Related Experiment Videos
Predicting Drowning Mortality Risk Using Machine Learning Models; A Retrospective Cohort Study
Yousef Veisani1, Ali Sahebi1, Masoud Jobaneh2,3
1Non-Communicable Diseases Research Center, Ilam University of Medical Sciences, Ilam, Iran.
Archives of Academic Emergency Medicine
|July 29, 2026
Summary
Machine learning models were evaluated to predict drowning mortality risk. Logistic regression showed the highest predictive power, identifying high-risk coastal areas as crucial for targeted prevention strategies to reduce drowning incidents.
Area of Science:
- Public Health
- Data Science
- Coastal Safety
Background:
- Drowning remains a significant global public health issue, particularly in coastal areas with high tourist activity.
- Accurate prediction of drowning-related mortality risk is essential for developing effective public health interventions.
Purpose of the Study:
- To investigate the predictive value of machine learning models in estimating drowning-related mortality risk.
- To compare the performance of logistic regression, decision tree, and naïve Bayes algorithms for predicting drowning fatalities.
Main Methods:
- A retrospective cohort study analyzed 600 drowning incident cases from Guilan Province (2018-2023).
- Data preprocessing included K-Nearest Neighbors (KNN) imputation for missing values and Synthetic Minority Over-sampling Technique (SMOTE) for data balancing.
- Logistic regression, decision tree, and naïve Bayes models were evaluated for predictive accuracy, sensitivity, and specificity.
Main Results:
- Logistic regression achieved the highest predictive accuracy (51.67%) and Area Under the Curve (AUC) of 60.02%.
- Key predictors of drowning mortality included drowning location, year, gender, and age.
- High-risk coastal areas presented a 33-fold increased mortality risk compared to safe locations (p < 0.001).
Conclusions:
- Logistic regression is the most effective model for assessing drowning mortality risk due to its interpretability and predictive power.
- Preventative strategies must prioritize identifying and managing high-risk coastal zones.
- Recommendations include enhanced warning systems, lifeguard deployment, public education, and stringent coastal safety regulations.
Related Concept Videos
01:18Steps in Outbreak Investigation
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
01:30Typical Model Studies
Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.