What question did this study set out to answer?

April 1, 2026International Journal of Infectious Diseases0 citationsOpen Access

Machine Learning and Probabilistic Approaches for Forecasting Infectious Disease Transmission and Cases

MHMd Sakhawat HossainClemson University RGRavi GoyalUniversity of California, San Diego NMNatasha K. MartinUniversity of California System

Puntos clave

The aim is to develop an effective model for forecasting infectious disease transmission using machine learning techniques.
Utilized Integrated Regression, Random Forest, and XGBoost models in an ensemble approach.
Focused on forecasting COVID-19 cases over a 7-day period.
Employed the framework across counties in South Carolina for real-time application.
Achieved up to 96% agreement for 7-day forecasts of COVID-19 cases across counties.
Demonstrated generalizability to other infectious diseases and geographic scales.

Resumen

disease transmission dynamics. Integrated Regression, Random Forest, and XGBoost models into an ensemble forecasting approach. Achieved up to 96% agreement for 7-day forecasts for COVID-19 across counties in SC. Framework supports real-time epidemic surveillance and early intervention decisions. The approach is generalizable to other infectious diseases and finer geographic scales for real-time outbreak monitoring and response.

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo