Figures & data
Figure 1 (A) Workflow of the study; (B) Flowchart of patient selection.
![Figure 1 (A) Workflow of the study; (B) Flowchart of patient selection.](/cms/asset/2c8b0e11-fe5f-4856-809a-5bad16704d3e/dmso_a_383960_f0001_c.jpg)
Table 1 Differences Between Demographic and Clinical Characteristics of Healed and Hard-to-Heal Groups
Table 2 Prediction Factors for Hard-to-Heal in DFUs
Figure 2 Confusion matrix of the risk prediction models with machine learning algorithms. (A) AdaBoost: adaptive boosting; (B) GLM: general linear regression; (C) KNN: k-nearest neighbor; (D) NB: naïve Bayes; (E) RF: random forest; (F) SVM: support vector machine.
![Figure 2 Confusion matrix of the risk prediction models with machine learning algorithms. (A) AdaBoost: adaptive boosting; (B) GLM: general linear regression; (C) KNN: k-nearest neighbor; (D) NB: naïve Bayes; (E) RF: random forest; (F) SVM: support vector machine.](/cms/asset/c32126ec-685d-46e3-96e5-7b4e775b0576/dmso_a_383960_f0002_c.jpg)
Table 3 The Comparisons of Machine Learning Algorithms
Figure 3 ROC curves for predicting hard-to-heal in DFU patients with machine learning algorithms.
![Figure 3 ROC curves for predicting hard-to-heal in DFU patients with machine learning algorithms.](/cms/asset/cbeb1cdb-686a-43fd-90a0-9c6854726da1/dmso_a_383960_f0003_c.jpg)