AI technology is achieving remarkable feats all over the world and hospitals are also effectively using it to detect various disease.
As per BBC, Imperial College and Chelsea and Westminster hospital NHS foundation trusts in London are using AI technology to predict if patients will develop type 2 diabetes up to 10 years before the condition actually occurs.
The trusts have begun training an AI system called Aire-DM. This system examines patients’ ECG (electrocardiogram) heart traces to find early warning signs of health problems that are difficult for doctors to identify through traditional methods.
Early results show that the system can identify risk correctly around 70% of the time.
Type 2 diabetes is a common condition in which the blood sugar levels are too high and if the disease is not properly managed, it can lead to serious health problems like heart attacks and strokes.
Dr Fu Siong Ng, lead researchers explains that providing the AI with more information about a patient’s background, such as their age, sex and whether they have high blood pressure or are overweight, can make the AI system more effecting at predicting health risks.
He said, "It is already quite good just with the ECG data, but it is even better when you add in those."
Dr.Ng explains that the changes in the ECG detected by the system are too diverse that even highly skilled doctors cannot interpret them correctly.
During the trial, up to 1,000 patients at both hospitals will have their ECG scans checked by the AI system to see if it can help in detecting diseases.
However, this technology will not be used regularly just yet, experts are hopeful that it could be eventually be introduced more broadly in the NHS.