Key points are not available for this paper at this time.
Introduction: Current prognostic tools in non-muscle-invasive bladder cancer (NMIBC) perform poorly and do not fully reflect contemporary practices.We aimed to develop, externally validate, and conduct an algorithmic audit of a progression risk assessment tool using artificial intelligence approaches (PROGRxN-BCa).Methods: PROGRxN-BCa, based on a random survival forest, was trained on NMIBC patients treated from January 1, 2005, to June 30, 2022, at four Canadian academic or community hospitals.External validation was performed on patients treated from November 1, 2011, to September 11, 2023, across 13 institutions from the Canadian Bladder Cancer information system.The primary outcome was time to progression, defined as first development of muscle-invasive or metastatic disease.PROGRxN-BCa was compared to the European Association of Urology risk calculator and a LASSO Cox model using identical variables as PROGRxN-BCa.Model performance in predicting five-year progression risk was characterized using c-index, calibration plots, decision curve analysis, and an algorithmic audit.Results: Overall, 999 of 7032 patients (14%) developed progression during a median followup of 3.0 years (IQR 1.4-5.4).PROGRxN-BCa had the highest c-index overall (training: 0.83, 95% CI 0.81-0.84;validation: 0.76, 95% CI 0.74-0.77)and across different subgroups.It was well-calibrated and had the highest net benefit for clinically relevant thresholds from 15-40%.False negatives occurred in only 2-6% of all predictions, most commonly found in patients with Ta disease.PROGRxN-BCa could better substratify intermediate-risk patients compared to current guideline recommendations, reclassifying 12% of these patients with an observed five-year progression risk of 31.6% who otherwise would not have been considered for treatment intensification or clinical trial enrollment (Figure 1).Conclusions: PROGRxN-BCa outperformed current prognostication tools and improved substratification of the heterogenous intermediate-risk group.
Building similarity graph...
Analyzing shared references across papers
Loading...
Editor CUAJ
Canadian Urological Association Journal
Building similarity graph...
Analyzing shared references across papers
Loading...
Editor CUAJ (Tue,) studied this question.
www.synapsesocial.com/papers/68e664c0b6db6435875f195d — DOI: https://doi.org/10.5489/cuaj.8822
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: