Andrew Soltan

I am a clinician–engineer, as an Academic Clinical Lecturer in Oncology and Junior Research Fellow in Engineering at Jesus College. I practise clinically as a Specialty Registrar in Medical Oncology at Oxford University Hospitals.

My research develops and evaluates multi-agent AI systems and federated techniques for cancer care. I designed and lead development of TrustedMDT, an agentic AI system to support multidisciplinary decision making in oncology. The project is a collaboration with Oxford University Hospitals, Microsoft Health & Life Sciences, and is supported by awards from Microsoft Research and Oxford University Innovation. TrustedMDT has a modular architecture with agents for clinical summarisation, TNM staging, and treatment planning, and integrates with existing MDT workflows.

I collaborate with the Computational Health Informatics Lab where I previously led the CURIAL programme, which formed the basis of my PhD in Clinical Machine Learning (by published works).

During my NIHR Academic Clinical Fellowship, I focused on developing AI-enabled screening, diagnostic, and prognostic tools using routinely collected healthcare data. As Chief Investigator of the CURIAL study, I developed and evaluated an AI screening test for COVID-19 in emergency departments based on blood tests and vital signs recorded within the first hour of admission, while affiliated with Prof David Clifton's Computational Health Informatics lab. The CURIAL AI test was piloted in Oxford’s John Radcliffe Hospital in 2021 and described in The Lancet Digital Health as “an elegant breakthrough to enhance the clinical decision-making process in the age of artificial intelligence.” Related work also explored model-level approaches to reducing bias in AI predictions.

To support confidential development of AI models within the NHS, I built and deployed a new platform for rapidly-deployable and readily scalable federated learning, using inexpensive micro-computing devices. The Full-Stack Federated Learning platform was piloted at 4 NHS Trusts in 2022 to train and evaluate a Covid-19 screening test, with participating hospitals retaining custody of their data at all times, and published in The Lancet Digital Health in February 2024.

I graduated with distinction from the University of Cambridge's medical school, moving to Oxford in 2018 for  postgraduate training within the NIHR joint academic clinical training pathway. My PhD in Clinical Machine Learning was awarded by the University of Cambridge based upon published works. My research has been funded by the NIHR, Medical and Life Sciences Translational Fund (Wellcome/MRC), and Microsoft Research.

Between 2022 and 2025, I led the Dissertation Module for the MSc in Applied Digital Health, giving students a chance to explore a focus within the digital health development and translational pipeline while expanding their professional networks.