Utility Of Support Vector Machine And Decision Tree To Identify The Prognosis Of Metformin Poisoning In The United States: Analysis Of National Poisoning Data System

Background: With diabetes incidence growing globally, and metformin still being the first-line for its treatment, metformin’s toxicity and overdose have been increasing. Hence, its mortality rate is increasing. For the first time, we aimed to study the efficacy of machine learning algorithms in predicting the outcome of metformin poisoning using two well-known classifications methods including support vector machine (SVM) and decision tree (DT). Methods: : This is a retrospective cohort study of National Poison Data System data which is the largest data repository of poisoning cases in the United States. The SVM and DT algorithms developed using training and test datasets. Results: : The overall accuracy of the SVM and DT model were 85% and 89%, respectively. Our model showed that acidosis, hypoglycemia, electrolyte abnormality, hypotension, elevated anion gap, elevated creatinine, tachycardia , and renal failure are the most important determinants in terms of outcome prediction of metformin poisoning. Furthermore, we found that the accuracy of the SVM was higher than the DT model, so it could perform more efficiently to predict the outcomes. Conclusions: : In order to predict the prognosis of metformin poisoning, machine learning algorithms are very effective, and may help clinicians in the process of management and follow up of the metformin poisoning cases.