Related Experiment Video
Updated: Oct 2, 2025
07:15
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
7.0K
Development of a Risk Model for Predicting Microalbuminuria in the Chinese Population Using Machine Learning
Wei Lin1, Songchang Shi2, Huibin Huang1
1Department of Endocrinology, Shengli Clinical Medical College of Fujian Medical University, Fujian Provincial Hospital, Fuzhou, China.
Frontiers in Medicine
|February 24, 2022
Summary
Machine learning identified key factors for microalbuminuria (MAU) risk. Early screening using systolic blood pressure, diastolic blood pressure, fasting blood glucose, triglycerides, age, sex, and smoking can predict cardiovascular events.
Area of Science:
- Nephrology
- Cardiology
- Data Science
Background:
- Microalbuminuria (MAU) signifies endothelial damage, a precursor to kidney disease and cardiovascular events.
- Early identification of high-risk individuals for MAU is crucial for preventing cardiovascular mortality.
Purpose of the Study:
- To develop a predictive risk model for microalbuminuria (MAU) using machine learning algorithms.
- To identify key clinical and demographic factors associated with MAU prevalence.
Main Methods:
- A cross-sectional study of 3,294 participants analyzed using R software.
- Machine learning algorithms were employed to construct and validate risk prediction models.
- Variables with P <0.05 in the second-stage model were identified as significant predictors.
Main Results:
- Key predictors of MAU included systolic blood pressure, diastolic blood pressure, fasting blood glucose, triglyceride levels, sex, age, and smoking.
- Model validation using chi-square tests, confusion matrices, and calibration curves confirmed the predictability of MAU risk.
- A risk score was successfully established based on these identified predictors.
Conclusions:
- The study demonstrates the efficacy of machine learning in creating a reliable MAU risk score.
- Comprehensive assessment of identified factors (SBP, DBP, FBG, TG, gender, age, smoking) is recommended for MAU screening.
- This approach aids in early detection and management of individuals at risk for cardiovascular complications.
