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

Integrated machine learning-based prognostic models for patients with Myelodysplastic Syndromes/neoplasms (MDS)

View Full Paper
Ask AI
Bookmark
Share

Authors

XWXin WangZXZefeng XuBJBo Jiang

Discussion

Loading...

Member takes

Overview

Prognostic models integrate clinical factors and molecular data to enhance patient risk assessment in MDS.

Key Points

  • Machine learning predicts prognosis more accurately in patients with myelodysplastic syndromes, with a Brier score of 0.140.
  • The integrated model achieved a C-index of up to 0.708, outperforming existing models like IPSS-R and IPSS-M.
  • Analysis employs random survival forests to combine biological and clinical factors in 687 MDS patients across multiple cohorts.
  • Results support tailored treatment strategies for the elderly population, particularly those receiving hypomethylating agent treatment.

Cite This Study

Wang et al. (2025) studied this question.

synapsesocial.com/papers/69362f514fa91c937236d904https://doi.org/10.1182/blood-2025-7385
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. 1Enhanced IPSS-m: A comorbidity-integrated model for improved clinical risk stratification in myelodysplastic neoplasms2025
  2. 2Prognostic impact of pre-transplant IPSS-m risk downstaging in Myelodysplastic Syndromes2025
  3. 3IPSS-m outperforms IPSS-R in younger adults with Myelodysplastic Syndromes: A retrospective age-stratified analysis2025
  4. 4Comparative evaluation of ipss-m and cpss-mol in CMML: Impact of molecular markers on prognosis2025
  5. 5Clonal evolution and risk assessment in myelodysplastic syndromes (MDS): A prospective Study of dynamic IPSS-m validation and evolutionary trajectory modeling by the italian MDS foundation (FISIM)2025