Integrative Survival Prediction in Breast Cancer Using Extracellular Matrix Protease Transcript Signatures and Clinical Variables: A Machine Learning Approach.
Simple Summary: Breast cancer is among the most common malignancies globally, with incidence and mortality placing it at the forefront of oncological research. Patients with similar clinical profiles can experience markedly different outcomes, largely because traditional staging tools fail to captur...
| Publicado en: | Cancers Vol. 18; no. 10; pp. 1497 - 1520 |
|---|---|
| Autores principales: | , , , , |
| Formato: | research tables/charts Journal Article |
| Publicado: |
MDPI
May2026
|
| Acceso en línea: | Ver este registro en EBSCOhost |
| fields | @attributes: recordID: 1 pdfLink: plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=194129175&site=ehost-live header: @attributes: shortDbName: ccm uiTerm: 194129175 longDbName: CINAHL Complete uiTag: AN controlInfo: bkinfo: dissinfo: jinfo: jid: 20726694 B74B jtl: Cancers issn: 20726694 maglogo: N pubinfo: dt: May2026 vid: 18 iid: 10 pid: 97109 pub: MDPI artinfo: ui: 194129175 194129175 194129175 10.3390/cancers18101497 194129175 ppf: 1497 ppct: 23 formats: tig: atl: Integrative Survival Prediction in Breast Cancer Using Extracellular Matrix Protease Transcript Signatures and Clinical Variables: A Machine Learning Approach. aug: au: Babas, Rami Vynios, Demitrios H. Kompothrekas, Aristotelis Boutsinas, Basilis Karamanos, Nikos affil: Biochemistry, Biochemical Analysis & Matrix Pathobiochemistry Research Group, Department of Chemistry, University of Patras, 26504 Patras, Greece sug: subj: Breast Neoplasms Prognosis Tumor Markers, Biological Analysis Extracellular Matrix Proteins Analysis Machine Learning Algorithms Utilization Risk Assessment Human Male Female Adult Middle Age Aged Aged, 80 and Over Confidence Intervals Cox Proportional Hazards Model Descriptive Statistics Log-Rank Test Overall Survival Prediction Models Survival Analysis Random Forest Kaplan-Meier Estimator Post Hoc Analysis HER-2-neu Oncogene Matrix Metalloproteinases Gene Expression Profiling Spearman's Rank Correlation Coefficient RNA, Messenger Neoplasm Staging Comparative Studies Adult: 19-44 years Middle Aged: 45-64 years Aged: 65+ years Aged, 80 & over Male Female ab: Simple Summary: Breast cancer is among the most common malignancies globally, with incidence and mortality placing it at the forefront of oncological research. Patients with similar clinical profiles can experience markedly different outcomes, largely because traditional staging tools fail to capture molecular heterogeneity. This study addresses that gap by integrating transcriptional abundance of extracellular matrix proteases, specifically the MMP, ADAM, and ADAMTS families, with standard clinical variables to improve survival prediction. The models successfully identified "hidden high-risk" patterns in TCGA-BRCA. Independent testing in METABRIC showed statistically significant risk-group separation but only modest individual-level discrimination (external C-index = 0.581), indicating that the signature is promising but requires further platform-harmonized and prospective validation before clinical use. Background/Objectives: Traditional breast cancer prognostic tools relying on clinical staging often miss molecular heterogeneity, leading to divergent patient outcomes. Extracellular matrix (ECM) remodeling, driven by the Matrix Metalloproteinase (MMP), ADAM, and ADAMTS enzyme families, is critical to tumor progression. This study evaluates whether integrating ECM protease transcript abundance with standard clinical variables improves survival prediction accuracy and personalized risk stratification. Methods: Clinical and transcriptomic data from The Cancer Genome Atlas (TCGA) breast cancer cohort were analyzed. We integrated the protein-coding transcripts per million (pTPM) of top-ranked protease genes with standard clinical covariates (age, ordinal stage). Cox Proportional Hazards (CoxPH), penalized Cox (CoxNet), Random Survival Forest (RSF), and Gradient Boosting Survival (GBS) models were evaluated under a stratified 70/30 train–test split, followed by five-fold cross-validation. The locked final RSF model was then externally tested in METABRIC without retraining or risk-cutoff optimization. Results: Univariate screening identified ADAM15, MMP15, and ADAMTSL1 as global risk factors, whereas ADAMTS8 and MMP7 were protective. Prognostic signals were subtype-dependent. Integrated multivariable models outperformed transcript-only approaches in internal testing. The integrative RSF achieved the highest held-out discrimination (C-index = 0.797), outperforming a clinical-only Cox baseline trained on age and stage alone (C-index = 0.742, 95% CI 0.636–0.826). In METABRIC, the external C-index was 0.581 (95% CI 0.562–0.598), with significant survival separation across training-defined risk groups (log-rank p < 0.0001). Conclusions: ECM protease transcript profiles provide complementary prognostic information in TCGA-BRCA and show partial transportability to METABRIC. However, the modest external C-index indicates limited individual-level discrimination across platforms, so these candidate markers should be interpreted as hypothesis-generating and require further validation before clinical implementation. pubtype: Academic Journal doctype: research tables/charts Journal Article ougenre: Article language: English refInfo: holdings: @attributes: islocal: N |
|---|