Cardiff Uni researchers develop new AI diagnosis method

If these methods are refined, lives can be saved as well as hospital resources. Source: Seanbatty (Pixabay)

By Danny Brown

A recent paper published by researchers at Cardiff University details how artificial intelligence and machine learning can give highly accurate and reliable prognoses for patients with cardiovascular diseases.

The team used an artificial intelligence technique to assess the possible future risks of a cardiovascular event in over 3800 cardiovascular patients over a 10 year period.

At the moment, in this evidence-based era of medicine, the use of statistics is crucial in estimating the severity and risks of diseases. This has normally been done by clinicians and statisticians, by manually developing highly complex equations. Using the artificial intelligence techniques detailed in the research paper reveals hidden or complex associations in the data.

Professor Craig Currie, one of the co-authors of the study, has said: “If we can refine these methods, they will allow us to determine much earlier those people who require preventative measures. This will extend people’s lives and conserve NHS resources.

“Although we already have reliable methods of forecasting people according to their degree of risk of serious heart events, artificial intelligence promises new ways of interrogating data and the likelihood of more reliable classification of risk”.

The research team used a technique known as genetic programming (GP) – it’s inspired by the evolution of nature, through which, computer programmes are encoded as a set of genes which are then iteratively changed.

There are several significant benefits to using GP, instead of manually developing an algorithm. One of the more important ones being that there Is less chance for human error or bias, while also allowing for the environmental conditions to be changed at the same time.