Skip to main content
Fig. 3 | BMC Medical Informatics and Decision Making

Fig. 3

From: Predicting polypharmacy in half a million adults in the Iranian population: comparison of machine learning algorithms

Fig. 3

Top 10 variable importance (VIMP) values for predicting polypharmacy in Khuzestan residence patients using: A mean decrease in classification accuracy (MDA) or B mean decrease in classification Gini impurity (MDG); C The error rate of the RF model (OOB: out of bag, 0: Non-polypharmacy, and 1: Polypharmacy); D Confusion matrix performance metrics. The results was an average of 100 runs of RF. NOP: Number of prescriptions; ICPD: Insurance coverage for prescription drugs; NCD’s: Non-communicable diseases; DM: Diabetes mellitus; HTN: Hypertension; CVD: Cardiovascular diseases

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us