New AI tool could cut wasted efforts to transplant organs by 60% | Organ donation

Doctors have developed an artificial intelligence tool that can reduce wasted organ transplant efforts by 60%.

Thousands of patients around the world are waiting for a potentially life-saving donor, and more candidates are stuck on waiting lists than there are available organs.

Recently, in cases where people need a liver transplant, access has been expanded to include the use of donors who have died after cardiac arrest. However, in approximately half of donations following cardiovascular death (DCD), the transplant is discarded.

This is because the time between turning off life support and death should not exceed 45 minutes. If the donor does not die within the time required to preserve organ quality, surgeons often discard the liver due to the increased risk of complications in the recipient.

Now doctors, scientists and researchers at Stanford University have developed a machine learning model that predicts whether a donor is likely to die during the period of time during which their organs will be viable for transplantation.

The AI ​​tool outperformed the judgment of leading surgeons and reduced by 60% the number of wasteful purchases that occur when preparations for a transplant have already begun but the donor dies too late.

“By identifying when an organ might be useful before any preparation for surgery begins, this model could make the transplant process more efficient,” said Dr. Kazunari Sasaki, clinical professor of abdominal transplantation and senior author of the study.

“It may also allow more candidates who need an organ transplant to receive one.”

Details of the breakthrough were published in Lancet Digital Health.

This progress could reduce the number of times health care providers prepare organs for recovery only to determine they are unsuitable for recovery and transplantation, creating a financial and operational burden on transplant centers.

Hospitals rely primarily on the judgment of surgeons to estimate these critical timings, which can vary widely and result in unnecessary costs and wasted resources.

The new artificial intelligence tool was trained on data from more than 2,000 donors from several US transplant centers. It uses neurological, respiratory and circulatory data to predict the progression of a potential donor's death with greater accuracy than previous models and human experts.

The model was tested retrospectively and prospectively, resulting in a 60% reduction in wasteful purchases compared to surgeons' predictions. Importantly, the researchers say it remains accurate even if some donor information is missing.

A reliable, data-driven tool can help healthcare staff make more informed decisions, optimizing organ utilization and reducing wasted effort and costs.

According to the research team, this approach could represent a significant advance in the field of transplantation, highlighting “the potential of advanced artificial intelligence techniques to optimize the use of DCD donor organs.”

Next, they plan to modify the artificial intelligence tool to test it in heart and lung transplants.