UK non-profit organisation Wellcome has announced funding support for two new digital technology projects focussed on the detection of paediatric brain injuries and improving stroke care, respectively.
The digital technology projects are supported by the recent £20m funding under Wellcome Innovator Awards.
Both digital technology innovations will leverage machine learning and artificial intelligence to analyse huge volumes of data that would usually require years to process.
Wellcome Innovation director Stephen Caddick said: “Digital innovation offers a unique opportunity to improve human health and help people living in poverty.
“We are offering funding to innovators who want to create and develop new digital interventions at speed and scale, and who have the ambition to improve the lives of millions of people.”
“Both digital technology innovations will leverage machine learning and artificial intelligence to analyse huge volumes of data that would usually require years to process.”
As part of the first project by the INFANT Centre at University College Cork, researchers are creating a smart system to identify patterns in electrical brain activity. This is intended to aid in detecting babies who need quick treatment.
Currently, doctors use EEG brain monitoring to decide on the treatment for new-born babies with suspected brain injuries. Wellcome noted that these brain scans need to be interpreted by an expert, and there aren’t enough experts to be at every cot side.
The INFANT Centre team is training computers to learn EEG patterns and their relation to the extent of brain injuries.
It is expected that the detection of warning signs by the computer could allow more babies to survive, and reduce the risk of permanent disabilities such as epilepsy, cerebral palsy or learning difficulties.
The second of the digital technology projects involves the development of a new system at University College London to tailor stroke treatment for individual patients. The team has built a supercomputer that is being trained using data from numerous stroke patients.
This computer is expected to learn patterns in the outcomes for various types of strokes and the impact of different treatment decisions. The goal is to make the computer predict the best clinical decisions for each patient, in turn expediting treatment and potentially enhance recovery.
King’s Health Partner hospitals will work with the King’s College London clinicians and machine learning engineers to develop parallel systems.
