New algorithms help surgeons make high-stakes transplant decisions in minutes

A new generation of artificial intelligence (AI) tools could help save more patients who need heart transplants by making better use of donor hearts that are currently discarded, according to research presented today by Brian Wayda, MD, at International Society for Heart and Lung Transplantation (ISHLT) 46th Annual Meeting and Scientific Sessions.

"There is a massive shortage of heart donors in the United States, with patients waiting months-if not longer-for a transplant, often on life support in the ICU. So the stakes are very high," said Dr. Wayda, an Assistant Professor of Medicine at NYU Grossman School of Medicine and Heart Failure and Transplant Cardiologist.

AI tools offer surgeons assistance in complex decision-making

Recently developed AI tools are designed to help transplant teams make the complex decision to accept or decline a donor heart in a more data-driven, consistent, and efficient way. Despite the shortage of hearts in the U.S., only about 30–40% of the hearts that become available are actually used for transplant. Research shows that not all donor hearts are justifiably discarded.

When a heart becomes available, a cardiologist or surgeon typically has just 15 to 30 minutes to consider myriad factors, including the donor's history, imaging, and lab tests, to determine whether the heart is a good match for a specific patient.

It's an extremely complex judgment call that must be made in a very short time window, often in the middle of the night."

Brian Wayda, Assistant Professor of Medicine, NYU Grossman School of Medicine

"AI can support these life‑and‑death decisions made under extreme time constraints," said Dr. Wayda.

AI tools to synthesize risk – without replacing clinicians

Dr. Wayda outlined several AI models, including a web-based prediction tool he developed in collaboration with ISHLT President-Elect Kiran Khush, MD, heart failure cardiologist at Stanford Health Care. TOPHAT (Tool Predicting Heart Acceptance for Transplant) uses 20 donor characteristics to estimate the probability that a transplant center will accept a donor heart, based on historical data. Use of this tool could increase the efficiency of the donor process, reducing the likelihood that hearts go unused simply because time runs out before a recipient match is found.

"The tool doesn't say 'this is a good heart' or 'this is a bad heart,'" Dr. Wayda explained. "Instead, it quickly shows how a donor compares to the national experience. An older donor, or one with a single risk factor like cocaine use, may look high-risk at first glance. But when you consider all the variables at once, that donor may not be any riskier than a typical heart we already use."

Goal of AI development is ensuring viable hearts are used, not discarded

A second tool provides AI-assisted reading of echocardiograms, a key test of heart function, as a second opinion for physicians.

"Measuring ejection fraction from an echocardiogram is notoriously subjective," said Dr. Wayda. "We've shown that AI-based reads can be more consistent and a better match to expert interpretation."

Dr. Wayda also described a future goal: a unified decision-support report that would synthesize outputs from TOPHAT, AI-assisted echocardiogram readings, other emerging AI tools, and the broader donor medical record into a single, easy-to-digest summary for clinicians making time-sensitive decisions.

"With this kind of integrated view, doctors would be less likely to anchor their decision on a single 'red flag' – such as donor age over 50 – and decline hearts that could have performed well."

Throughout his talk, Dr. Wayda emphasized that AI is a decision support tool, not an autonomous decision-maker.

"The real value of AI is helping us synthesize a huge amount of data quickly and objectively so clinicians can make better-informed choices," he said.

Even modest gains in donor heart utilization could have a significant impact on the transplant wait list, which includes nearly 4,000 patients.

"An incremental improvement of 500 additional hearts would be enough to reduce wait time substantially," he said.

Technology alone won't fix policy and incentives

Dr. Wayda also argued that AI innovations must be paired with policy reforms to change how centers are graded and incentivized.
"I think there's a temptation to think we can 'tech' our way out of this problem," he said. "We need to reshape transplant policy to align with the goal of using more donors."

For AI tools to make a real-world impact, Dr. Wayda noted, they must also be embedded into the existing national transplant infrastructure.

"We can build beautiful web tools, but a surgeon isn't going to log into a separate site," he said. "To be useful, AI must be integrated into the standard electronic platforms part of the normal data pipeline we already use to review donors."