AI-assisted Endomyocardial biopsy assessment may improve heart transplant outcomes

Cardiac failure is the most common cause of hospitalization in the United States and the most rapidly growing cardiovascular condition globally. For patients with end-stage heart failure, transplantation is often the only viable solution. Cardiac allograft transplantation is associated with significant risk of rejection.

To prevent rejection, patients receive individually tailored immunosuppressive regimens after transplantation. Despite the medications, cardiac rejection remains the most common and serious complication, as well as the main cause of mortality in post-transplantation patients.

Manual interpretation of from Endomyocardial biopsy EMBs is affected by substantial interobserver and intraobserver variability, which often leads to inappropriate treatment with immunosuppressive drugs, unnecessary follow-up biopsies and poor transplant outcomes.

A recent human reader study in Nature Medicine revealed that a deep learning-based artificial intelligence (AI) system was effective in detecting anomalies post transplantation by automated assessment of gigapixel whole-slide images obtained EMBs, which simultaneously addresses, detection, subtyping and grading of allograft rejection effectively .

To assess model performance, researchers curated a large dataset from the United States, as well as independent test cohorts from Turkey and Switzerland, which includes large-scale variability across populations, sample preparations and slide scanning instrumentation.

• The model detects allograft rejection with an area under the receiver operating characteristic curve (AUC) of 0.962; assesses the cellular and antibody-mediated rejection type with AUCs of 0.958 and 0.874,
• Detects Quilty B lesions, benign mimics of rejection, with an AUC of 0.939; and differentiates between low-grade and high-grade rejections with an AUC of 0.833.

Authors concluded that "In a human reader study, the AI system showed non-inferior performance to conventional assessment and reduced interobserver variability and assessment time. This robust evaluation of cardiac allograft rejection paves the way for clinical trials to establish the efficacy of AI-assisted EMB assessment and its potential for improving heart transplant outcomes."

Reference: https://doi.org/10.1038/s41591-022-01709-2