Hasty Briefsbeta

Bilingual

Machine learning-driven investigation on liquid-liquid phase separation-related prognostic signature in diffuse large B-cell lymphoma - PubMed

4 hours ago
  • #machine-learning
  • #lymphoma-research
  • #prognostic-signature
  • A study aimed to develop a liquid-liquid phase separation (LLPS)-related prognostic model for risk stratification in diffuse large B-cell lymphoma (DLBCL).
  • Using transcriptomic and clinical data from 768 patients across four cohorts, machine learning algorithms identified six prognostic LLPS-related genes (LRGs) to construct the model.
  • The 6-LRG model effectively stratified patients into risk groups with significantly different overall survival, demonstrating strong predictive performance (1-year AUC: 0.661-0.820, 3-year: 0.683-0.779, 5-year: 0.711-0.807).
  • The model remained independent of established clinical variables and improved risk prediction when integrated into a nomogram.
  • Distinct biological and immune microenvironment characteristics were observed between risk groups, suggesting potential underlying mechanisms.
  • Prospective validation in larger populations is essential before clinical implementation of the model.