Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

AARS2-mediated lactylation of ULK1 promotes autophagy-dependent progression of clear cell renal cell carcinoma.

Autophagy·2026
Same author

Mask Optimization for High-Precision Extraction of Geometric Features in Microscopic Scenes.

Journal of imaging·2026
Same author

Predicting extraperitoneal ssRARP difficulty: an MRI-based nomogram.

Journal of robotic surgery·2026
Same author

Revisiting InternVL: A Systematic Technical Framework for Building Powerful Open-Source Vision-Language Models.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

GPI promotes immunosuppression in anaplastic thyroid carcinoma via O-GlcNAcylated THBS1-mediated myeloid cell crosstalk.

Cancer letters·2026
Same author

A proposed clinical framework for intentional tooth replantation based on healing dynamics: case series.

BMC oral health·2026

Related Experiment Video

Updated: Sep 15, 2025

Microarray-based Identification of Individual HERV Loci Expression: Application to Biomarker Discovery in Prostate Cancer
13:19

Microarray-based Identification of Individual HERV Loci Expression: Application to Biomarker Discovery in Prostate Cancer

Published on: November 2, 2013

16.7K

Prognostic and Predictive Value of Machine Learning-Based Biomarker and Pathomics Signatures in Patients With

Jianpeng Zhang1,2,3,4, Jinyou Pan1,2,3,4, Jingwei Lin1

  • 1Department of Urology, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.

Cancer Science
|July 17, 2025
PubMed
Summary
This summary is machine-generated.

New machine learning models, metastasis-associated prognostic risk score (MAPRS) and pathomics score (PSpc), effectively predict prostate cancer recurrence after surgery. These scores offer insights into treatment sensitivity and tumor heterogeneity.

Keywords:
biomarkermachine learningpathomicsprognostic modelprostate cancer

More Related Videos

Author Spotlight: Advancing Prostate Cancer Research Through Improved Tissue Sampling and Biobanking
07:34

Author Spotlight: Advancing Prostate Cancer Research Through Improved Tissue Sampling and Biobanking

Published on: November 17, 2023

789
miRNA Expression Analyses in Prostate Cancer Clinical Tissues
11:29

miRNA Expression Analyses in Prostate Cancer Clinical Tissues

Published on: September 8, 2015

10.9K

Related Experiment Videos

Last Updated: Sep 15, 2025

Microarray-based Identification of Individual HERV Loci Expression: Application to Biomarker Discovery in Prostate Cancer
13:19

Microarray-based Identification of Individual HERV Loci Expression: Application to Biomarker Discovery in Prostate Cancer

Published on: November 2, 2013

16.7K
Author Spotlight: Advancing Prostate Cancer Research Through Improved Tissue Sampling and Biobanking
07:34

Author Spotlight: Advancing Prostate Cancer Research Through Improved Tissue Sampling and Biobanking

Published on: November 17, 2023

789
miRNA Expression Analyses in Prostate Cancer Clinical Tissues
11:29

miRNA Expression Analyses in Prostate Cancer Clinical Tissues

Published on: September 8, 2015

10.9K

Area of Science:

  • Oncology
  • Bioinformatics
  • Digital Pathology

Background:

  • Radical prostatectomy (RP) for prostate cancer (PCa) faces challenges with recurrence and castration resistance.
  • Existing prognostic models for PCa lack widespread clinical application.
  • Understanding molecular and morphological heterogeneity is crucial for accurate PCa prognosis.

Purpose of the Study:

  • To develop and validate novel machine learning-based prognostic scores for predicting recurrence-free survival (RFS) in PCa patients post-RP.
  • To assess the utility of transcriptome-derived (MAPRS) and digital pathology-derived (PSpc) scores in predicting PCa outcomes.
  • To explore the association of these scores with tumor microenvironment, genetic variants, and treatment sensitivity.

Main Methods:

  • Utilized five machine learning algorithms (LASSO, RSF, SVM-RFE, Boruta, XGBoost) on multi-center transcriptome data to develop the metastasis-associated prognostic risk score (MAPRS).
  • Employed a machine learning framework (XGBoost, RSF, GBM, plsRCox, CoxBoost, Enet, Ridge, LASSO, SVM, superPC) on H&E-stained digital pathology images to derive the pathomics score (PSpc).
  • Validated MAPRS and PSpc using in-house histopathological samples and assessed their predictive performance for RFS and progression-free survival (PFS).

Main Results:

  • MAPRS effectively predicted poorer RFS and was linked to tumor microenvironment and pathogenic variants.
  • A higher MAPRS suggested potential sensitivity to treatments like PARP inhibitors, docetaxel, and oxaliplatin.
  • Combined evaluation of MAPRS and PSpc demonstrated superior prediction of RFS post-RP compared to individual scores or other tools.
  • MAPRS also predicted PFS in patients on androgen deprivation therapy, while PSpc showed limited efficacy in this context.

Conclusions:

  • Machine learning-based prognostic signatures, particularly digital pathology-derived ones, offer superior predictive efficacy for PCa recurrence.
  • MAPRS and PSpc provide valuable insights into molecular and morphological tumor heterogeneity, aiding in risk stratification.
  • These novel scores hold promise for improved clinical decision-making and personalized treatment strategies in prostate cancer management.