
Using AI to combine patient data with results from a test for levels of a protein made by the heart could help doctors spot heart failure sooner and improve patient care, experts say.
Acute heart failure affects nearly one million people in the UK and accounts for five percent of all unplanned hospital admissions.
It is a life-threatening condition caused when the heart is suddenly unable to pump blood around the body.
Diagnosis is difficult because symptoms, such as shortness of breath and leg swelling, occur in many other illnesses. Previous research has shown that patients who are diagnosed quickly benefit the most from treatment.
Informing decisions
Researchers from the University of Edinburgh and 13 other countries combined data from 10,369 patients with suspected acute heart failure to develop a tool – called CoDE-HF – to inform clinicians’ decisions.
CoDE-HF uses AI to combine routinely collected patient information with results from a blood test for the heart protein NT-proBNP to produce an estimate of whether they suffered heart failure.
The current recommended diagnosis method is to test to see if levels of NT-proBNP are below a certain cut-off value, but this is not widely used as levels can vary depending on an individual’s age, weight and other health conditions.
As well as spotting acute heart failure more accurately than heart protein blood tests on their own, CoDE-HF was especially precise in difficult to diagnose patient groups – such as older people and those with pre-existing medical conditions.