Scientists have developed a new artificial intelligence-based tool that can predict life expectancy of heart failure patients. The technology could help clinicians to make more informed decisions while caring for such patients.
The researchers, including those from the University of California (UC) at San Diego in the US, said while predicting mortality is important in patients with heart failure, current strategies for evaluating this risk are only modestly successful and can be subjective.
As part of the study, published in the journal European Journal of Heart Failure, the researchers developed a machine learning algorithm based on de-identified electronic health records data of nearly 6,000 heart failure patients at UC San Diego Health in the US.
They developed a risk score that determined low- and high-risk of death by identifying eight variables collected from the majority of patients with heart failure.
These variables include blood pressure during heart relaxation, the amount of white blood cells, albumin, haemoglobin, platelets, and urea and nitrogen in the blood, and the level of creatinine—a chemical waste product from amino acid breakdown that is excreted via urine, the study noted.
Using these inputs, the researchers said, the newly developed model could accurately predict life expectancy 88 per cent of the time, and performed substantially better than other popular published models.
“This tool gives us insight, for example, on the probability that a given patient will die from heart failure in the next three months or a year,” said Eric Adler, co-author of the study from UC San Diego.
The researchers, however, added that the study needs further validation with more tests on larger groups of people.