Organ donation: Stanford University clinicians and data scientists have built a machine-learning model that predicts whether a donor who has life support withdrawn will die within the 45-minute window needed to preserve organs from donations after circulatory death (DCD).
In liver transplantation, about half of planned DCD recoveries are cancelled because death occurs too late, wasting time, money and scarce clinical resources.
Also Read | India urges states to upgrade trauma centres to boost organ donation
Trained on data from more than 2,000 donors across multiple US centres, the model ingests neurological, respiratory and circulatory metrics to forecast progression to death. In retrospective and prospective testing, it outperformed senior surgeons’ estimates and cut “futile procurements”, cases where teams mobilise only to stand down, by roughly 60%, the team reported in The Lancet Digital Health.
“By identifying when an organ is likely to be useful before any preparations for surgery have started, this model could make the transplant process more efficient,” said senior author Dr Kazunari Sasaki, a clinical professor of abdominal transplantation. He added that better triage could also increase the number of patients who ultimately receive a transplant.
The tool maintained accuracy even when some donor information was missing, the researchers said. Beyond easing operational strain on transplant programmes, a reliable, data-driven prediction could improve organ utilisation from DCD donors. The team plans to adapt and trial the approach for heart and lung transplantation next.
