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

Developing artificial intelligence-based transcriptomic signature for the diagnosis of dark zone lymphoma in patients without MYC gene rearrangement

View Full Paper
Ask AI
Bookmark
Share

Authors

AIAndrew IpSASally AgersborgACAhmad Charifa

Discussion

Loading...

Member takes

Overview

AI identifies transcriptomic signature in DLBCL without MYC alteration, suggesting 14% misdiagnosis of DZL.

Key Points

  • To establish an artificial intelligence-defined transcriptomic signature for diagnosing dark zone lymphoma.
  • Extracted RNA from lymph node samples of 363 lymphoma cases.
  • Employed next generation sequencing and hybrid capture to analyze RNA from high-grade lymphoma cases.
  • Utilized Bayesian statistics and XGBoost to differentiate dark zone lymphoma from DLBCL without MYC rearrangement.
  • Achieved an AUC of 0.927 distinguishing DZL from DLBCLn using 6 key genes.
  • Increased delineation accuracy to AUC of 0.962 with 50 genes in the model.
  • Discovered that 10 out of 187 DLBCLn patients had a DZ transcriptomic signature indicating potential misclassification.

Cite This Study

Ip et al. (2025) studied this question.

synapsesocial.com/papers/69362f7f4fa91c937236e56dhttps://doi.org/10.1182/blood-2025-3525
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. 1An immunohistochemical germinal center B-cell dark zone signature identifies Burkitt lymphoma and molecular high-grade B-cell lymphomas2025 · 3 citations
  2. 2Abstract IA007: Dark zone lymphomas2026
  3. 3Real-world patient-based next-generation sequencing assessments identify a high-risk subgroup and associated gene signature in diffuse large B cell lymphoma2025
  4. 4AI for prognostic assessment of diffuse large B‐cell lymphoma using H&E whole‐slide images2026
  5. 5Non-invasive classification & molecular subtyping of mature lymphoid neoplasms by cell-free DNA profiling2025