South Central Section of the AUA 2022

SCS AUA 2022: Context-based Identification of Muscle-Invasion Status in Bladder Cancer Patients Using Natural Language Processing

( Mortality from bladder cancer (BC) increases exponentially once it invades the muscle with inherent challenges delineating at the population level. They sought to develop and validate a natural language processing (NLP) model for automatically identifying muscle-invasive BC (MIBC) patients.

All patients with a CPT code for transurethral resection of bladder tumor (TURBT) (N=76,060) were selected from the Department of Veterans Affairs (VA) database. A sample of 600 patients (with 2,337 full-text notes) who had TURBT and confirmed pathology results were selected for NLP model development and validation. The NLP performance was assessed by calculating the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), F1 score, and overall accuracy at the individual note and patient levels.

In the validation cohort, the NLP model had an average overall accuracy of 94% and 96% at the note and patient levels. Specifically, the F1 score and overall accuracy for predicting muscle-invasion on patient level were 0.87 and 96%, respectively. The model classified non-muscle invasive BC (NMIBC) with 90% and 93% overall accuracy at the note and patient levels. When applying the model to 71,200 patients VA-wide, the model classified 13,642 (19%) as having MIBC and 47,595 (66%) as NMIBC and was able to identify invasion status for 96% TURBT patients at the population level. Inherent limitations include relatively small training set given the size of the VA population.

In summary, this NLP model, with high accuracy, maybe a practical tool for efficiently identifying BC invasion status and aid in population-based BC research. Artificial intelligence will become increasingly more common in healthcare in order to meet the increasing demands of our patients and large data analyses. This work embodies much of the current shift and the accuracy of the models far out surpass conventional hand abstraction which in all intensive purposes will become obsolete in health services research.

Presented by: Stephen B. Williams, MD, MBA, MS, Durham VA Medical Center, The University of Texas Medical Branch

Written by: Stephen B. Williams, MD, MBA, MS @SWilliams_MD on Twitter during the South Central Section American Urological Association Annual Meeting, September 6-10, 2022, Coronado, CA

email news signup