Abstract 13830: Prediction of Cardiac Rejection Trajectories via Machine Learning Derived Features From Digital Endomyocardial Biopsy Images

Abstract

Introduction: Cellular rejection occurs in 20-40% of transplant recipients with an increased risk of graft failure. Previously, we developed a model for predicting ISHLT rejection grades via the automated extraction of morphologic features in Endomyocardial biopsy (EMB) images. Considering the frequent discordance between conventional rejection grade and clinical rejection severity, in this work, we sought to identify morphologic features that predict the clinical trajectory of rejection events. Methods: Our study comprised 299 EMBs with grade and trajectory labels. Trajectory labels are based on the development of overt clinical signs of allograft injury as “clinically evident” or “clinically silent”. Morphologic features describing number, spatial arrangement of lymphocytes, and shape, orientation of interstitial fibers were computationally extracted. To identify the top features associated with clinically evident disease, the T-test method was applied across 500 iterations of 3-fold cross validation. In each iteration, a quadratic discriminant analysis model was trained with top 10 features on 2 folds of dataset using trajectory labels (M trj ) and was validated on one hold out test set. This model was trained using grade labels (M grd ) to predict “high” (2R + 3R) or “low” (0R + 1R). To assess feature importance, in each model, the frequency of every feature appearing in the classifier was measured through iterations. Results: The mean area under the receiver operating curve of M trj and M grd was 0.80±0.04 and 0.84±0.02 correspondingly. The top features for predicting grades differ substantially from those for predicting clinical trajectory (Figure 1). Conclusions: The additional features required to predict clinical trajectory vs. rejection grade may explain the discordance between conventional histology and rejection syndrome observed in clinical practice, and highlights the translational potential of computer-assisted histologic analysis of EMBs.