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

  1. Home
  3. Development And Validation Of Interpretable Machine Learning Models To Predict Distant Metastasis And Prognosis Of Muscle-invasive Bladder Cancer Patients.
  1. Home
  3. Development And Validation Of Interpretable Machine Learning Models To Predict Distant Metastasis And Prognosis Of Muscle-invasive Bladder Cancer Patients.

Related Experiment Video

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K

Development and validation of interpretable machine learning models to predict distant metastasis and prognosis of

Qian Deng1, Shan Li2, Yuxiang Zhang3

  • 1Luoyang Central Hospital Affiliated of Zhengzhou University, Henan, China.

Scientific Reports
|April 6, 2025

View abstract on PubMed

Summary
This summary is machine-generated.
Keywords:
Distant metastasisMachine learningMuscle-Invasive bladder CancerPrognosis predictionSEER

More Related Videos

Magnetic Resonance Imaging Assessment of Carcinogen-induced Murine Bladder Tumors
05:19

Magnetic Resonance Imaging Assessment of Carcinogen-induced Murine Bladder Tumors

Published on: March 29, 2019

10.3K
An Orthotopic Bladder Cancer Model for Gene Delivery Studies
07:48

An Orthotopic Bladder Cancer Model for Gene Delivery Studies

Published on: December 1, 2013

12.4K

Related Experiment Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K
Magnetic Resonance Imaging Assessment of Carcinogen-induced Murine Bladder Tumors
05:19

Magnetic Resonance Imaging Assessment of Carcinogen-induced Murine Bladder Tumors

Published on: March 29, 2019

10.3K
An Orthotopic Bladder Cancer Model for Gene Delivery Studies
07:48

An Orthotopic Bladder Cancer Model for Gene Delivery Studies

Published on: December 1, 2013

12.4K

Machine learning models accurately predict metastasis and prognosis in muscle-invasive bladder cancer (MIBC) patients. Tumor size is a key factor for distant metastasis prediction in MIBC.

Area of Science:

  • Oncology
  • Medical Informatics
  • Computational Biology

Background:

  • Muscle-invasive bladder cancer (MIBC) presents a higher risk of metastasis compared to non-muscle-invasive bladder cancer (NMIBC).
  • Accurate prediction of metastasis and prognosis is crucial for effective management of MIBC patients.

Purpose of the Study:

  • To develop and validate machine learning (ML) models for predicting distant metastasis (DM) and patient prognosis in MIBC.
  • To identify key clinical variables influencing metastasis risk and to interpret the predictive models.

Main Methods:

  • Utilized clinical data from 43,951 MIBC patients (T2-T4) from the SEER database (2000-2020).
  • Employed logistic regression, Recursive Feature Elimination (RFE), and various ML algorithms (including CatBoost and RSF+Enet) for model development and evaluation.
  • Assessed model performance using metrics like AUC, accuracy, sensitivity, specificity, and C-index, with SHapley Additive exPlanations (SHAP) for interpretability.

    • Main Results:

    • The CatBoost model demonstrated high predictive accuracy for DM (AUC up to 0.956 training, 0.839 external), identifying tumor size as the most significant predictor.
    • The RSF+Enet model showed robust performance in predicting prognosis (C-index up to 0.688).
    • Selected nine clinical variables were crucial for predicting DM in MIBC.

    Conclusions:

    • Developed highly accurate and dependable ML models for predicting metastasis risk and prognosis in MIBC.
    • These models offer potential for refined, individualized risk assessment and treatment planning for MIBC patients.
    • Highlights the importance of clinical variables, particularly tumor size, in predicting MIBC outcomes.