Researchers from the University of California, Los Angeles (UCLA) have developed an algorithm capable of accurately predicting which patients will survive a heart transplant and for how long. Findings were published March 28 in PLOS One.
In this study, led by Mihaela van der Schaar, Chancellor's Professor of Electrical and Computer Engineering at UCLA, researchers tested the “Trees of Predictors” algorithm in its ability to predict life expectancy in heart failure patients.
The Trees of Predictors uses machine learning to analyze 53 data points—33 related to information about recipients or potential recipients, 14 pertaining to the donors and six focusing on compatibility between donor and recipient. Additionally, the data points may help predict how long a patient with heart failure will live if they have the transplant.
"Following this method, we are able to identify a significant number of patients who are good transplant candidates but were not identified as such by traditional approaches," said Martin Cadeiras, MD, a cardiologist at the David Geffen School of Medicine at UCLA. "This methodology better resembles the human thinking process by allowing multiple alternative solutions for the same problem but taking into consideration the variability of each individual."
Researchers tested the accuracy of the algorithm on 30 years' worth of data from patients in the United Network for Organ Sharing. Researchers found it outperformed predictions made by other machine learning methods and those made by providers.
"Our work suggests that more lives could be saved with the application of this new machine-learning-based algorithm," said van der Schaar, a fellow at the Alan Turing Institute in London, and the Man Professor at University of Oxford. "It would be especially useful for determining which patients need heart transplants most urgently and which patients are good candidates for bridge therapies such as implanted mechanical-assist devices."