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

Early detection of advanced-stage DLBCL using random forest: Uncovering large-scale demographic disparities and site-specific risk patterns

View Full Paper
Ask AI
Bookmark
Share

Authors

JSJunho SongACAsfand Yar CheemaJSJessica Santucci

Discussion

Loading...

Member takes

Overview

Analysis reveals machine learning predicts advanced DLBCL risk in clinical data, indicating targeted screening may enhance outcomes.

Key Points

  • Random forest model predicted advanced DLBCL stage with AUC of 0.723, supporting early intervention.
  • Feature importance analysis highlighted demographics and treatment factors as key in risk prediction.
  • Confusion matrix assessment validated the accuracy of the machine learning approach.
  • Machine learning's use in predicting DLBCL risk may improve clinical decision-making and resource use.

Cite This Study

Song et al. (2025) studied this question.

synapsesocial.com/papers/69362f3d4fa91c937236d4e8https://doi.org/10.1182/blood-2025-7194
View Full Paper
Ask AI
Bookmark
Share