Fig 1.
Study design flowchart and data screening flowchart.
(A) Study design flowchart; (B) Data screening flowchart. Abbreviations: DFU, diabetic foot ulcer; DT, decision tree; LR, logistic regression; RF, random forest; SMOTE, synthetic minority oversampling technique; SVM, support vector machine; XGBoost, extreme gradient boosting.
Table 1.
Calculation formulae for the evaluation indicators of the model.
Table 2.
Results of univariate analysis of minor amputation for diabetic foot ulcer patients.
Table 3.
Data distribution of both the training set and validation set before and after SMOTE.
Fig 2.
Confusion matrix of the risk prediction models with machine learning algorithms.
(A) DT: decision tree. (B) RF: random forest. (C) LR: logistic regression. (D) SVM: support vector machine. (E) XGBoost: extreme gradient boosting.
Fig 3.
Performance comparisons of machine learning algorithms after over-sampling.
Abbreviations: DT, Decision Tree; RF, Random Forest; LR, Logistic Regression; SVM, Support Vector Machine; XGBoost, extreme gradient boosting; AUC, area under the curve.
Fig 4.
ROC curves for predicting minor amputation in DFU patients with machine learning algorithms after over-sampling.
Abbreviations: ROC, receiver operating characteristic curve; DFU, diabetic foot ulcers; DT, decision tree; RF, random forest; LR, logistic regression; SVM, support vector machine; XGBoost, extreme gradient boosting; FPR, false positive rate; TPR, true positive rate.
Table 4.
Performance parameter values for five machine learning algorithms before and after over-sampling.
Fig 5.
Feature importance ranking of the included feature of the XGBoost model.
Abbreviations: XGBoost, extreme gradient boosting.