July 8, 2025
I was fortunate to receive an ACREME MASTER-MAP Travel and Training Award to attend the second European Summer Program in Infectious Disease Analysis and Modelling (ESPIDAM), held at the Department of Mathematics at Stockholm University, Sweden.
This intensive and inspiring workshop brought together masters, PhD, early and mid-career researchers from across Europe and beyond to explore cutting-edge topics in infectious disease modelling. The program included two half-week courses, and I had the opportunity to dive into (1) Modelling and AI for Infectious Disease Control, and (2) Within-Host Modelling of Infectious Diseases.
The first course was incredibly timely, given the growing integration of artificial intelligence (AI) in research — from large language models like ChatGPT to applications in public health. We explored how reinforcement learning, a branch of AI where an “agent” learns to make decisions by interacting with its environment, can be used to optimise disease control strategies. A particularly striking example came from Belgium’s COVID-19 response, where course instructors Prof. Niel Hens and Prof. Pieter Libin applied reinforcement learning to simulate the effects of school closures on disease spread, using a classic susceptible-infected-recovered (SIR) model. It was exciting to see how these methods can support data-driven public health policies.
The second course zoomed in to the cellular level — exploring how we can use mathematical models to describe interactions within the human body, such as immune responses to pathogens. With expert instructors Dr Mélanie Prague and Dr Jérémie Guedj, we examined how different equations can capture the dynamics between immune cells and viruses, track antibody responses over time, and evaluate how these dynamics change with interventions like vaccination. It offered a powerful perspective on how within-host models complement population-level studies.
I also had the opportunity to present a poster on my research, which focuses on a machine learning algorithm designed to classify recent Plasmodium vivax infections using serological biomarkers. This approach aims to identify individuals who may be carrying hypnozoites — the dormant liver-stage parasites that can cause relapses. Alongside this, I showcased an RShiny application, PvSeroApp, which allows users to apply the model in field settings in a user-friendly way. The poster attracted strong interest from attendees, particularly around how we’ve applied machine learning in a tropical disease context and how RShiny can streamline data processing in real time. I received thoughtful and constructive questions that will directly inform the next stage of my work — especially around refining and validating the algorithm.
Overall, ESPIDAM was a deeply rewarding experience. I came away with new skills, fresh ideas, and a reinvigorated sense of community. What I learned will directly feed into my postdoctoral research on seroclassification of Plasmodium vivax malaria, and more broadly, it’s strengthened my foundation in infectious disease modelling. I would again like to sincerely thank ACREME for supporting this fundamental educational journey, and the chance to experience Stockholm in the summer!
