Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 8, 2025BloodOpen Access

AI-derived prediction of response and relapse to venetoclax plus hypomethylating agent based therapy in Acute Myeloid Leukemia

View Full Paper
Ask AI
Bookmark
Share

Authors

SGSarvarinder GillMAMaher AlbitarJKJamie Koprivnikar

Discussion

Loading...

Member takes

Overview

Machine learning predicts relapse and response in AML patients receiving venetoclax and hypomethylating agents, suggesting personalized treatment strategies.

Key Points

  • This research aims to predict treatment response and relapse in patients with acute myeloid leukemia receiving venetoclax combined with hypomethylating agents using AI models.
  • Retrospective analysis of 128 patients treated with venetoclax plus hypomethylating agents (Ven-HMA).
  • Baseline bone marrow samples underwent next-generation sequencing (NGS) and genomic data was collected.
  • Utilized a Bayesian statistical approach for feature selection and constructed machine learning models, including a random forest classifier.
  • Split cohort into training (60%) and testing (40%) sets.
  • Developed models incorporating RNA expression data using leave-one-out cross-validation (LOOCV).
  • Overall response rate to Ven-HMA was 75%, with 46% of responders relapsing.
  • AI models predicted treatment response with 92.3% sensitivity and 75.7% specificity, AUC of 0.876.
  • Transcriptomic data (20 genes) achieved 94.7% sensitivity and 94.1% specificity for predicting relapse, with an AUC of 0.981.

Cite This Study

Gill et al. (2025) studied this question.

synapsesocial.com/papers/69362f6e4fa91c937236e0adhttps://doi.org/10.1182/blood-2025-1731
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. 1Real-world efficacy and prognostic modeling of venetoclax-enhanced intensive chemotherapy in fit AML2025
  2. 2Machine learning using bayesian networks to predict response in patients with newly diagnosed Acute Myeloid Leukemia2025
  3. 3Genetic risk model to predict outcomes for AML treated with HMA and venetoclax2025
  4. 4IDH1 mutation predicts response and survival in treatment-naïve Acute Myeloid Leukemia patients receiving with venetoclax with a hypomethylating agent2025
  5. 5Predictive Models for Long Term Survival of AML Patients Treated with Venetoclax and Azacitidine or 7+3 Based on Post Treatment Events and Responses: Retrospective Cohort Study2024 · 9 citations