Related Experiment Video
Updated: Jan 15, 2026
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
Development and International Evaluation of an Artificial Intelligence-based Model (PROGRxN-BCa) Using the World
Jethro C C Kwong1, Zizo Al-Daqqaq2, Yashan Chelliahpillai2
1Division of Urology, Department of Surgery, University of Toronto, Toronto, Canada; Division of Urology, Department of Surgery, University Health Network, Toronto, Canada; Temerty Centre for AI Research and Education in Medicine, University of Toronto, Toronto, Canada.
A new artificial intelligence tool, PROGRxN-BCa, significantly improves risk prediction for non-muscle-invasive bladder cancer (NMIBC) progression. This AI model offers superior accuracy compared to existing methods, enhancing patient management strategies.
Area of Science:
- Urology
- Oncology
- Artificial Intelligence in Medicine
Background:
- Current tools for non-muscle-invasive bladder cancer (NMIBC) have suboptimal performance in predicting disease progression.
- Accurate risk stratification is crucial for managing NMIBC and preventing progression to muscle-invasive disease.
Purpose of the Study:
- To develop and validate an artificial intelligence (AI) approach, PROGression Risk assessment in NMIBC (PROGRxN-BCa), for improved NMIBC risk assessment.
- To compare the performance of PROGRxN-BCa against existing risk calculators and guideline-endorsed tools.
Main Methods:
- PROGRxN-BCa was trained on 14 clinicopathological features from 3324 NMIBC patients across four Canadian institutions.
- External validation involved 9335 NMIBC patients from 30 institutions in North America and Europe.
- Performance was evaluated using concordance index (c-index), calibration, decision curve analysis, and algorithmic audit, comparing PROGRxN-BCa against the European Association of Urology (EAU) risk calculator.
Main Results:
- In external testing, PROGRxN-BCa demonstrated a significantly higher c-index (0.79) compared to the EAU risk calculator (0.71).
- The AI tool showed superior net benefit across various subgroups and outperformed other guideline-endorsed tools and a prior AI model.
- PROGRxN-BCa effectively stratified intermediate-risk patients into distinct tertiles with varying 5-year progression risks (2%, 7%, 15%).
Conclusions:
- PROGRxN-BCa represents a significant advancement in NMIBC risk stratification, outperforming current tools in the largest cohort of its kind.
- Integration of PROGRxN-BCa into clinical guidelines has the potential to enhance patient management and outcomes for NMIBC.
