New York: A novel artificial intelligence score provides a more accurate forecast of the likelihood of patients with suspected or known coronary artery disease dying within 10 years than established scores used by health professionals worldwide, researchers have found.
The research, presented at EuroEcho 2021, found that the machine learning (ML) score was able to predict which patients would be alive or dead with 76 per cent accuracy.
“This means that in approximately three out of four patients, the score made the correct prediction,” said researcher Theo Pezel of the US’ Johns Hopkins Hospital.
For the study, the team involved over 30,000 patients referred for stress cardiovascular magnetic resonance (CMR) between 2008 and 2018 because of chest pain, shortness of breath on exertion, or high risk of cardiovascular disease but no symptoms.
High risk was defined as having at least two risk factors such as hypertension, diabetes, dyslipidemia, and current smoking. The average age was 64 years and 66 per cent were men.
Information was collected on 23 clinical and 11 CMR parameters. Patients were followed up for a median of six years for all-cause death, which was obtained from the national death registry in France. During the follow-up period, 2,679 (8.4 per cent) patients died.
ML was conducted in two steps. First, it was used to select which of the clinical and CMR parameters could predict death and which could not. Second, ML was used to build an algorithm based on the important parameters identified in step one, allocating different emphasis to each to create the best prediction.
Patients were then given a score of 0 (low risk) to 10 (high risk) for the likelihood of death within 10 years.
The ML score was able to predict which patients would be alive or dead with 76 per cent accuracy (in statistical terms, the area under the curve was 0.76).
Using the same data, they calculated the 10-year risk of all-cause death using established scores and a previously derived score incorporating clinical and CMR data.