AI Machine Learning-Based Diabetes Prediction in Older Adults in South Korea: Cross-Sectional Analysis
Hocheol Lee1, Myung-Bae Park1, Young-Joo Won1
11, Department of Health Administration, College of Software and Digital Healthcare Convergence, Yonsei University, Changjogwan, Yonseidae-gil 1, Wonju, 26493, Republic of Korea, +82 (0) 33-760-2257.
JMIR Formative Research
|January 22, 2025
Summary
Machine learning accurately predicts diabetes in older adults, identifying hypertension, age, and stress as key risk factors. This aids in developing targeted interventions for diabetes prevention and management in this population.
Area of Science:
- Gerontology
- Computational Medicine
- Public Health
Background:
- Diabetes is a significant health concern for older adults.
- Machine learning offers potential for predicting diabetes in this demographic.
Purpose of the Study:
- To identify diabetes risk factors in adults aged 60 and above using machine learning.
- To develop and optimize a predictive model for diabetes in older adults.
Main Methods:
- A cross-sectional study of 3084 older adults in Seoul.
- Data collected via mobile app and health coordinators, including lifestyle and clinical factors.
- Analysis using multiple machine learning algorithms (Random Forest, GBM, LGBM, XGBM, KNN) with SHAP for interpretability.
Main Results:
- Hypertension, hyperlipidemia, age, stress, and heart rate were significant diabetes predictors.
- The Extreme Gradient Boosting Model (XGBM) achieved the highest performance (84.88% accuracy, 0.7957 AUC).
- SHAP analysis identified hypertension, age, body fat, heart rate, hyperlipidemia, BMR, stress, and oxygen saturation as key predictors.
Conclusions:
- The study highlights modifiable risk factors for diabetes in older adults.
- Findings support the development of automated health data collection systems for proactive care.
- Machine learning models provide valuable insights for diabetes risk stratification and intervention.
Related Concept Videos
01:15Diabetes: Symptoms, Diagnosis, and Complications
500
For most patients, experiencing several weeks of polyuria, polydipsia, fatigue, and significant weight loss may indicate the presence of diabetes. Furthermore, adults displaying the phenotypic appearance of type 2 diabetes (particularly those who are obese and not initially insulin-requiring), may have islet cell autoantibodies, suggesting autoimmune-mediated β cell destruction and a diagnosis of latent autoimmune diabetes of adults (LADA). The categorization of glucose homeostasis is...
500
01:22Diabetes Mellitus: Type 2 and Gestational
2.2K
Type 2 diabetes, characterized by insulin resistance, arises when the insulin receptors on cells lose responsiveness to insulin, diminishing the cell's capacity to take up glucose, resulting in elevated blood glucose levels. To receive a diagnosis of Type 2 diabetes, a series of blood glucose tests are necessary to assess whether the blood glucose falls within normal parameters. If the result is out of the normal range, a patient may be diagnosed as prediabetic or diabetic, depending on the...
2.2K
01:22Diabetes Mellitus: Overview and Type I Subtype
2.4K
Diabetes mellitus is a chronic metabolic disorder characterized by high blood glucose levels due to inadequate insulin production, insulin resistance, or both. The condition affects millions worldwide and can significantly impact their health and quality of life.
Type 1 diabetes is an autoimmune disease in which the immune system mistakenly attacks and destroys the insulin-producing beta cells in the pancreas. As a result, the body is unable to produce sufficient insulin, and individuals with...
Type 1 diabetes is an autoimmune disease in which the immune system mistakenly attacks and destroys the insulin-producing beta cells in the pancreas. As a result, the body is unable to produce sufficient insulin, and individuals with...
2.4K