For individuals with end-stage cardiac failure, a heart transplant can save their lives.
Many patients, however, undergo organ transplant rejection, which occurs when the immune system attacks the donated organ.
However, recognizing transplant rejection is difficult since patients may not feel symptoms in the early stages, and doctors do not always agree on the degree and severity of rejection.
To address these issues, Brigham and Women’s Hospital researchers developed the Cardiac Rejection Assessment Neural Estimator (CRANE), an artificial intelligence (AI) system that can identify rejection and evaluate its severity.
The scientists tested CRANE’s efficacy on samples provided by patients from three different nations in a pilot study, finding that it could assist cardiac professionals to diagnose rejection more accurately and reducing examination time.
“Our retrospective pilot study demonstrated that combining artificial intelligence and human intelligence can improve expert agreement and reduce the time needed to evaluate biopsies,” explains sr author Faisal Mahmood. “Our results set the stage for large-scale clinical trials to establish the utility of AI models for improving heart transplant outcomes.”
Heart biopsies are frequently used to diagnose and grade the severity of organ rejection in individuals who have had a heart transplant. Several investigations have revealed, however, that doctors frequently disagree on whether or not the patient is rejecting the heart, as well as the severity of the rejection. Variability in diagnosis has direct therapeutic implications, resulting in treatment delays, unnecessary follow-up biopsies, anxiety, insufficient medication dose, and, ultimately, worse outcomes.
CRANE is intended to be used in conjunction with an expert assessment to help establish an accurate diagnosis more quickly, and it can also be utilized in situations when pathology experts are scarce. Using hundreds of pathology images from over 1,300 heart samples from Brigham, the scientists trained CRANE to detect, subtype, and grade transplant rejection.
The researchers then used test biopsies from Brigham as well as independent, external test sets from hospitals in Switzerland and Turkey to validate the model.
The external validation datasets were created to stress-test the suggested AI model by demonstrating a high degree of variability.
CRANE performed well in terms of detecting and analyzing rejection, with findings that were comparable to those obtained by traditional methods. When experts utilized the technology, it reduced expert disagreement and cut evaluation time in half. The authors acknowledge that its utility in clinical practice is unknown, and they intend to refine the system further, but the findings show the value of incorporating AI into diagnostics.
“Throughout the history of medicine, diagnostic assessments have been largely subjective,” adds Mahmood. “But because of the power and assistance of computational tools, that’s beginning to change. The time is right to make a shift by bringing together people with clinical expertise and those with expertise in computational science to develop assistive diagnostic tools.”
Source: 10.1038/s41591-022-01709-2
Image Credit: Getty
You were reading: New test detects signs of heart-transplant rejection earlier than biopsy
