International researchers use AI to assess allograft health

Important points:

• Researchers have shown in a five-year study that artificial intelligence can be a valuable tool in detecting signs of allograft failure.
• Protecting allografts can help reduce the impact on limited organ supplies.

In this interview with Healio, alexandagain Loopy, MD, PhD, We describe the results of a five-year international study examining the value of artificial intelligence in detecting signs of allograft renal failure.

Roupie, professor of nephrology and epidemiology at the Neckar Hospital in Paris and director of the Paris Institute for Multi-Organ Transplantation and Organ Regeneration, told Healio: “Rejection is the leading cause of allograft loss.

The study, conducted in 20 transplant centers in Europe and the United States, was funded by the French National Institutes of Health. natural medicine.

In this study, researchers used algorithms to evaluate how to reclassify diagnoses indicative of allograft rejection in adult and pediatric kidney transplant recipients. In a review of 4,409 biopsies from 3,054 patients, the Banff Automation System used by the research team found that 83 of 279 (29.75%) cases of antibody-mediated rejection and 57 of 105 (54.29%) cases of antibody-mediated ) reclassified a case of T-cell-mediated rejection to a diagnosis of no. rejection.

A review of 3,239 (7.32%) biopsies diagnosed as non-rejected by pathologists was identified as 237 rejected by the algorithm.

“This study demonstrates the potential of automated histologic classification to improve care for transplant patients by correcting diagnostic errors and standardizing allograft rejection diagnoses,” the authors wrote. I’m here.

“It’s like ChatGPT, focused on rejection.” Daniel Yu, MpH, A data scientist at the Paris Institute for Transplantation and Organ Regeneration and co-first author of the study, said a press release. “We have developed a system that is intelligent and easy to use.”