Answers are grounded in this paper and cite their sources.
Comparative analysis predicts acute respiratory infections in San Juan de Lurigancho, suggesting improved resource allocation.
Acute Respiratory Infections (ARIs) are a known public health challenge in San Juan de Lurigancho, the most populous district in Peru. This investigation presents a comparative and predictive analysis of ARI cases of timeline data, using three Machine Learning algorithms: K-Nearest Neighbors (KNN), Random Forest, and Extreme Gradient Boosting (XGBoost). After careful hyperparameter tuning, XGBoost were the superior model achieving a Coefficient of Determination (𝑅2) of 0.710 and a Mean Absolute Error (MAE) of 209.35 cases. It improved the results of both the Random Forest model (MAE of 212.37 cases) and the KNN baseline (K=1, MAE of 219.16 cases). These models were trained and evaluated using historical epidemiological and environmental data to predict infection trends and These results demonstrate that gradient boosting techniques can effectively capture the complex, nonlinear patterns of respiratory diseases in heavy populated urban areas. These results provide a clearer predictive framework for local health authorities to optimize resource allocation and proactive medical responses.
No takes yet. Share an insight, caveat, or question.
Yersi A. Brocos Barbaron (2026) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: