A Deep Learning Approach for TUG and SPPB Score Prediction of (Pre-) Frail Older Adults on Real-Life IMU Data

Björn Friedrich; Sandra Lau; Lena Elgert; Jürgen M Bauer; Andreas Hein

doi:10.3390/healthcare9020149

A Deep Learning Approach for TUG and SPPB Score Prediction of (Pre-) Frail Older Adults on Real-Life IMU Data

Healthcare (Basel). 2021 Feb 2;9(2):149. doi: 10.3390/healthcare9020149.

Authors

Björn Friedrich¹, Sandra Lau², Lena Elgert³, Jürgen M Bauer⁴, Andreas Hein¹

Affiliations

¹ Assistance Systems and Medical Device Technology, Carl von Ossietzky University, Ammerländer Heerstraße 114-118, 26129 Oldenburg, Germany.
² Geriatric Medicine, Carl von Ossietzky University, Ammerländer Heerstraße 114-118, 26129 Oldenburg, Germany.
³ Peter L. Reichertz Institute for Medical Informatics of TU Braunschweig and Hannover Medical School, Carl-Neuberg-Straße 1, 30625 Hannover, Germany.
⁴ Center for Geriatric Medicine, Agaplesion Bethanien Krankenhaus, University of Heidelberg, Rohrbacher Straße 149, 69117 Heidelberg, Germany.

Abstract

Since older adults are prone to functional decline, using Inertial-Measurement-Units (IMU) for mobility assessment score prediction gives valuable information to physicians to diagnose changes in mobility and physical performance at an early stage and increases the chances of rehabilitation. This research introduces an approach for predicting the score of the Timed Up & Go test and Short-Physical-Performance-Battery assessment using IMU data and deep neural networks. The approach is validated on real-world data of a cohort of 20 frail or (pre-) frail older adults of an average of 84.7 years. The deep neural networks achieve an accuracy of about 95% for both tests for participants known by the network.

Keywords: decision support; frail; machine learning; mobility assessments; older adults; pre-frail; supervised learning.