What question did this study set out to answer?

The research aims to develop a machine learning framework that incorporates biological insights to stratify breast cancer progression risk using gene expression data.

February 28, 2026Open Access

A Biologically Informed Explainable Machine Learning Framework for Breast Cancer Progression Risk Stratification From Tumor Gene Expression

Key Points

The research aims to develop a machine learning framework that incorporates biological insights to stratify breast cancer progression risk using gene expression data.
Developed a machine learning framework informed by biological pathways from tumor gene expression data.
Engineered pathway-level features from various curated gene sets.
Trained models on TCGA data and validated externally on GSE96058.
Applied Cox proportional hazards survival analysis and assessed model performance with AUC and feature importance analyses.
Achieved a C-index of 0.827 for survival analysis using Cox regression.
Reported an AUC of 0.856 during external validation.
Demonstrated feature importance via SHAP with a mean Spearman correlation of 0.820.

Abstract

This study presents a biologically informed explainable machine learning framework for breast cancer progression risk stratification using tumor gene expression data. We engineer pathway-level features from curated gene sets spanning proliferation, estrogen response, immune activation, invasion/EMT, apoptosis, HER2 signaling, and angiogenesis. Models are trained on TCGA (n=213) and externally validated on GSE96058 (n=1,483). We integrate Cox proportional hazards survival analysis (C-index 0.827), ssGSEA baseline comparison, SHAP-based feature importance with cross-fold stability analysis (mean Spearman ρ=0.820), and calibration assessment. The framework achieves AUC 0.856 on external validation with patient-level interpretability through SHAP waterfall plots.

Read Full Paperexternally

Perguntar à IA

Bookmark

View Full Paper

Cite This Study

Thayyil et al. (Mon,) studied this question.

synapsesocial.com/papers/69a287690a974eb0d3c0314a https://doi.org/https://doi.org/10.5281/zenodo.18765408

Also Consider

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

Perguntar à IA

Bookmark

View Full Paper