University of Southampton researchers are embarking on two major areas of research which harness the power of artificial intelligence (AI) to improve the health of patients.
The AGENDA (AI methods applied to GENomic Data) project will develop AI algorithms and data modelling to vast genomic datasets to improve their analysis and interpretation for application in a 'real-world' clinical environment.
RELOAD (REspiratory disease progression through LOngitudinal Audio Data machine learning) will use AI to identify patients at risk of developing severe respiratory tract infections.
A diverse team of medics, computer scientists, biological scientists and chemists will work on AGENDA, led by Southampton's Professor Sarah Ennis (Medicine). The project has been awarded a £744k UKRI grant as part of the EPSRC led Artificial Intelligence Innovation to Accelerate Health Research programme.
Professor Ennis comments: "This grant provides the opportunity to develop novel solutions to analysis of genomic data. By incorporating an automated AI-based toolkit, we will maximise data usage, significantly speed up the return of molecular diagnoses, and identify biologically relevant targets for personalised therapies. In the future this will reduce hospital and treatment costs and provide digital systems, minimising the need for manual curation."
The RELOAD project also received funding from the UKRI, worth £590,000. The University of Southampton's Professor Anna Barney (Institute Of Sound & Vibration Research) and Professor Nick Francis (Medicine) will work with the lead academic on the project, Professor Ceclia Mascolo of the University of Cambridge. The team will develop an app which patients can use to record their coughs, breathing and speech at different times. Machine learning will interpret these sounds to decide whether the infection is likely to cure itself, or if it is progressing to a more serious state.
Respiratory Tract Infections (RTIs) range from the common cold to more serious conditions, such as Pneumonia. Most RTIs get better without treatment, but others may need to be assessed by a GP.
"Using acoustic data is a relatively underexplored application of machine learning," says Professor Anna Barney. "The AI in this application will reassure patients when an infection is self-limiting and direct patients to a GP when it is not. This should help to ensure that GP appointments are freed up for those that need them."
The Southampton researchers will work with other AI projects funded by UKRI to share best practice, minimise machine learning bias, and better explain how AI arrives at its decisions.
These grants follow the recent announcement of £31M to the University of Southampton to lead on the Responsible AI UK consortium.