. significantly (p Language: en