Machine learning algorithms to predict seizure due to acute tramadol poisoning

• Published in: Human & experimental toxicology Vol. 40; no. 8; pp. 1225 - 1233
• Main Authors: Behnoush, B, Bazmi, E, Nazari, SH, Khodakarim, S, Looha, MA, Soori, H
• Format: Journal Article
• Language: English
• Published: London, England SAGE Publications 01.08.2021; Sage Publications Ltd
• Subjects: Adolescent; Adult; Algorithms; Analgesics, Opioid - poisoning; Artificial neural networks; Bayes Theorem; Bayesian analysis; Bicarbonates; Bicarbonates - blood; Blood; Blood pressure; Decision Making; Decision trees; Emergency medical care; Emergency medical services; Emergency Service, Hospital; Female; Humans; Hydrogen-Ion Concentration; Learning algorithms; Learning theory; Machine Learning; Male; Models, Biological; Neural networks; Neural Networks, Computer; Patients; Poisoning; Prediction models; Predictions; Pulse; Pulse rate; Random variables; Risk groups; Seizures; Seizures - chemically induced; Sex Characteristics; Support vector machines; Tramadol; Tramadol - poisoning; Young Adult; prediction; tramadol; seizure; Machine learning
• ISSN: 0960-3271; 1477-0903
• DOI: 10.1177/0960327121991910

Introduction: This study was designed to develop and evaluate machine learning algorithms for predicting seizure due to acute tramadol poisoning, identifying high-risk patients and facilitating appropriate clinical decision-making. Methods: Several characteristics of acute tramadol poisoning cases were collected in the Emergency Department (ED) (2013–2019). After selecting important variables in random forest method, prediction models were developed using the Support Vector Machine (SVM), Naïve Bayes (NB), Artificial Neural Network (ANN) and K-Nearest Neighbor (K-NN) algorithms. Area Under the Curve (AUC) and other diagnostic criteria were used to assess performance of models. Results: In 909 patients, 544 (59.8%) experienced seizures. The important predictors of seizure were sex, pulse rate, arterial blood oxygen pressure, blood bicarbonate level and pH. SVM (AUC = 0.68), NB (AUC = 0.71) and ANN (AUC = 0.70) models outperformed k-NN model (AUC = 0.58). NB model had a higher sensitivity and negative predictive value and k-NN model had higher specificity and positive predictive values than other models. Conclusion: A perfect prediction model may help improve clinicians’ decision-making and clinical care at EDs in hospitals and medical settings. SVM, ANN and NB models had no significant differences in the performance and accuracy; however, validated logistic regression (LR) was the superior model for predicting seizure due to acute tramadol poisoning.