An integrated molecular diagnostic report for heart transplant biopsies using an ensemble of diagnostic algorithms

J Heart Lung Transplant. 2019 Jun;38(6):636-646. doi: 10.1016/j.healun.2019.01.1318. Epub 2019 Feb 6.

Abstract

Background: 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. In the present study we examined the stability of machine-learning algorithms in new biopsies, compared 3AA vs 4AA algorithms, assessed supervised binary classifiers trained on histologic or molecular diagnoses, created a report combining many scores into an ensemble of estimates, and examined possible automated sign-outs.

Methods: We studied 889 EMBs from 454 transplant recipients at 8 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.

Results: A`lgorithms 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 (areas under the curve [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 1 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 signouts.

Conclusions: 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.

Keywords: T-cell‒mediated rejection; antibody-mediated rejection; heart transplant; injury; microarray.

Publication types

  • Research Support, Non-U.S. Gov't

MeSH terms

  • Adolescent
  • Adult
  • Aged
  • Algorithms*
  • Child
  • Child, Preschool
  • Cohort Studies
  • Female
  • Graft Rejection / etiology*
  • Graft Rejection / pathology
  • Heart Failure / etiology
  • Heart Failure / pathology*
  • Heart Failure / surgery
  • Heart Transplantation*
  • Humans
  • Machine Learning*
  • Male
  • Middle Aged
  • Myocardium / pathology*
  • Pathology, Molecular
  • Predictive Value of Tests
  • ROC Curve
  • Risk Assessment
  • Young Adult