Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 8, 2025BloodOpen Access

Multi-endpoint AI morphology model (MEAM) enhances risk prediction for vascular events and disease progression in MPNs

View Full Paper
Ask AI
Bookmark
Share

Authors

SRSharon RuaneMCMingyi ChenAGAnna L. Godfrey

Discussion

Loading...

Member takes

Overview

AI morphology model enhances risk prediction for vascular events and disease progression in patients with MPNs, indicating improved clinical utility.

Key Points

  • The aim is to enhance risk prediction for vascular events and disease progression in patients with myeloproliferative neoplasms using an AI morphology model.
  • Developed a multi-endpoint AI morphological model from bone marrow samples of MPN patients.
  • Analyzed a dataset of 949 patients using a Cox proportional hazards framework and a vision transformer for prediction.
  • Used 5-fold cross-validation to validate model performance and calculated C-index for risk prediction.
  • MEAM outperformed conventional risk models in predicting overall survival and vascular events in essential thrombocythemia patients.
  • Enhanced risk prediction for secondary myelofibrosis and AML transformation
  • Combined MEAM with existing models significantly improved prediction accuracy across several endpoints.

Cite This Study

Ruane et al. (2025) studied this question.

synapsesocial.com/papers/69362f694fa91c937236df7dhttps://doi.org/10.1182/blood-2025-5599
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1A large language model-based framework for automated phenotypic characterization in myeloproliferative neoplasms2025
  2. 2Machine learning accurately predicts mortality in adult NPM1-mutant Acute Myeloid Leukemia using baseline clinical and genomic features2025
  3. 3Real-world temporal evaluation of static risk prediction in polycythemia vera2025
  4. 4Stem Cell-Derived Gene Expression Scores Predict Survival and Blastic Transformation in Myelofibrosis2024 · 2 citations
  5. 5Integrating the cardiovascular-renal-metabolic syndrome（ckm）: Construction and validation of a comprehensive model for early identification of high-risk multiple myeloma2025