Potential Risk Estimation Drowning Index for Children (PREDIC): a pilot study from Matlab, Bangladesh

Drowning in Children and Predictive Parameters: A 15-Year Multicenter Retrospective Analysis

BACKGROUND

Drowning is a serious and underestimated public health problem, with the highest morbidity and mortality reported among children. Data regarding pediatric outcomes of drowning are often inadequate, and data collection is poorly standardized among centers. This study aims to provide an overview of a drowning pediatric population in pediatric emergency department, focusing on its main characteristics and management and evaluating prognostic factors.

METHODS

This is a retrospective multicenter study involving eight Italian Pediatric Emergency Departments. Data about patients between 0 to 16 years of age who drowned between 2006 and 2021 were collected and analyzed according to the Utstein-style guidelines for drowning.

RESULTS

One hundred thirty-five patients (60.9% males, median age at the event 5; interquartile range, 3-10) were recruited and only those with known outcome were retained for the analysis (133). Nearly 10% had a preexisting medical conditions with epilepsy being the most common comorbidity. One third were hospitalized in the intensive care unit (ICU) and younger males had a higher rate of ICU admission than female peers. Thirty-five patients (26.3%) were hospitalized in a medical ward while 19 (14.3%) were discharged from the emergency department and 11 (8.3%) were discharged after a brief medical observation less than 24 hours. Six patients died (4.5%). Medium stay in the ED was approximately 40 hours. No difference in terms of ICU admission was found between cardiopulmonary resuscitation performed by bystanders or trained medical personnel ( P = 0.388 vs 0.390).

CONCLUSIONS

This study offers several perspectives on ED victims who drowned. One of the major finding is that no difference in outcomes was seen in patients who received cardiopulmonary resuscitation performed by bystanders or medical services, highlighting the importance of a prompt intervention.

Non-Fatal Drowning Risk Prediction Based on Stacking Ensemble Algorithm

Drowning is a major public health problem and a leading cause of death in children living in developing countries. We seek better machine learning (ML) algorithms to provide a novel risk-assessment insight on non-fatal drowning prediction. The data on non-fatal drowning were collected in Qingyuan city, Guangdong Province, China. We developed four ML models to predict the non-fatal drowning risk, including a logistic regression model (LR), random forest model (RF), support vector machine model (SVM), and stacking-based model, on three primary learners (LR, RF, SVM). The area under the curve (AUC), F1 value, accuracy, sensitivity, and specificity were calculated to evaluate the predictive ability of the different learning algorithms. This study included a total of 8390 children. Of those, 12.07% (1013) had experienced non-fatal drowning. We found the following risk factors are closely associated with the risk of non-fatal drowning: the frequency of swimming in open water, distance between the school and the surrounding open waters, swimming skills, personality (introvert) and relationality with family members. Compared to the other three base models, the stacking generalization model achieved a superior performance in the non-fatal drowning dataset (AUC = 0.741, sensitivity = 0.625, F1 value = 0.359, accuracy = 0.739 and specificity = 0.754). This study indicates that applying stacking ensemble algorithms in the non-fatal drowning dataset may outperform other ML models.