EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access

Development and External Validation of a Machine Learning-Derived Risk Stratification Score for Metastatic Castration-Resistant Prostate Cancer

Laura Castro-Labrador iD, Rafael Zamora iD, Sergio Szyldergemajn iD, Pablo Gómez Del Campo iD, José Del Castillo Izquierdo iD, José A De All, Juan M Domínguez, Carlos M Galmarini iD

JCO Clinical Cancer Informatics · 2026

DOI: 10.1200/cci-26-00054 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift JCO Clinical Cancer Informatics, 2026. Verfasst von Laura Castro-Labrador und 7 weiteren Autor:innen. Beteiligte Einrichtung: Topazium Artificial Intelligence, Madrid, Spain. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Castration-Resistant, Machine Learning. Die Arbeit nennt 47 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

Metastatic castration-resistant prostate cancer (mCRPC) shows marked clinical heterogeneity and poor long-term survival, highlighting the need for simple and reliable risk stratification tools beyond the limited usability of existing complex prognostic models. In this study, we developed and validated PROGRESS (Prostate Cancer Global Risk Evaluation and Stratification Score), a simplified prognostic score derived through machine learning‑guided feature selection distilled into a simple laboratory-based tool.

Methods

Baseline data from 2,035 patients with mCRPC (training set) were embedded into synthetic representations, reduced with UMAP, and clustered with DBSCAN to discover outcome-related subpopulations. Feature contribution analysis informed a multivariable model that yielded three independent predictors (prostate specific antigen [PSA], alkaline phosphatase [ALP], and AST) composing PROGRESS. External validation used two independent data sets (n = 1,239) across different therapeutic settings. Overall survival (OS) was analyzed with Kaplan-Meier and Cox regression; discrimination was assessed by ROC-AUC, AUC(t), and Harrel C-index.

Results

Unsupervised modeling identified two patient risk subpopulations with significantly different OS rates (median 27.4 v 17.7 months; hazard ratio [HR], 2.20 [95% CI, 1.91 to 2.54]; P < .00001). The three retained predictors (PSA, ALP, and AST) were combined into a composite score (PROGRESS) that showed strong discrimination in the training cohort (ROC-AUC 0.89; AUC(t) 0.60; Harrel C-index 0.69). Using a prespecified cutoff, patients classified by PROGRESS as increased risk had significantly shorter survival than low-risk patients (median 18.3 v 25.6 months; HR, 1.72 [95% CI, 1.50 to 1.97]; P < .0001). PROGRESS prognostic performance was consistent across all validation cohorts (all P < .0001).

Conclusion

By combining ML-based pattern discovery with classical modeling, PROGRESS provides a simple, objective, and readily implementable prognostic tool using three inexpensive routine laboratory measures. Its consistent performance across independent data sets supports clinical utility for individual risk stratification, trial enrichment, and early decision making. Prospective real-world validation is warranted.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Prostatic Neoplasms, Castration-ResistantMachine LearningHumansMalePrognosisRisk AssessmentAgedNeoplasm MetastasisBiomarkers, TumorKaplan-Meier EstimateMiddle AgedPredictive Learning ModelsProstate-Specific AntigenROC Curve

Substanzen

Biomarkers, TumorProstate-Specific Antigen

Autor:innen und Institutionen

  • Topazium Artificial Intelligence, Madrid, Spain.
  • Medicus, Buenos Aires, Argentina.
  • DLPHI Oncology Global Consultants, Vaud, Switzerland.

ORCID-Profile: Laura Castro-Labrador, Rafael Zamora, Sergio Szyldergemajn, Pablo Gómez Del Campo, José Del Castillo Izquierdo, Carlos M Galmarini

Zitieren

APA

Castro-Labrador, L., Zamora, R., Szyldergemajn, S., Gómez Del Campo, P., Del Castillo Izquierdo, J., De All, J. A., Domínguez, J. M., & Galmarini, C. M. (2026). Development and External Validation of a Machine Learning-Derived Risk Stratification Score for Metastatic Castration-Resistant Prostate Cancer. JCO Clinical Cancer Informatics. https://doi.org/10.1200/cci-26-00054

Vancouver

Castro-Labrador L, Zamora R, Szyldergemajn S, Gómez Del Campo P, Del Castillo Izquierdo J, De All JA, et al. Development and External Validation of a Machine Learning-Derived Risk Stratification Score for Metastatic Castration-Resistant Prostate Cancer. JCO Clinical Cancer Informatics. 2026. doi:10.1200/cci-26-00054

BibTeX
@article{CastroLabrador2026,
  author = {Castro-Labrador, Laura and Zamora, Rafael and Szyldergemajn, Sergio and Gómez Del Campo, Pablo and Del Castillo Izquierdo, José and De All, José A and Domínguez, Juan M and Galmarini, Carlos M},
  title = {Development and External Validation of a Machine Learning-Derived Risk Stratification Score for Metastatic Castration-Resistant Prostate Cancer},
  journal = {JCO Clinical Cancer Informatics},
  year = {2026},
  doi = {10.1200/cci-26-00054}
}
Kostenlos starten →