New app to identify patients at risk of developing severe RTIs
Researchers from the Faculty of Medicine are to work on a new project with colleagues in the Institute Of Sound & Vibration Research, using AI to identify patients at risk of developing severe Respiratory Tract Infections (RTIs).
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.
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.
Professor Nick Francis, head of School of Primary Care, Population Sciences and Medical Education, explained: “RTIs are the most common cause of illness resulting in around half of all antibiotic prescriptions. Most people get better fairly quickly, but we need to notice quickly when people are getting seriously ill. If we do not, the effect on them and on healthcare services can be large.
“We have tests that help doctors identify patients who are more likely to need treatment, but these do not work well for every patient and are not useful for helping patients manage their own illness.
“We already know that some signs, such as breathing faster, can tell us whether an RTI is getting worse, and we know we can measure these signs by recording the sound of the breath. We also know that RTIs also affect breathing pattern, the sound of speech and trying to breathe when speaking.
“We hope to develop an app that will assess all of these signs and give warning if someone with an RTI should see their doctor for advice or they can expect to get better without treatment. It will also rate its own confidence in its prediction, which will help doctors trust machine learning in healthcare.”
The RELOAD (REspiratory disease progression through LOngitudinal Audio Data machine learning) is funded by a grant from the UKRI, worth £590,000. The University of Southampton’s Professor Anna Barney (Institute Of Sound & Vibration Research) is part of the Southampton team, which will work with the lead academic on the project, Professor Ceclia Mascolo of the University of Cambridge.
“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 UKRI funding was part of a £13 million investment from the government into projects aiming to transform health using AI to assist and refine diagnostics and procedures. The investment is also funded another Faculty project using AI to improve analysis, interpretation, and clinical translation of newly discovered variations in the genome.