AI Science Tracker
EN

Correlation Study Between Neoadjuvant Chemotherapy Response and Long-Term Prognosis in Breast Cancer Based on Deep Learning Models.

Not stated in the abstract reviewed · 31 Oct 2025 · medicine

Discovery

Correlation Study Between Neoadjuvant Chemotherapy Response and Long-Term Prognosis in Breast Cancer Based on Deep Learning Models.

Source check: Source checked. Not independent scientific confirmation.

Finding: A retrospective 832-patient breast-cancer cohort used an MLP to predict five-year recurrence/metastasis after neoadjuvant chemotherapy; the model reported internal cross-validated discrimination across subtypes.

Technology: A PyTorch MLP integrated molecular subtype, grade, tumor-size reduction, nodal status, Miller–Payne grade, Ki-67 and surgery; five-fold CV and SHAP were used.

Publication: Peer-reviewed paper · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
A PyTorch MLP integrated molecular subtype, grade, tumor-size reduction, nodal status, Miller–Payne grade, Ki-67 and surgery; five-fold CV and SHAP were used.
Test and result
The study predicts recorded five-year recurrence/metastasis; MLP AUC 0.86 (95% CI 0.81–0.92), accuracy 0.86, F1 0.84; a retrospective result, not treatment effect.
Limitation / still unknown
Five-fold internal CV was reported on 832 patients from one retrospective cohort. No external or prospective validation is established; evidence supports only the source-reported prognostic result.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://www.mdpi.com/2075-4418/15/21/2763/xml

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 3/5 · Validation 2/5 · Novelty 3/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse medicine discoveries.