New algorithm more accurately predicts life expectancy after heart failure

May 17, 2018, University of California, Los Angeles
The Trees of Predictors algorithm uses machine learning and 53 data points to more accurately predict life expectancy after heart failure. Credit: UCLA Samueli

A new algorithm developed by UCLA researchers more accurately predicts which people will survive heart failure, and for how long, whether or not they receive a heart transplant. The algorithm would allow doctors to make more personalized assessments of people who are awaiting heart transplants, which in turn could enable health care providers to make better use of limited life-saving resources and potentially reduce health care costs.

As precision medicine gains ground in health care, this study could be a key step toward tailoring organ procedures to individual patients. The study, which was published in PLOS One, was led by Mihaela van der Schaar, Chancellor's Professor of Electrical and Computer Engineering at the UCLA Samueli School of Engineering.

The algorithm, which the researchers call Trees of Predictors, uses machine learning—meaning that computers effectively "learn" from additional new data over time. It takes into account 53 data points—including age, gender, body mass index, blood type and blood chemistry—to address the complex differences among people waiting for and the compatibility between potential transplant recipients and donors.

Trees of Predictors uses these 53 data points to predict how long people with heart failure will live, based on whether they receive a transplant or not. (Of those data points, 33 relate to information about the recipients or potential recipients, 14 pertain to the donors and six apply to the compatibility between donor and recipient.)

The researchers tested the Trees of Predictors on 30 years of data on people who were registered with the United Network for Organ Sharing, the nonprofit organization that matches donors and transplant recipients in the U.S. They found that their algorithm provided significantly better predictions for how long someone would live for than the current methods that providers use.

It also outperformed predictions from machine learning methods that have been developed by other research groups.

"Our work suggests that more lives could be saved with the application of this new machine-learning-based algorithm," said van der Schaar, who also is a Turing 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."

The algorithm is able to analyze many possible risk scenarios for potential transplant candidates to help doctors more thoroughly assess people who could be candidates for heart transplants, and it is flexible enough to incorporate more data as treatments evolve.

"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 Dr. Martin Cadeiras, 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."

For example, when compared against prediction models that most doctors currently use to project which transplant recipients would live for at least three years after a transplant, a commonly used benchmark, the UCLA algorithm outperformed the models by 14 percent—correctly predicting that 2,442 more of the 17,441 who received transplants and lived at least that long after the surgery.

Van der Schaar said that the Trees of Predictors could be used for insights from medical databases and many other types of complex databases. Already, Yoon, Zame and van der Schaar have shown it can work to recognize handwriting, and to predict credit card fraud and the popularity of specific news items.

Explore further: Optimizing the use of organs donated from overdose deaths could help to address the national organ shortage

More information: Jinsung Yoon et al. Personalized survival predictions via Trees of Predictors: An application to cardiac transplantation, PLOS ONE (2018). DOI: 10.1371/journal.pone.0194985

Related Stories

Optimizing the use of organs donated from overdose deaths could help to address the national organ shortage

April 16, 2018
The number of organs donated as a result of overdose death has increased 24-fold since 2000 and transplants with those organs have similar outcomes to transplants with organs donated after trauma or natural death. Optimizing ...

Alternatives to whole liver transplants for children have become safer, study finds

February 7, 2018
In a new Johns Hopkins study of patient and graft survival trends for pediatric liver transplant recipients between 2002 and 2015, researchers found that outcomes for alternatives to whole liver transplantation (WLT), such ...

New method for organ transplant monitoring promises better care for patients

August 3, 2017
Using a combination of DNA sequencing and computer science techniques, a team of researchers has developed a new method for monitoring the health of organ transplant patients - one that promises to provide life-saving clues ...

Eliminating blood test may increase availability of donor hearts

June 21, 2016
A blood test that leads to the rejection of donor hearts may be unnecessary in predicting whether a heart transplant will succeed or fail, according to new research in Circulation: Heart Failure, an American Heart Association ...

Transplant donors and recipients want more information about each others' health

August 13, 2015
Both donors and recipients want more information about each others' health before participating in transplant surgeries, according to a study appearing in an upcoming issue of the Clinical Journal of the American Society ...

Study finds low rate of cancer screening among transplant patients

May 9, 2017
People who have received organ transplants are at higher risk of developing and dying of cancer than the general population. Yet their rates of cancer screening do not meet existing guidelines, a new study has found.

Recommended for you

Genomic autopsy can help solve unexplained cardiac death

August 15, 2018
Molecular autopsies can reveal genetic risk factors in young people who unexpectedly die, but proper interpretation of the results can be challenging, according to a recent study published in Circulation.

Neonatal pig hearts can heal from heart attack

August 15, 2018
While pigs still cannot fly, researchers have discovered that the hearts of newborn piglets do have one remarkable ability. They can almost completely heal themselves after experimental heart attacks.

Fifty percent of cardiovascular patients suffer from multiple diseases

August 15, 2018
New research led by The University of Western Australia has revealed that one in two patients admitted to hospital with a cardiovascular disease is suffering from multiple chronic medical conditions which required complex ...

Innovative triple pill significantly lowers blood pressure, study finds

August 14, 2018
A new low dose three in one pill to treat hypertension could transform the way high blood pressure is treated around the world.

Drug repurposing study sheds light on heart disease risk

August 14, 2018
A team led by researchers at Brigham and Women's Hospital has developed a computational technique to reveal the unknown side effects—both good and bad—of hundreds of drugs. That knowledge could help pharmacologists discover ...

Rethinking the stroke rule 'time is brain'

August 13, 2018
In 1993, neurologist Camilo R. Gomez, MD, coined a phrase that for a quarter century has been a fundamental rule of stroke care: "Time is brain!"

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.