Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 8, 2025Blood

Redefining the myeloid disease continuum: Machine learning–based development and validation of an integrated multimodal classification of myeloid neoplasms

View Full Paper
Ask AI
Bookmark
Share

Authors

MPManuel Pérez‐EncinasHHHsin‐An Hou

Discussion

Loading...

Member takes

Overview

Machine learning identifies prognostic score and genomic features in myeloid neoplasms, suggesting refined treatment approaches.

Key Points

  • The model projects patients onto a continuous 3-dimensional space, revealing significant structure across myeloid neoplasms.
  • An unsupervised random forest algorithm validated prognostic score reached a robust c-index of 0.84 across 2012 cases.
  • Clustering revealed 58 distinct subclusters, with TP53 alterations indicating varying outcomes, highlighting disease complexity.
  • Integrating clinicopathologic and genomic data suggests novel pathways for treatment selection in myeloid neoplasms.

Cite This Study

Pérez‐Encinas et al. (2025) studied this question.

synapsesocial.com/papers/69362f6e4fa91c937236e131https://doi.org/10.1182/blood-2025-4347
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. 1Machine learning uncovers invariant evolutionary molecular trajectories in MDS.2025
  2. 2Machine learning uncovers prognostically distinct myeloma cast nephropathy phenotypes not captured by standard risk stratification systems2025
  3. 3Which molecular patterns of high-risk myeloid malignancies are concordantly identified using two machine learning algorithms?2025
  4. 4Molecular subclusters across the continuum of myelodysplastic neoplasms and acute myeloid leukaemia define distinct clinical entities2025
  5. 5Consideration of genomic determinants improves the diagnostic accuracy of oligomonocytic chronic myelomonocytic leukemia2025