Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 9, 2026Beni-Suef University Journal of Basic and Applied SciencesOpen Access

Multicohort transcriptomic integration and machine learning-based diagnostic modeling for myelodysplastic syndromes

View Full Paper
Ask AI
Bookmark
Share

Authors

RERana Hossam EldenNSNancy M. Salem

Discussion

Loading...

Member takes

Overview

Randomized trial identifies gene expression signatures in myelodysplastic syndromes, suggesting new diagnostic pathways.

Key Points

  • This study aims to improve diagnostic accuracy for myelodysplastic syndromes by identifying gene expression signatures and key pathways.
  • Utilized integrative transcriptomic analysis of four microarray datasets (N=461 samples).
  • Identified differentially expressed genes (543 total), followed by functional enrichment analysis and protein–protein interaction (PPI) network construction.
  • Trained a Support Vector Machine (SVM) classifier using 20 hub genes; validated with external datasets (GSE114922 and GSE2779).
  • SVM classifier achieved 99.39% accuracy and AUC of 0.9998.
  • 100% sensitivity and over 91% accuracy in external validation cohorts.
  • Identified functional disruptions in erythropoiesis and immune-related pathways associated with MDS.

Cite This Study

Elden et al. (2026) studied this question.

synapsesocial.com/papers/6a4f3c8a2b81a944af575d7bhttps://doi.org/10.1186/s43088-026-00767-6
View Full Paper
Ask AI
Bookmark
Share