Accepted for/Published in: JMIR Formative Research
Date Submitted: Feb 28, 2024
Date Accepted: Dec 9, 2024
AI Machine Learning based Diabetes Prediction in the Elderly Population in South Korea: a Cross-Sectional Analysis
ABSTRACT
Background:
Diabetes mellitus (DM) is prevalent in older adults. While machine learning (ML) algorithms could help predict DM in older adults.
Objective:
This study determined DM risk factors among older adults aged ≥60 years using ML algorithms and selected an optimized model.
Methods:
Overall, 3,084 Korean older adults aged >60 years were recruited.
Results:
Hypertension, age, heart rate, hyperlipidemia, BMR, stress, and oxygen saturation were found to be important features that predict DM. Thus, these were included in the ML model for DM prediction. Five different ML algorithms were evaluated based on accuracy, precision, recall, F-score, and area under the curve, and the X Gradient Boosting Model was found to have the best performance. These results contribute to the understanding of obesity as a risk factor for DM as no significant differences were found in DM risk according to percent body fat.
Conclusions:
This study focused on modifiable risk factors, providing crucial data for establishing a system for the automated collection of health information and life log data from older adults using digital devices at service facilities frequented by older adults.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.