Peer-reviewed article
Advancing epidemic intelligence: evaluating Senegal's mpox surveillance system and readiness for AI-driven predictive modelling.
Sylvain L B Faye, Fatoumata B Diongue, Abdourakhmane Ndao, Boly Diop, Georgette H C Sow et al. ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001This study evaluates Senegal's mpox surveillance system and its readiness for AI-driven predictive modelling. It reviews mpox case data from January 2024 to October 2025, finding seven cases concentrated in Dakar among young mobile populations. The surveillance system has improved but faces challenges including underreporting in rural areas and limited real-time analytics capacity.
Key points
- By October 2025, Senegal had reported seven mpox cases, all in Dakar, with higher incidence among children and working-age adults
- Transmission patterns showed urban density and population mobility as key factors influencing disease spread along the Dakar-Thiès-Diourbel corridor
- The surveillance system improved reporting and geolocation capabilities through One Health coordination and digital infrastructure
- Challenges identified include underreporting in rural areas, uneven coverage, and limited real-time analytics capacity
- The AI4MPOX-SN initiative proposes integrating human-animal-environment data using AI for anomaly detection and predictive modelling
Limitations
This document focuses on surveillance system infrastructure and epidemic intelligence rather than interventions to improve child health outcomes directly. It does not evaluate the effectiveness of any specific intervention for a defined health problem in children.
Abstract
INTRODUCTION: Mpox has re-emerged as a public health issue in West Africa, underscoring the need for robust surveillance systems that can detect outbreaks and facilitate effective responses. This study evaluates Senegal's mpox surveillance system, focusing on performance, data quality, governance, and potential for Artificial Intelligence-powered, predictive epidemic intelligence. It reviews trends and system operations while exploring AI and modeling to improve early warnings. METHODOLOGY: A descriptive, exploratory approach combined quantitative and qualitative data from various sources. A retrospective review of mpox cases from January 2024 to October 2025 utilized DHIS2 Tracker to analyze geographical, temporal, and demographic patterns, as well as reporting delays and biases. Data-quality checks and stakeholder interviews provided insights into system performance, intersectoral coordination, and preparedness for advanced analytics. RESULTS: By late October 2025, Senegal had reported seven mpox cases, all in Dakar, primarily affecting young, mobile populations, with a higher incidence among children and working-age adults. Transmission followed population movement along the Dakar-Thiès-Diourbel corridor, showing how urban density and mobility influence spread. The surveillance system improved reporting, geolocation, and follow-up, supported by One Health coordination and digital health infrastructure. Challenges include underreporting in rural areas, uneven coverage, limited real-time analytics, and gaps in data interoperability and responsible AI regulation. The AI4MPOX-SN initiative offers an opportunity to enhance epidemic intelligence by integrating human-animal-environment data, using AI for anomaly detection and predictive modeling to inform interventions. CONCLUSION: To develop predictive epidemic intelligence in Senegal, it's vital to involve local stakeholders, promote transparency, build workforce capacity, and establish safeguards for the ethical use of data. Combining technology, participatory governance, and institutional strengthening will enable Senegal to transition from reactive detection to proactive surveillance, positioning it as a regional leader in health security in West Africa.