AI HEALTHCARE
The NHS needs this tech yesterday
Stanford doctors have built an AI tool that could cut wasted organ-transplant attempts by 60%.
Thousands of people need life-saving organs, but there aren’t enough available.
For liver transplants, hospitals now use donors who die after cardiac arrest (DCD donors).
The issue is timing: the donor must pass away within 45 minutes to keep the liver usable.
In about half of these cases, that doesn’t happen, so the transplant is cancelled after preparations have already begun.
Hospitals usually rely on surgeons’ judgment to predict this timing, and it can be unpredictable and costly.
The new AI model helps by predicting whether a donor is likely to die within that critical window. In tests, it performed better than senior surgeons.
Key points from the research:
AI cut unnecessary organ-recovery attempts by 60%.
It predicted outcomes more accurately than human experts.
It could save time, money, and increase usable donor organs.
A win for donors and recipients
It was trained on data from more than 2,000 donors across several US hospitals, using neurological, respiratory and circulatory information.
It also works well even if some data is missing.
Researchers say this tool could help staff make clearer decisions, reduce wasted effort, and possibly increase the number of successful transplants.
The study was published in The Lancet Digital Health. The team now plans to adapt the tool for heart and lung donations.
I don’t know that I would want an AI predicting if I was going to die within 45 minutes, but if it saves lives, I guess that’s good? - MV