Citation

Mehrpour O, Saeedi F, Vohra V, Abdollahi J, Shirazi FM, Goss F. Basic Clin. Pharmacol. Toxicol. 2023; ePub(ePub): ePub.

Copyright

(Copyright © 2023, Nordic Pharmacological Society, Publisher John Wiley and Sons)

DOI

10.1111/bcpt.13865

PMID

36960587

Abstract

Bupropion is widely used for the treatment of major depressive disorder and for smoking cessation assistance. Unfortunately, there are no practical systems to assist clinicians or poison centers in predicting outcomes based on clinical features. Hence, the purpose of this study was to use a decision tree approach to inform early diagnosis of outcomes secondary to bupropion overdose. This study utilized a dataset from the National Poison Data System, a six-year retrospective cohort study on toxic exposures and patient outcomes. A machine learning algorithm (decision tree) was applied to the dataset using the sci-kit-learn library in Python. Shapley Additive exPlanations (SHAP) were used as an explainable method. Comparative analysis was performed using Random Forest (RF), Gradient Boosting classification, eXtreme Gradient Boosting, Light Gradient Boosting (LGM), and Voting Ensembling. ROC curve and Precision-Recall curve were used to analyze the performance of each model. LGM and random forest demonstrated the highest performance to predict outcome of bupropion exposure. Multiple seizures, conduction disturbance, intentional exposure, and confusion were the most influential factors to predict the outcome of bupropion exposure. Coma and seizure, including single, multiple and status, were the most important factors to predict major outcomes.

Language: en

Keywords

prognosis; machine learning; outcome; overdose; bupropion; Decision tree