The AFRIDIARRHEA multimodal fusion framework for Estimating the Burden of Diarrheal Diseases Among Children Under Five in Kenya, Zimbabwe, and Somaliland

Background: Accurate estimation of childhood diarrheal disease burden in Africa remains challenging because of limited surveillance, incomplete mortality data, pathogen-attribution uncertainty, and complex environmental and socioeconomic drivers. This study developed the African Diarrheal Disease Integrated Risk Intelligence and Burden Estimation Architecture (AFRIDIARRHEA), a multimodal fusion framework for estimating under-five diarrheal burden in resource-constrained settings. Methods: AFRIDIARRHEA integrates Bayesian epidemiological modeling, machine learning, temporal forecasting, geospatial analytics, pathogen attribution, environmental intelligence, and uncertainty quantification within a unified framework. Synthetic datasets representing Kenya, Zimbabwe, and Somaliland were used to evaluate mortality, morbidity, hospitalization burden, pathogen-attributed mortality, and predictive performance. Results: The framework identified substantial heterogeneity in disease burden across countries, with Zimbabwe exhibiting the highest modeled mortality and morbidity burden and Somaliland the highest hospitalization burden. Rotavirus and Shigella were the dominant contributors to pathogen-attributed mortality. The multimodal fusion model outperformed the Bayesian baseline and individual component models, achieving improved predictive accuracy, robust uncertainty calibration, and strong agreement with benchmark estimates. Conclusions: AFRIDIARRHEA demonstrates the potential of multimodal fusion modeling for integrated estimation of childhood diarrheal burden, pathogen attribution, and uncertainty in African settings. The framework provides a scalable, transparent, and policy-relevant approach for supporting vaccine prioritization, WASH investments, outbreak preparedness, and child survival programs in data-limited environments. Keywords: Diarrheal disease, burden estimation, multimodal fusion, pathogen attribution, machine learning, uncertainty quantification, Africa