AI shows potential in detecting kidney allograft failure, says international study funded by French National Institutes of Health and published in Nature Medicine. The study evaluated algorithms’ use to reclassify diagnoses indicating allograft rejection in adult and pediatric kidney transplant recipients and showed that the Banff Automation System reclassified 83 of 279 (29.75%) antibody-mediated rejection cases and 57 of 105 (54.29%) T cell-mediated rejection cases. A review of 3,239 (7.32%) biopsies diagnosed as non-rejection by pathologists were identified by the algorithm as rejection in 237 cases. The results suggest that AI can be a valuable tool in protecting allografts and reducing the impact on a limited organ supply. In a press release, the data scientist Daniel Yoo refers to the system as “somewhat like a ChatGPT specialized for rejections.”
