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 Experiment Video

Updated: Jul 4, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Clinical Variable-Based Machine Learning for Predicting Early mCRPC Using Exclusively Clinical Variables: Development

Miguel Ángel Gómez-Luque1,2, Pedro De Pablos-Rodríguez3, Daniel Adolfo Pérez-Fentes4

  • 1Department of Urology, Hospital Universitario Virgen del Rocio, Seville, Spain.

The Prostate
|July 2, 2026
PubMed

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

Magnetic Resonance Imaging as a Predictor of Early Discontinuation of Active Surveillance in Patients with Prostate Cancer.

Archivos espanoles de urologia·2026
Same author

Cholesterol metabolism and aggressive prostate cancer: clarifying the signal from EPICAP.

Translational andrology and urology·2026
Same author

PSA Response as a Prognostic Marker in Metastatic Hormone-sensitive Prostate Cancer: Comparison with Tumor Volume (CHAARTED).

European urology open science·2026
Same author

Prediction of infectious complications after supine percutaneous nephrolithotomy: development and internal validation of a multivariable nomogram.

Urolithiasis·2026
Same author

The 24-h pad test in the assessment of post-prostatectomy incontinence: is there still a role for counting pads per day?

BJU international·2026
Same author

Robotic versus laparoscopic radical prostatectomy: a large cohort study using the 24-hour pad test highlights the impact of continence definition on functional outcomes.

Journal of robotic surgery·2026
Summary

A new RINH algorithm accurately predicts early metastatic castration-resistant prostate cancer (mCRPC) progression using only clinical data. This advance offers improved risk stratification for metastatic hormone-sensitive prostate cancer (mHSPC) patients.

Area of Science:

  • Oncology
  • Artificial Intelligence in Medicine
  • Prostate Cancer Research

Background:

  • Metastatic hormone-sensitive prostate cancer (mHSPC) progression is heterogeneous, with early progression to mCRPC indicating poor prognosis.
  • Current risk stratification tools (CHAARTED, LATITUDE) have limited predictive accuracy for individual mHSPC patients.
  • Existing machine learning (ML) models often show modest performance and lack external validation or rely on non-clinical data.

Purpose of the Study:

  • To develop and externally validate a novel Rivality Index Neighborhood (RINH) algorithm for predicting early mCRPC progression (≤12 months) in mHSPC.
  • To assess RINH's performance using exclusively clinical variables, aiming for superior prediction compared to conventional ML classifiers.
  • To advance precision oncology by creating a clinically applicable risk stratification tool.
Keywords:
castration‐resistant prostate cancerearly progressionexternal validationmachine learningpredictive modellingrisk stratification

Related Experiment Videos

Last Updated: Jul 4, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

Main Methods:

  • A multicenter study involving 412 de novo mHSPC patients from seven Spanish academic centers.
  • Collected 20 clinical variables, including demographics, PSA, ISUP grade, and metastatic site.
  • Trained and validated six ML algorithms (including RINH) using a two-tiered strategy: fivefold cross-validation and external validation on independent cohorts.

Main Results:

  • The RINH algorithm demonstrated superior predictive performance for early mCRPC progression compared to other ML models.
  • The model utilized exclusively clinical variables, enhancing its potential for routine clinical use.
  • While performance metrics were high, external validation highlighted the need for further reliability assessment.

Conclusions:

  • The RINH algorithm shows promise as a superior tool for predicting early mCRPC progression in mHSPC patients.
  • Clinical deployment requires validation in larger cohorts with more progression events to ensure stability.
  • Successful validation could enable personalized, risk-adapted treatment strategies for mHSPC.