AI Machine Learning–Based Diabetes Prediction in Older Adults in South Korea: Cross-Sectional Analysis
Abstract BackgroundDiabetes is prevalent in older adults, and machine learning algorithms could help predict diabetes in this population. ObjectiveThis study determined diabetes risk factors among older adults aged ≥60 years using machine learning algorithms and se...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2025-01-01
|
| Series: | JMIR Formative Research |
| Online Access: | https://formative.jmir.org/2025/1/e57874 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832583219227131904 |
|---|---|
| author | Hocheol Lee Myung-Bae Park Young-Joo Won |
| author_facet | Hocheol Lee Myung-Bae Park Young-Joo Won |
| author_sort | Hocheol Lee |
| collection | DOAJ |
| description |
Abstract
BackgroundDiabetes is prevalent in older adults, and machine learning algorithms could help predict diabetes in this population.
ObjectiveThis study determined diabetes risk factors among older adults aged ≥60 years using machine learning algorithms and selected an optimized prediction model.
MethodsThis cross-sectional study was conducted on 3084 older adults aged ≥60 years in Seoul from January to November 2023. Data were collected using a mobile app (Gosufit) that measured depression, stress, anxiety, basal metabolic rate, oxygen saturation, heart rate, and average daily step count. Health coordinators recorded data on diabetes, hypertension, hyperlipidemia, chronic obstructive pulmonary disease, percent body fat, and percent muscle. The presence of diabetes was the target variable, with various health indicators as predictors. Machine learning algorithms, including random forest, gradient boosting model, light gradient boosting model, extreme gradient boosting model, and k-nearest neighbors, were employed for analysis. The dataset was split into 70% training and 30% testing sets. Model performance was evaluated using accuracy, precision, recall, F1 score, and area under the curve (AUC). Shapley additive explanations (SHAPs) were used for model interpretability.
ResultsSignificant predictors of diabetes included hypertension (χ1Pχ1Pt3082Pt3082P
ConclusionsThis study focused on modifiable risk factors, providing crucial data for establishing a system for the automated collection of health information and lifelog data from older adults using digital devices at service facilities. |
| format | Article |
| id | doaj-art-3f3d122bc1b646599c677ad8c845fcec |
| institution | Kabale University |
| issn | 2561-326X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Formative Research |
| spelling | doaj-art-3f3d122bc1b646599c677ad8c845fcec2025-01-28T20:31:18ZengJMIR PublicationsJMIR Formative Research2561-326X2025-01-019e57874e5787410.2196/57874AI Machine Learning–Based Diabetes Prediction in Older Adults in South Korea: Cross-Sectional AnalysisHocheol Leehttp://orcid.org/0000-0003-1467-8843Myung-Bae Parkhttp://orcid.org/0000-0002-1892-6632Young-Joo Wonhttp://orcid.org/0000-0001-9861-6740 Abstract BackgroundDiabetes is prevalent in older adults, and machine learning algorithms could help predict diabetes in this population. ObjectiveThis study determined diabetes risk factors among older adults aged ≥60 years using machine learning algorithms and selected an optimized prediction model. MethodsThis cross-sectional study was conducted on 3084 older adults aged ≥60 years in Seoul from January to November 2023. Data were collected using a mobile app (Gosufit) that measured depression, stress, anxiety, basal metabolic rate, oxygen saturation, heart rate, and average daily step count. Health coordinators recorded data on diabetes, hypertension, hyperlipidemia, chronic obstructive pulmonary disease, percent body fat, and percent muscle. The presence of diabetes was the target variable, with various health indicators as predictors. Machine learning algorithms, including random forest, gradient boosting model, light gradient boosting model, extreme gradient boosting model, and k-nearest neighbors, were employed for analysis. The dataset was split into 70% training and 30% testing sets. Model performance was evaluated using accuracy, precision, recall, F1 score, and area under the curve (AUC). Shapley additive explanations (SHAPs) were used for model interpretability. ResultsSignificant predictors of diabetes included hypertension (χ1Pχ1Pt3082Pt3082P ConclusionsThis study focused on modifiable risk factors, providing crucial data for establishing a system for the automated collection of health information and lifelog data from older adults using digital devices at service facilities.https://formative.jmir.org/2025/1/e57874 |
| spellingShingle | Hocheol Lee Myung-Bae Park Young-Joo Won AI Machine Learning–Based Diabetes Prediction in Older Adults in South Korea: Cross-Sectional Analysis JMIR Formative Research |
| title | AI Machine Learning–Based Diabetes Prediction in Older Adults in South Korea: Cross-Sectional Analysis |
| title_full | AI Machine Learning–Based Diabetes Prediction in Older Adults in South Korea: Cross-Sectional Analysis |
| title_fullStr | AI Machine Learning–Based Diabetes Prediction in Older Adults in South Korea: Cross-Sectional Analysis |
| title_full_unstemmed | AI Machine Learning–Based Diabetes Prediction in Older Adults in South Korea: Cross-Sectional Analysis |
| title_short | AI Machine Learning–Based Diabetes Prediction in Older Adults in South Korea: Cross-Sectional Analysis |
| title_sort | ai machine learning based diabetes prediction in older adults in south korea cross sectional analysis |
| url | https://formative.jmir.org/2025/1/e57874 |
| work_keys_str_mv | AT hocheollee aimachinelearningbaseddiabetespredictioninolderadultsinsouthkoreacrosssectionalanalysis AT myungbaepark aimachinelearningbaseddiabetespredictioninolderadultsinsouthkoreacrosssectionalanalysis AT youngjoowon aimachinelearningbaseddiabetespredictioninolderadultsinsouthkoreacrosssectionalanalysis |