Adverse effects following immunization (AEFI) in children involve any unpleasant medical condition following immunization, irrespective of causality. Understanding and monitoring AEFI is paramount for vaccine safety and public health. In Rwanda, immunization plays a pivotal role in safeguarding children and pregnant women's health, with over 90% of the targeted population receiving vaccinations. Despite the widespread coverage, we still have a significant gap in AEFI reporting, hindering effective monitoring and response. This gap highlighted by the Rwanda FDA. This study proposes a mobile application solution to address AEFI underreporting in Rwanda. The study's objectives include designing and customizing the VigiMobile application, piloting it in health facilities, and developing a predictive model for AEFI factors. The application adapted from the globally utilized VigiMobile platform, will undergo customization to suit the Rwandan context. Through a user centred design approach, the application will be used by parents to report AEFI directly bridging the reporting to response gap. Additionally, the integration of machine learning algorithms will facilitate the identification of factors influencing AEFI within the Rwandan population. This will enhance understanding and response while also addressing the underreporting of AEFI. This solution will strengthen vaccine safety monitoring and improve public health outcomes in Rwanda.
Research areas
Machine Learning in Health
Eligible researchers
Master's students, Ph.D. students