Automated Assessment Tests with Depth Sensors in Older Adults

Mobility assessments are essential for understanding frailty in older adults, as they indicate mobility conditions and the likelihood of falls. Continuous assessments using automated systems allow us to detect mobility changes early and to improve mobility before severe events occur. In this study, we aim to automate the assessment tests using depth images. We present an automated Short Physical Performance Battery (SPPB) test using a depth sensor that captures older adults performing the SPPB test. Additionally, we discuss an automated Timed-Up-and-Go (TUG) test. We propose a method that identifies activities based on skeleton joints extracted from depth images and subsequently predicts the corresponding SPPB test scores. These scores serve as criteria for classifying older adults into high-risk, borderline, or not-at-risk for frailty. To achieve this, we collected 70 minutes of assessment data from 17 older outpatients at a long-term care facility. The proposed automated SPPB system achieved 98% MSE accuracy in predicting SPPB scores. Furthermore, automated prediction of TUG timing using an LSTM model achieved an MSE accuracy of 94%.Clinical relevance- The Short Physical Performance Battery (SPPB) and Timed-up-and-go (TUG) assessment scores are valuable clinical tools that help physicians evaluate a person's frailty level. These assessments can guide the implementation of targeted physiotherapy and mobility-enhancing training programs. Since motor function is a key indicator of various medical conditions, physicians can use the assessment test values to determine the necessity of further diagnostic tests, facilitating the early detection and management of underlying diseases.