EUVIMEDEUVIMED entdecken
BeobachtungsstudieValidierungsstudieOpen Access · CC BY-NC 4.0

Prognostic and Predictive Value of Machine Learning‐Based Biomarker and Pathomics Signatures in Patients With Prostate Cancer

Jianpeng Zhang, Jinyou Pan, Jingwei Lin, Yingxin Cai, Yangzhou Liu, Fuyang Lin, Hantian Guan, Gaoxiang Zhou, Daqiang Wei, Zuomin Wang, Yuxiang Ma, Zhigang Zhao iD

Cancer Science · 2025

DOI: 10.1111/cas.70149 ↗

Kurz gefasst

Beobachtungsstudie in der Zeitschrift Cancer Science, 2025. Verfasst von Jianpeng Zhang und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Neoplasm Recurrence, Local, Biomarkers, Tumor, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recurrence and the potential development of castration resistance after radical prostatectomy (RP) are significant challenges in the management of prostate cancer (PCa). Despite the development of advanced prognostic models, few have been clinically applied. Five machine learning algorithms (LASSO, RSF, SVM‐RFE, Boruta, and XGBoost) were used to identify biomarkers for PCa using transcriptome data from multicenters (TCGA, MSKCC, DKFZ, and GSE70770) for constructing and validating the metastasis‐associated prognostic risk score (MAPRS), which revealed the molecular biological heterogeneity and was confirmed with in‐house histopathological samples. The pathomics score (PSpc), derived from a machine learning framework (XGBoost, RSF, GBM, plsRCox, CoxBoost, Enet, Ridge, LASSO, SVM, and superPC) using hematoxylin and eosin (H&E)‐stained digital pathology, quantified tumor morphological heterogeneity. The MAPRS correlated with poorer recurrence‐free survival (RFS) and was associated with the tumor microenvironment and pathogenic variants. A higher MAPRS may indicate sensitivity to treatments such as PARP inhibitors, docetaxel, and oxaliplatin. Pathology‐based evaluations of MAPRS, PSpc, and their combination effectively predicted RFS in patients who underwent RP. MAPRS also predicted progression‐free survival in patients receiving androgen deprivation therapy when combined with clinical indicators, whereas PSpc demonstrated limited efficacy. The digital pathology‐based signatures showed superior predictive efficacy compared to other tools. Trial Registration: Chinese Clinical Trial Registry number: ChiCTR2400085748 (June 18, 2024).

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Prostatic NeoplasmsNeoplasm Recurrence, LocalBiomarkers, TumorMachine LearningProstatectomyRisk AssessmentGene Expression ProfilingDisease-Free SurvivalProstateAntineoplastic Combined Chemotherapy ProtocolsDrug Resistance, NeoplasmProgression-Free SurvivalAndrogen AntagonistsDatasets as TopicHumansMaleMiddle AgedAgedRetrospective Studies

Stichwörter der Autor:innen

biomarkermachine learningpathomicsprognostic modelprostate cancer

Substanzen

Biomarkers, TumorAndrogen Antagonists

Autor:innen und Institutionen

  • Department of Urology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.
  • Guangdong Provincial Key Laboratory of Urology, Guangzhou, China.
  • Guangdong Engineering Research Center of Urinary Minimally Invasive Surgery Robot and Intelligent Equipment, Guangzhou, China.
  • Guangzhou Institute of Urology, Guangzhou, China.
  • Department of Urology, The Second Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.

ORCID-Profile: Zhigang Zhao

Zitieren

APA

Zhang, J., Pan, J., Lin, J., Cai, Y., Liu, Y., Lin, F., Guan, H., Zhou, G., Wei, D., Wang, Z., Ma, Y., & Zhao, Z. (2025). Prognostic and Predictive Value of Machine Learning‐Based Biomarker and Pathomics Signatures in Patients With Prostate Cancer. Cancer Science. https://doi.org/10.1111/cas.70149

Vancouver

Zhang J, Pan J, Lin J, Cai Y, Liu Y, Lin F, et al. Prognostic and Predictive Value of Machine Learning‐Based Biomarker and Pathomics Signatures in Patients With Prostate Cancer. Cancer Science. 2025. doi:10.1111/cas.70149

BibTeX
@article{Zhang2025,
  author = {Zhang, Jianpeng and Pan, Jinyou and Lin, Jingwei and Cai, Yingxin and Liu, Yangzhou and Lin, Fuyang and Guan, Hantian and Zhou, Gaoxiang and Wei, Daqiang and Wang, Zuomin and Ma, Yuxiang and Zhao, Zhigang},
  title = {Prognostic and Predictive Value of Machine Learning‐Based Biomarker and Pathomics Signatures in Patients With Prostate Cancer},
  journal = {Cancer Science},
  year = {2025},
  doi = {10.1111/cas.70149}
}
Kostenlos starten →