Factors Associated with COVID-19 Mortality in Mexico: A Machine Learning Approach Using Clinical, Socioeconomic, and Environmental Data

Abstract

COVID-19 mortality is a complex phenomenon influenced by multiple factors. This study aimed to identify factors associated with death in COVID-19 patients by considering clinical, demographic, environmental, and socioeconomic conditions, using machine learning models and a national dataset from Mexico covering all pandemic waves. We integrated data from the national COVID-19 dataset, municipal-level socioeconomic indicators, and water quality contaminants (physicochemical and microbiological). Patients were assigned to one of four datasets (groundwater, lentic, lotic, and coastal) based on their municipality of residence. We trained XGBoost models to predict patient death or survival on balanced subsets of each dataset. Hyperparameters were optimized using a grid search and cross-validation, and feature importance was analyzed using SHAP values, point-biserial correlation, and XGBoost metrics. The models achieved strong predictive performance (F1 score > 0.97). Key risk factors included older age (≥50 years), pneumonia, intubation, obesity, diabetes, hypertension, and chronic kidney disease, while outpatient status, younger age (<40 years), contact with a confirmed case, and care in private medical units were associated with survival. Female sex showed a protective trend. Higher socioeconomic levels appeared protective, whereas lower levels increased risk. Water quality contaminants (e.g., manganese, hardness, fluoride, dissolved oxygen, fecal coliforms) ranked among the top 30 features, suggesting an association between environmental factors and COVID-19 mortality.