Predicting Drowning Mortality Risk Using Machine Learning Models; A Retrospective Cohort Study

Yousef Veisani, Ali Sahebi, Masoud Jobaneh, Hojjat Sayyadi, Ali Delpisheh, Jamshid Mohammadi, Faezeh Rahmani, Zohreh Ghomian · 2026

Read Predicting Drowning Mortality Risk Using Machine Learning Models; A Retrospective Cohort Study by Yousef Veisani, Ali Sahebi, Masoud Jobaneh, Hojjat Sayyadi, Ali Delpisheh, Jamshid Mohammadi, Faezeh Rahmani, Zohreh Ghomian (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-13412114.txt.

Description

Veisani and co-authors test, in 2026, whether machine learning can predict which drowning victims will die. They use 600 cases recorded by the emergency system of Guilan Province, Iran, a Caspian Sea tourist coast, from 2018 to 2023. Missing values were filled by nearest-neighbor imputation and the data rebalanced. Three models, logistic regression, decision tree, and naive Bayes, were trained on 70 percent of cases and tested on the rest.

Logistic regression won, though modestly, with an accuracy of 51.67 percent and an area under the curve of 60.02 percent on the held-out cases in evaluation. Location dominated the risk picture: high-risk areas carried a 33-fold higher mortality risk than safe locations, while age and gender were not significant predictors despite ranking among the top variables. The authors recommend prevention aimed at geography, warning signage and surveillance at dangerous sites, rather than profiling, and present the model as a baseline for emergency planning.

Catalog record

CREATORYousef Veisani, Ali Sahebi, Masoud Jobaneh, Hojjat Sayyadi, Ali Delpisheh, Jamshid Mohammadi, Faezeh Rahmani, Zohreh Ghomian
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE22 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC13412114

Browse the full library · About the Tower of Babel