Creating a climate-sensitive disease forecasting application for DHIS2 via participatory modeling

This abstract has been accepted at the 2024 DHIS2 Annual Conference

Creating a climate-sensitive disease forecasting application for DHIS2 via participatory modeling

Climate change is impacting both long-term climate change and short-term extreme climatic events, making infectious disease dynamics increasingly difficult to predict. The wide availability of remotely-sensed environmental data and public health metrics has resulted in the proliferation of climate-sensitive disease forecasting tools, which can aid health systems in adapting to climate change. However, such tools are rarely integrated into existing health management information systems (HMIS), nor is their impact on health system readiness evaluated. In resource-constrained settings in particular, accurate and timely predictions resulting from disease forecasting can greatly aid in the planning and logistics for efficient allocation of supplies to meet population health needs. The objective of this project is the creation of a disease forecasting tool (Predicting Infectious Diseases via Environment and Climate; PRIDE-C) in the form of a DHIS2 application for an existing health management information system in Ifanadiana district southeastern Madagascar. PRIDE-C focuses on three climate-sensitive infectious diseases that contribute to the vast majority of childhood deaths in the district: malaria, diarrheal disease, and acute respiratory infections (ARI). The disease forecasting tool is created via a series of participatory modeling workshops, whereby key public health actors co-develop conceptual models of disease systems that are operationalized into forecasting models. The output of these forecasting models, and the relevant environmental indicators, are made available in the local DHIS2 system via the PRIDE-C application. After the development of the application, we will evaluate its implementation via a mixed-methods study focusing on health-system readiness in the district. In this presentation, we present the results of the initial participatory modeling workshops and the resulting predictive models. We will also discuss the software architecture behind the analytical side of the application, and our plans to integrate the diverse datasets and computationally-intensive analytics into the existing DHIS2 system so that it can be transferable to other regions.

Primary Author: Michelle Evans

disease forecasting; climate; malaria; diarrheal disease; acute respiratory infection; software development