Predicting Drowning Mortality Risk Using Machine Learning Models; A Retrospective Cohort Study.
Archives of Academic Emergency Medicine · 01.01.2026 · 14 (1) · e21-e21
DOI: 10.22037/aaem.v14i1.2963 ↗Kurz gefasst
Kohortenstudie in der Zeitschrift Archives of Academic Emergency Medicine, erschienen am 01.01.2026. Verfasst von Yousef Veisani und 7 weiteren Autor:innen. Beteiligte Einrichtung: Non-Communicable Diseases Research Center, Ilam University of Medical Sciences, Ilam, Iran. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Introduction
Particularly in highly tourist-active coastal locations, drowning is still a serious international public health concern. This study investigates the predictive value of machine learning approaches in estimating drowning-related mortality risk.
Methods
This retrospective cohort study analyzed drowning incident data from the Emergency Management and Medical Urgency Center of Guilan Province, covering the period from 2018 to 2023. The data were preprocessed, missing values imputed using the K-Nearest Neighbors (KNN) algorithm, and balanced using the Synthetic Minority Over-sampling Technique (SMOTE). Three models including logistic regression, decision tree, and naïve Bayes were evaluated in predicting the risk of mortality following drowning and sensitivity, specificity, and accuracy of each model was calculated and compared.
Results
A total of 600 consecutive cases meeting the eligibility criteria were extracted for analysis, forming the final dataset. Logistic regression exhibited the highest predictive power, with an accuracy of 51.67% and an area under the curve (AUC) of 60.02%. The most influential variables in drowning-related mortality prediction were drowning location, drowning year, gender, and age. High-risk areas posed a 33-fold higher mortality risk than safe locations (p < 0.001). Age and gender were not statistically significant predictors of fatal drowning.
Conclusion
Given its superior interpretability and predictive capability, logistic regression was identified as the most effective model for assessing drowning mortality risk. Preventative measures should focus on identifying high-risk areas, installing warning signs, implementing lifeguard teams, educating tourists, and enforcing strict coastal safety regulations to mitigate drowning fatalities.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Non-Communicable Diseases Research Center, Ilam University of Medical Sciences, Ilam, Iran.
- School of Public Health and Safety, Department of Health in Disasters and Emergencies, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
- Technical and Operations Deputy of the Pre-Hospital Emergency and Disaster Management Center, Gilan University of Medical Sciences, Gilan, Iran.
- Safety Promotion and Injury Prevention Research Centre, Research Institute for Health Sciences and Environment, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
- School of Public Health and Safety, Department of Epidemiology, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
- Director of Pre-Hospital Emergency and Disaster Management Center, Gilan University of Medical Sciences, Gilan, Iran.
Zitieren
APA
Veisani, Y., Sahebi, A., Jobaneh, M., Sayyadi, H., Delpisheh, A., Mohammadi, J., Rahmani, F., & Ghomian, Z. (2026). Predicting Drowning Mortality Risk Using Machine Learning Models; A Retrospective Cohort Study. Archives of Academic Emergency Medicine, 14(1), e21-e21. https://doi.org/10.22037/aaem.v14i1.2963
Vancouver
Veisani Y, Sahebi A, Jobaneh M, Sayyadi H, Delpisheh A, Mohammadi J, et al. Predicting Drowning Mortality Risk Using Machine Learning Models; A Retrospective Cohort Study. Archives of Academic Emergency Medicine. 2026;14(1):e21-e21. doi:10.22037/aaem.v14i1.2963
BibTeX
@article{Veisani2026,
author = {Veisani, Yousef and Sahebi, Ali and Jobaneh, Masoud and Sayyadi, Hojjat and Delpisheh, Ali and Mohammadi, Jamshid and Rahmani, Faezeh and Ghomian, Zohreh},
title = {Predicting Drowning Mortality Risk Using Machine Learning Models; A Retrospective Cohort Study},
journal = {Archives of Academic Emergency Medicine},
year = {2026},
volume = {14},
number = {1},
pages = {e21--e21},
doi = {10.22037/aaem.v14i1.2963}
}
EUVIMED