Skip to main content

Table 3 Comparison of classification results of different models (mean ± std)

From: Study on risk factors of diabetic peripheral neuropathy and establishment of a prediction model by machine learning

Algorithm

Accuracy

Precision

Recall

F1-score

LR

0·679 ± 0·052

0·687 ± 0·056

0·659 ± 0·062

0·672 ± 0·056

KNN

0·674 ± 0·039

0·858 ± 0·070

0·419 ± 0·073

0·559 ± 0·070

DT

0·682 ± 0.032

0·695 ± 0.032

0·648 ± 0·067

0·669 ± 0·042

NB

0·590 ± 0·029

0·784 ± 0·087

0·253 ± 0·061

0·378 ± 0·071

RF

0·736 ± 0·021

0·769 ± 0·026

0·677 ± 0·040

0·719 ± 0·027

XGBoost

0·746 ± 0·041

0·765 ± 0·040

0·711 ± 0·066

0·736 ± 0·050

  1. The best results are in bold
  2. XGBoost Extreme Gradient Boosting, NB Naive Bayes, LR Logistic Regression, KNN K-Nearest-Neighbor, RF Random Forest, DT Decision Tree
Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us