BioProject

We previously reported a microarray-based diagnostic system for heart transplant endomyocardial biopsies (EMBs), using either 3-archetype (3AA) or 4-archetype (4AA) unsupervised algorithms to estimate rejection. The present study aimed to examine the stability of machine-learning algorithms in new biopsies, compare 3AA vs. 4AA algorithms, assess supervised binary classifiers trained on histologic or molecular diagnoses, create a report combining many scores into an ensemble of estimates, and examine possible automated sign-outs. Algorithms derived in cohort 331 performed similarly in new biopsies despite differences in case mix. In the combined cohort, the 4AA model, including a parenchymal injury score, retained correlations with histologic rejection and DSA similar to the 3AA model. Supervised molecular classifiers predicted molecular rejection (AUCs>0.87) better than histologic rejection (AUCs<0.78), even when trained on histology diagnoses. A report incorporating many AA and binary classifier scores interpreted by one expert showed highly significant agreement with histology (p<0.001), but with many discrepancies as expected from the known noise in histology. An automated random forest score closely predicted expert diagnoses, confirming potential for automated sign-outs.Molecular algorithms are stable in new populations and can be assembled into an ensemble that combines many supervised and unsupervised estimates of the molecular disease states. (ClinicalTrials.gov NCT02670408). Overall design: We studied 889 EMBs from 454 transplant recipients at eight centers: the initial cohort (N=331) and a new cohort (N=558). Published 3AA algorithms derived in cohort 331 were tested in cohort 558; the 3AA and 4AA models were compared; and supervised binary classifiers were created.