Machine learning algorithm to evaluate risk factors of diabetic foot ulcers and its severity.

Early identification of the risk factors associated with development of diabetic foot ulcer (DFU) can be facilitated using machine learning techniques. The aim of this study is to find out the association of various clinical and biochemical risk factors with DFU and develop a prediction model using different machine learning algorithms. Eighty each of type 2 diabetes mellitus (T2DM) with DFU and (T2DM) without DFU were enrolled for this observational study. Clinical and laboratory data were analysed using different machine learning algorithms: Support vector machines (SVM-Poly K), Naive Bayes (NB), K-nearest neighbour (KNN), random forest (RF) and three ensemble learners: Stacking C, Bagging and AdaBoost for constructing prediction models for discriminating between the two groups (stage I classification) and ulcer type classification (stage II classification). Ensemble learning performed better than individual classifiers in terms of various performance evaluation metrics. New risk factors like ApoA1 and IL-10 for development of DFU in diabetes mellitus were identified. IL-10 along with uric acid could discriminate the grades of ulcers according to its severity. Decision fusion strategy using Stacking C algorithm resulted in enhanced prediction accuracy for both the stages of classification which can be used as a complementary method for computational screening for DFU and its subtypes. Current methodology for T2DM with DFU/T2DM without DFU and ulcer type classification.