cGvHD

Could a machine-learning algorithm help to better stratify chronic graft-versus-host disease survival and phenotypes?

Machine-learning algorithms have been shown to make medical diagnoses as accurate as doctors in the field of cardiology, dermatology, and oncology.1,2,3 By using machine-learning approaches, diagnostic success may be increased whilst human error rate could be reduced. Jocelyn S. Gandelman from Vanderbilt University Medical Center, Nashville, TN, USA, and colleagues published a study ahead of print in Haematologica assessing machine-learning methods in chronic graft-versus-host disease (cGvHD) patients to identify distinct clusters of phenotypes and survival patterns.4

The study group investigated whether a machine-learning algorithm could diagnose patients according to organ scores, identify phenotypic subgroups and also stratify survival. Clinical data was used from 339 patients.

Key findings:
  • Seven patient groups with contrasting clinical risks were identified
  • High-risk cGvHD patients had poor overall survival in comparison with low-risk cGvHD patients: HR = 2.24 (95% CI, 1.36-3.68)
  • Clinical applicability:
    • Information was converted into a clinical prognostic decision tree
    • Groups were selected by the decision tree
    • Intermediate- and high-risk patients had inferior overall survival compared to patients in the low-risk group: HR = 2.79, HR = 1.78, respectively

This study shows that machine-learning is promising in terms of identifying biomarkers and stratifying risk in patients with cGvHD. The authors stated that “these results have the potential to be applied to stratify risk in the clinical setting, enhance the current cGvHD classification system, refine inclusion criteria for phase II trials, and guide biomarker discovery for more specific therapeutic targets.” Further studies are required to confirm this data.

 

References
  1. Luo G. et al. A novel left ventricular volumes prediction method based on deep learning network in cardiac MRI. Comput Cardiol. 2010;2017:2–5. DOI10.23919/CIC.2016.7868686.
  2. Esteva A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639): 115–118. DOI: 10.1038/nature21056. Epub 2017 Jan 25.
  3. Wang D. et al. Deep learning for identifying metastatic breast cancer. arXiv preprint arXiv: 1606.05718, 2016. http://j.mp/2o6FejM.
  4. Gandelman J.S. et al. Machine learning reveals chronic graft-versus-host disease phenotypes and stratifies survival after stem cell transplant for hematologic malignancies. Haematologica.2018 Sep 20. DOI: 10.3324/haematol.2018.193441. [Epub ahead of print].
Download this article:

You can now download this article in Adobe PDF® format.

Download as PDF
Was this article informative? Thank you for your feedback!
100% of people found this article informative