According to the institution, the solution is intended to provide a “prediction model that can rapidly and reliably diagnose a prognosis to doctors.” This is being accomplished through “deep learning approaches”, in conjunction with clinical datasets derived from Austria, China, Italy and the UK.
Speaking of the project, a spokesperson for Cambridge University said: “Fast and accurate diagnosis of patients in order to limit disease spread - together with the rapid determination of whether a patient is likely to recover, require intensive care unit admission, or intensive ventilation - is key to allocating resources and to improving patient outcomes.
“Any effort for developing a widely applicable tool for COVID-19 hospital support must be open source so it can be adapted to different environments. It must be based on a serious data sharing, curation, cleaning and a standardisation effort.”
Professor Evis Sala, who co-leads the project with professor Carola-Bibiane Schönlieb, said: “AI offers huge potential to support agile clinical decision making, ensuring patients receive the most appropriate support and leading to better patient outcomes.”
The Cambridge research team is hoping to launch the tool - AIX-COV-NET - within the next 12 to 18 months.
Editorial contact
Philip Mason
Editor, Critical Communications Portfolio
Tel: +44 (0)20 3874 9216
Philip.mason@markallengroup.com
