A Decision Tree Analysis of Diabetic Foot Amputation Risk in Indian Patients

Abstract

Aim: The aim of this study is to create an evidence-based tool that guides the risk of amputation in diabetic foot patients. Materials and methods: Hospital records of 301 diabetic foot patients were examined retrospectively for explanatory variables of foot amputation decisions. The study included all patients with a lower limb ulcer with a known history of diabetes mellitus or those diagnosed post-admission. The dataset was analyzed, and a risk scoring system was constructed using the decision tree algorithm, C5.0. Two classifiers, one simple and another complex, were constructed for predicting amputation outcome.Results and discussion: Based on our evaluation, the most influential predictors for a decision to amputate are Doppler flow measurements and the Wagner grading of the ulceration. The simple classifier uses just these two parameters in determining risk. The results obtained show an accuracy of 96.4% in the primary group and an accuracy of 94% in the test group. The second classifier is a more complex computer-derived construct that showed 100% accuracy in the principle group and an accuracy of 96% during testing.Conclusion: In the present era of precision medicine, these two classifiers act as an accurate guide to the prognosis of the limb in patients with diabetic foot and can predict the risk of future amputation.