I’m Max, a DPhil student in Population Health at the Big Data Institute, University of Oxford. My research focuses on modeling diseases in multimorbid settings and quantifying the associated uncertainties. My area of interest is the co-distribution of schistosomiasis and malaria, specifically examining the age-dependent differences in co-infection interactions and their impact on splenic pathologies. Additionally, I develop conversational AI agents in the context of research and business which can be used to enhance interviewing, data collection, and document interaction.
PhD Population Health
University of Oxford
MSc Statistical Science
University of Oxford
BSc Statistics
Ludwig-Maximilians-University Munich
Bridging the gap between statistical modeling, epidemiology, and public health decision-making, I believe that statistical approaches should be developed in close collaboration with fieldwork to ensure they are grounded in real-world data and practical applications. This is one of the main motivations why I joined the Schistotrack Group and Dr Goylette Chami at the BDI at Oxford, which involves biannual data collection in partnership with the Ministry of Health in rural Uganda.
In low-income countries, people often face multiple health challenges simultaneously. Understanding the interactions between diseases in multimorbid contexts is crucial for effective treatment and public health strategies. My research focuses on the co-distribution of malaria and schistosomiasis, particularly how co-infection interactions vary by age and influence splenic pathologies.
I also believe that qualitative data collection can be revolutionized with conversational AI and large language models (LLMs). Traditional feedback forms are becoming obsolete, and the future lies in chat interfaces and microphone-based interviews. That’s why I develop interviewing agents capable of conducting human-like interviews, enhancing data quality, and automating the data collection process.
Project Calliope is a conversational AI solution designed to disrupt how interviews and data collection are conducted, especially in regions with limited resources.
May 26, 2024
RAG-nificent is a state-of-the-art repository that leverages the power of Retrieval-Augmented Generation (RAG) to provide instant answers and references from a curated directory of PDFs containing information on any given topic such as WHO recommendations documents. This system is designed to aid researchers, policy makers, and the public in quickly finding specific information within extensive documents. Rag-nificent is powered by the Groq API, the fastes API (May 2024) for inference of LLMs resulting in (almost) instant responses.
May 1, 2024
Pytector is a Python package designed to detect prompt injection in text inputs using state-of-the-art machine learning models from the transformers library.
Apr 1, 2024