Abstract

Background: Japan has the highest proportion of older adults in the world, and is a so-called “super-aged society”. This suggests a prevalence of both cognitive and physical functional impairment and depression that affect quality of life (QOL) with age. Extending healthy life expectancy and reducing health disparities are global issues.
Methods: A total of 155 healthy adults age ≥65 years were included in the study, taken from among adult day-care center clients. From 5 baseline demographics datasets (age, sex, body mass index (BMI), percent of body fat (%Fat) and serum 25OHD (VitD)), we predicted Mini Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCAJ) levels, World Health Oganization quality of life (WHQOL), grip strength and skeletal muscle index (SMI) using a deep learning framework TensorFlow (prediction system). The deep learning model consists of 3 multi-overarching layers: the input, middle, and output layers. The input layer consisted of the above 5 baseline demographics datasets, and the output layer was 1 of the 5 prediction features. The number of neuron units in the first and second middle layers was 18 and 9, respectively. The output vectors in the middle layer were converted by the rectified linear unit (ReLU) function. The modes of MMSE, MoCAJ, and grip strength were decided according to medical criteria using minimal clinically important differences and the range of the correct answers was <3.0, <2.0 and 6.0 respectively. The range of correct answers in SMI (<1.0) and WHQOL (<0.6) was decided first.
Results: Our system achieved an accuracy rate of more than 70%. SMI was correctly predicted in 92.1% of test cases; MMSE was correctly predicted in 78.9% of test cases.
Conclusion: Our results indicate that deep learning techniques can effectively predict cognitive and physical function, muscle weight and QOL. This algorithm could serve as a tool to aid nurses in clinical decision‐making processes.