December 8, 2025BloodOpen Access

AI-based classification and outcome prediction in BCR::ABL1-like B-cell precursor acute lymphoblastic leukemia patients using targeted RNA-seq

View Full Paper

Ask AI

Bookmark

Authors

JRJordi Ribera MMMireia Morgades RARosa Ayala

Discussion

Member takes

Overview

Artificial intelligence models demonstrate predictive potential for relapse and death in BCR::ABL1-like BCP-ALL, highlighting gene expression's significance.

Key Points

AI models achieved test set accuracies of 0.96 for LightGBM and 0.98 for neural networks, indicating strong classification performance.
The LGBM model showed ROC-AUC values of 0.83 for predicting relapse and 0.68 for mortality, highlighting the clinical utility of RNA-seq.
Both approaches effectively utilized targeted RNA-seq gene expression data, ensuring reliable classification of BCR::ABL1-like BCP-ALL.
Findings point to SHOC2 as a protective biomarker, while RBM47 and LDB3 may indicate increased mortality risk in this leukemia subtype.

Cite This Study

Ribera et al. (2025) studied this question.

synapsesocial.com/papers/69362f6e4fa91c937236e140 https://doi.org/10.1182/blood-2025-4358

View Full Paper

Ask AI

Bookmark

December 8, 2025BloodOpen Access

AI-based classification and outcome prediction in BCR::ABL1-like B-cell precursor acute lymphoblastic leukemia patients using targeted RNA-seq

View Full Paper

Ask AI

Bookmark

Authors

JRJordi Ribera MMMireia Morgades RARosa Ayala

Discussion

Member takes

Overview

Artificial intelligence models demonstrate predictive potential for relapse and death in BCR::ABL1-like BCP-ALL, highlighting gene expression's significance.

Key Points

AI models achieved test set accuracies of 0.96 for LightGBM and 0.98 for neural networks, indicating strong classification performance.
The LGBM model showed ROC-AUC values of 0.83 for predicting relapse and 0.68 for mortality, highlighting the clinical utility of RNA-seq.
Both approaches effectively utilized targeted RNA-seq gene expression data, ensuring reliable classification of BCR::ABL1-like BCP-ALL.
Findings point to SHOC2 as a protective biomarker, while RBM47 and LDB3 may indicate increased mortality risk in this leukemia subtype.

Cite This Study

Ribera et al. (2025) studied this question.

synapsesocial.com/papers/69362f6e4fa91c937236e140 https://doi.org/10.1182/blood-2025-4358

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark