Machine learning methods for predicting early recurrence in Ta stage bladder cancer and comparison with conventional statistical methods

Comprehensive Summary

One important form of management in tracking recovery from bladder cancer is determining whether there will be recurrence, specifically for bladder cancer confined to the mucosa (Ta-stage). Machine learning (ML) can thus be used to predict whether there would be recurrence of Ta-stage bladder cancer in the 2-year postoperative period for Non-Muscle Invasive Bladder Cancers. With significant variables identified as Body Mass Index, American Society of Anesthesiologists (ASA) score, and the presence of macroscopic hematuria, early prediction using ML was found to be more accurate than that of conventional statistical models.

Outcomes and Implications

With the development of machine learning, its predictive potential in determining bladder cancer recurrence allows for more personalized patient care. Specifically, as accuracy with ML prediction increases, physicians would be better able to determine recovery and post-operative care plans that would bring more benefit to the patient.