Parkes, Michael D. and Aliabadi, Arezu Z and Cadeiras, Martin and Crespo-Leiro, Maria G and Deng, Mario and Depasquale, Eugene C. and Goekler, Johannes and Kim, Daniel H and Kobashigawa, Jon and Loupy, Alexandre and Macdonald, Peter S and Potena, Luciano and Zuckermann, Andreas and Halloran, Philip F (2019) An integrated molecular diagnostic report for heart transplant biopsies using an ensemble of diagnostic algorithms. Journal of Heart and Lung Transplantation, ePub. ISSN 1557-3117 (Not OA)
Full text not available from this repository.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.
| Item Type: | Article |
|---|---|
| Subjects: | R Medicine > R Medicine (General) |
| Depositing User: | Repository Administrator |
| Date Deposited: | 11 Mar 2019 03:49 |
| Last Modified: | 11 Mar 2019 03:49 |
| URI: | https://eprints.victorchang.edu.au/id/eprint/811 |
Actions (login required)
 |
View Item |