The abstract is read at the publisher; the summary is JClub's.
The Transformer-based deep learning model using gene expression plus preoperative clinical data predicts sentinel lymph node macro-metastasis in SCAN-B node-negative T1–T2 breast cancer, improving ROC AUC to 0.693.
- Why it matters: Clinically node-negative patients still have occult sentinel lymph node macro-metastasis, creating a need for more accurate preoperative risk stratification to guide axillary surgery and prognosis.
- What they did: In SCAN-B, 6,836 patients were split into 4,625 development and 2,211 independent testing; three gene-expression DL models were compared with XGBoost, and a combined Pre-opClinic+GEX predictor was evaluated.
- The result: Pre-opClinic+GEX improved SLNM prediction versus Pre-opClinic alone (0.693 vs 0.596, P < 0.001) and enabled a 27.2% SLNB reduction at 92.1% sensitivity, with TNBC AUC 0.734 (95% CI: 0.644–0.837) and concordance between paired biopsy and surgical specimens (n=116).
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.