Innovation in health research
Researchers at Bristol are already applying AI to various health challenges including, investigating molecular mechanisms driving disease, predicting disease-causing genomic variants, modelling of patient behaviour following surgery, and using language models for semantic mapping of traits between biomedical datasets. How do we mobilise this talent and encourage further collaborations in AI research with the potential to improve our health?
Advancing AI aptitude
Elizabeth Blackwell Institute for Health Research is committed to supporting AI in health research. We have established an AI in Health research community, which brings together researchers at the University of Bristol from different disciplines and external partners with an interest in AI in health.
We host an online shared space for the community to connect virtually; run in-person events to explore applications of AI in health research in a range of contexts; and have provided springboard funding for innovative AI projects.
We spoke to two of the five successful candidates from our recent AI in Health funding call about their projects and the potential benefit for society.
Luca Iart Shytaj, who is leading on a project titled: ‘Assessment of the integration of molecular docking with AI-based design of personalised vaccines', said: “Future medicine is envisioned as personalised, with most medicines or vaccines tailored to individual needs. Our immune system identifies diseased cells through small protein fragments, akin to a game of Wordle. However, not all fragments are equally informative, and recognition varies based on genetics, like the information provided by letter combinations differs in various languages. We aim to combine AI computation and laboratory testing to design informative fragments for optimal immune recognition, using HIV as a model. If successful, our project could help in the development of more effective, personalised vaccines and immune-based treatments.”
Helen Smith, who is leading on a project titled: ‘Professional Ethical Guidance for Healthcare AI Use', said: “Healthcare professionals look to their regulatory bodies (e.g. the General Medical Council, the Nursing and Midwifery Council) to direct their practice. Artificial intelligence (AI) is being developed for use in healthcare in the UK. The problem is that there is no guidance to help healthcare professionals safely and fairly use AI in their work. Each of the different healthcare professions could make its own guidance for AI use. This could be confusing, however, as different professions might be given contradictory guidance.
“Our research will help by identifying what could be in professional ethical guidance for AI use for all healthcare professionals (doctors, nurses, physios, paramedics, etc), taking a first step towards creating unified guidance.”
Elizabeth Blackwell Institute Director, Rachael Gooberman-Hill, said: “Bristol’s health research is world-renowned, and the University is a hotbed of AI innovation. Through our AI in Health research community we are bringing together those working in AI and those working in health to strengthen research and explore AI’s potential to improve our health. By supporting researchers working in this field we aim to enhance AI capacity at Bristol and support the development of ideas for future major health research grants.”
Supporting collaboration on AI research
A small team of researchers have received funding from the UK Research and Innovation (UKRI) Enhancing Research Culture fund to scope out feasibility and support for a centralised registry for AI projects. The aim of the centralised registry is to improve the visibility of AI projects to University of Bristol staff across the university and to facilitate collaborative multi and interdisciplinary working.
The team, who are supported by Elizabeth Blackwell Institute, Jean Golding Institute, Brigstow Institute, Bristol Digital Futures Institute, Research Data Service and ESRC Centre for Sociodigital Futures, are currently preparing a short staff survey to capture views about the AI registry.
Barbara Caddick, who leads the research team explains: “We want to ensure that we design and develop a useful resource that reflects the needs of its users and will make a useful contribution to research at the University.”
We will be sharing a link to the survey for University of Bristol researchers once it is live.
Looking ahead at AI in Bristol
The government announced in September 2023 that the University of Bristol was chosen to host a new national supercomputer research facility focused on AI. Known as Isambard-AI, it is expected to be the most powerful supercomputer in the UK and among the most powerful in Europe.
We asked Christopher Woods, AI Supercomputing Infrastructure Lead at the University of Bristol, about what role the new Isambard-AI facility could play in the future of health research.
Christopher Woods, School of Computer Science, said: “AI has the potential to enhance what we are already doing to improve our health and help us to explore new avenues to health discoveries. AI systems can analyse a massive amount of data extremely quickly and can recognise complex patterns that researchers might miss.
“The new Isambard-AI supercomputer facility will be used by researchers at the University of Bristol, along with a wide range of organisations from across the UK to harness the power of AI. With its vast potential to speed up processes, reduce costs, and generate insights, it offers a powerful way to advance health research.”