ReachRxResearch
Home
Research
Sign Up
Artificial intelligence in myeloproliferative neoplasms: From digital bone marrow pathology to clinical decision support
Back to Research Hub
  1. Home
  2. Research Hub
  3. Artificial intelligence in myeloprolifer…

Artificial intelligence in myeloproliferative neoplasms: From digital bone marrow pathology to clinical decision support

Blood Reviews·October 23Open Access
HematologyLimited evidenceMyelofibrosisMyeloproliferative NeoplasmsNarrative ReviewArtificial IntelligenceDeep LearningMachine LearningNatural Language ProcessingMixed

Summary

View source

What was studied

This narrative review (PubMed/MEDLINE searched through August 2026) evaluated the evidence for AI, machine learning, and deep learning applications across the full myeloproliferative neoplasm (MPN) continuum — from automated bone marrow biopsy analysis and blood count-based diagnosis to risk stratification, therapy response prediction, drug discovery, and EHR mining.

Key findings

AI has produced meaningful technical advances across multiple MPN domains, but most published models rely on internal or single-cohort validation only; prospective evaluation has been reported solely for blood count-based fibrosis prediction, and no tool has yet been shown to change clinical decision-making or improve patient outcomes.

Study limitations

As a narrative review, it is subject to selection bias in the literature appraised. The majority of underlying studies lack external validation, limiting generalizability. Conference abstracts were included, introducing risk of reporting immature or unvetted findings.

Clinical implications

Clinicians should treat current AI tools in MPN as research-stage aids: predictive performance alone does not equal clinical utility, and no AI tool has yet been prospectively shown to improve patient outcomes. Prospective, externally validated studies are needed before these tools can be adopted in routine care.

Caveats

  • Inclusion of conference abstracts alongside peer-reviewed studies means some findings may reflect preliminary or unvetted data
  • Most underlying studies assessed in this review used only internal or single-cohort validation, substantially limiting the generalizability of reported model performance
  • No AI tool reviewed has been prospectively validated to change clinical decision-making or improve patient outcomes in MPN — predictive accuracy should not be equated with clinical utility

Related Questions

Explore related topics

What AI or machine learning tools are available for bone marrow fibrosis grading in myelofibrosis?How accurate are blood count-based machine learning models for predicting bone marrow fibrosis in MPN?What are the current validated risk stratification models for thrombosis and disease progression in myeloproliferative neoplasms?

Publication Details

Year
2026
Journal
Blood Reviews
Source
View article
Keep scrolling
More content below.
Up Next