Researchers demonstrate value of AI in predicting heart disease

Researchers from the Radcliffe Department of Medicine at the University of Oxford have published a study looking at how artificial intelligence (AI) could help in the diagnosis of heart disease.

The study, funded by the British Heart Foundation and supported by the National Institute for Health and Care Research Oxford Biomedical Research Centre, analysed routine cardiac computed tomography (CT) scans and clinical data from over 40,000 people at eight hospitals in the UK. Patients were followed for a period of up to 10 years to identify whether they experienced any major cardiac events such as heart attacks, heart failure or cardiac death.

While the minority of people with significant coronary artery narrowing on the initial CT scan were more likely to have serious cardiac events or death, two-thirds of these serious cardiac events happened among those who did not have significant narrowings of the arteries in their initial CT scan.

Kenneth Chan, a clinical research fellow at the University of Oxford and first author of the article, said: “AI technology can detect the level of inflammation of the heart arteries, by detecting changes in the fat tissue around arteries that are not visible to the human eye. In this way we can identify patients with high inflammation and high risk.”

The research team used the technology to give patients an AI risk-score based on the level of inflammation of their heart arteries, combined with the patient’s health background, including age, sex and whether they smoke, have diabetes, and/or high blood pressure.

The study showed that the AI risk-score could accurately predict the likelihood of cardiac events in the next 10 years. Since the prediction aligned well with the real-life cardiac events that were experienced by the patients in the study, the researchers believe the AI risk-score would also be able to identify when the cardiac events would occur.

During a pilot study that involved integrating this technology in four NHS hospitals, researchers provided AI-generated risk scores to doctors for 744 patients. In around 45% of cases, doctors altered their patients’ treatment plan as a result.

One of the co-investigators, David Adlam from the University of Leicester, said: “We have demonstrated that providing a more precise picture of cardiac risk to clinicians and patients can trigger timely administration of preventive treatments that could lead to less heart attacks and cardiac deaths.”

Bryan Williams, chief scientific and medical officer at the British Heart Foundation, said: “Technological advances like this are increasingly valuable in guiding treatment decisions, helping clinicians intervene at the right time to help patients avoid these devastating conditions.

“It is vital that we harness the power of AI to prevent countless unnecessary heart-related deaths. We hope this technology will be rolled out widely across the NHS to support everyone at risk.”

The technology is currently being piloted in a number of UK hospitals to see how the AI tools can be integrated with current NHS care.

The paper, Inflammatory risk and cardiovascular events in patients without obstructive coronary artery disease: The Orfan multicentre, longitudinal cohort study, was published in The Lancet last week.