AI-Based Clinical Rule Discovery for NMIBC Recurrence through Tsetlin Machines

TL;DR

This paper introduces an interpretable AI model using Tsetlin Machines for predicting NMIBC recurrence, outperforming traditional methods and providing transparent, human-readable rules for clinical decision support.

Contribution

The study presents a novel application of Tsetlin Machines in healthcare, demonstrating superior accuracy and interpretability over existing clinical risk models for bladder cancer recurrence prediction.

Findings

Tsetlin Machine achieved an F1-score of 0.80, outperforming other models.

TM provides transparent rules based on clinical features.

The model is suitable for real-world clinical decision support.

Abstract

Bladder cancer claims one life every 3 minutes worldwide. Most patients are diagnosed with non-muscle-invasive bladder cancer (NMIBC), yet up to 70% recur after treatment, triggering a relentless cycle of surgeries, monitoring, and risk of progression. Clinical tools like the EORTC risk tables are outdated and unreliable - especially for intermediate-risk cases. We propose an interpretable AI model using the Tsetlin Machine (TM), a symbolic learner that outputs transparent, human-readable logic. Tested on the PHOTO trial dataset (n=330), TM achieved an F1-score of 0.80, outperforming XGBoost (0.78), Logistic Regression (0.60), and EORTC (0.42). TM reveals the exact clauses behind each prediction, grounded in clinical features like tumour count, surgeon experience, and hospital stay - offering accuracy and full transparency. This makes TM a powerful, trustworthy decision-support tool ready for real-world adoption.