hs-CRP is strongly associated with coronary heart disease (CHD): A data mining approach using decision tree algorithm

Area of Science:

• Cardiology
• Data Mining
• Public Health

Background:

• Coronary heart disease (CHD) poses a significant global health challenge.
• Predictive algorithms integrating clinical biomarkers and traditional risk factors aid CHD detection and intervention.
• Decision tree (DT) models offer a data mining approach for uncovering hidden patterns in large datasets.

Purpose of the Study:

• To develop a predictive model for coronary heart disease (CHD) utilizing a decision tree (DT) algorithm.
• To identify key risk factors associated with CHD using data mining techniques.

Main Methods:

• A dataset of 2346 individuals (1159 healthy, 1187 with coronary angiography) was analyzed.
• Ten variables including age, sex, FBG, TG, hs-CRP, TC, HDL, LDL, SBP, and DBP were input into the DT algorithm.

Main Results:

• The DT model achieved high performance metrics: 96% sensitivity, 87% specificity, and 94% accuracy in identifying CHD.
• Serum hs-CRP levels emerged as the most significant predictor, followed by FBG, gender, and age.

Conclusions:

• The developed DT model demonstrates high accuracy, specificity, and sensitivity for CHD prediction.
• Further validation in prospective studies is recommended to confirm the model's clinical utility.