Intentional Self-Poisonings and Unintentional Poisonings of Adolescents With Nonfatal Outcomes

Comparison of machine learning algorithms to predict intentional and unintentional poisoning risk factors

Introduction

A major share of poisoning cases are perpetrated intentionally, but this varies depending on different geographical regions, age spectrums, and gender distribution. The present study was conducted to determine the most important factors affecting intentional and unintentional poisonings using machine learning algorithms.

Materials and methods

The current cross-sectional study was conducted on 658 people hospitalized due to poisoning. The enrollment and follow-up of patients were carried out during 2020-2021. The data obtained from patients' files and during follow-up were recorded by a physician and entered into SPSS software by the registration expert. Different machine learning algorithms were used to analyze the data. Fit models of the training data were assessed by determining accuracy, sensitivity, specificity, F-measure, and the area under the rock curve (AUC). Finally, after analyzing the models, the data of the Gradient boosted trees (GBT) model were finalized.

Results

The GBT model rendered the highest accuracy (91.5 ± 3.4) among other models tested. Also, the GBT model had significantly higher sensitivity (94.7 ± 1.7) and specificity (93.2 ± 4.1) compared to other models (P < 0.001). The most prominent predictors based on the GBT model were the route of poison entry (weight = 0.583), place of residence (weight = 0.137), history of psychiatric diseases (weight = 0.087), and age (weight = 0.085).

Conclusion

The present study suggests the GBT model as a reliable predictor model for identifying the factors affecting intentional and unintentional poisoning. According to our results, the determinants of intentional poisoning included the route of poison entry into the body, place of residence, and the heart rate. The most important predictors of unintentional poisoning were age, exposure to benzodiazepine, creatinine levels, and occupation.

Intentional suspected suicide exposures by poisoning among adolescents from 2009 to 2018 reported to the Georgia Poison Center and compared nationally

This retrospective chart review aimed to report the incidence and characteristics of intentional suspected suicide among 13- to 19-year-olds reported to the Georgia Poison Center (GPC) and compared nationally from 2009 to 2018. Of the 19 733 cases reported to the GPC, 74.9% were females. The total number of cases more than doubled from 2009 to 2018, increasing annually by 10%. Majority (90.1%) of the cases occurred in the home, and 60.4% of the cases resulted in either no effect or minor effect. More than half (66.5%) of the cases involved only one substance. Pharmaceuticals made up 94.5% of the substances used, with analgesics accounting for 42.10% and antidepressants at 20.77%. A significant difference was found in substances used between males and females (P < .001). Females were more likely to use analgesics (45.17% vs 32.90%), and males were more likely to use sedatives/hypnotics/antipsychotics (20.45% vs 13.58%). While the majority of the GPC patients were females, the GPC was more likely to have fewer female patients (74.7% vs 75.7%) and more male patients (25.3% vs 24.3%) than other poison centers. Intentional suspected suicide exposures by poisoning are on the rise and higher among females, demonstrating a need for strengthened intervention and prevention strategies.