Related Experiment Video
Updated: May 7, 2026
12:18
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
7.4K
Gender Differences in Predicting Metabolic Syndrome Among Hospital Employees Using Machine Learning Models: A
Yi-Syuan Wu1, Wen-Chii Tzeng2, Cheng-Wei Wu3
1Department of Computer Science and Information Engineering, National Taitung University, Taitung, Taiwan.
The Journal of Nursing Research : JNR
|March 31, 2025
Summary
Machine learning accurately predicts metabolic syndrome (MetS) in hospital employees. The Naïve Bayes model, considering gender differences, improves early risk identification for better cardiovascular health outcomes.
Area of Science:
- Health Informatics
- Machine Learning in Healthcare
- Preventive Cardiology
Background:
- Metabolic syndrome (MetS) is a cluster of conditions including obesity, high blood glucose, dyslipidemia, and hypertension.
- Early prediction of MetS risk, especially considering gender-specific factors, can improve cardiovascular health outcomes in hospital employees.
Purpose of the Study:
- To develop and optimize a machine learning model for predicting MetS risk in hospital employees.
- To investigate gender-specific differences in MetS prediction.
Main Methods:
- A population-based survey of 3,537 hospital employees (aged 20-65) from 2018-2020.
- Data included demographics, anthropometrics, medical history, lifestyle, and biochemical markers.
- Six machine learning models (K-NN, Random Forest, Logistic Regression, SVM, Neural Network, Naïve Bayes) were employed and evaluated.
Main Results:
- MetS prevalence was 8.91%.
- The Naïve Bayes model demonstrated superior performance (sensitivity 0.825, accuracy 0.859, AUC 0.936).
- Key predictors included BMI and ALT (both genders), with gender-specific factors like age, uric acid, AST (men), and chronic disease, phosphorus (women).
Conclusions:
- The Naïve Bayes model is effective for gender-independent MetS prediction in hospital employees.
- Integrating gender-specific factors into MetS prediction models is crucial for routine health screening and cardiovascular disease prevention.
