Saram Abbas ^1* Naeem Soomro ² Rakesh Heer ³ Rishad Shafik ¹ Kabita Adhikari ¹

• ¹ School of Engineering, Faculty of Science, Agriculture and Engineering, Newcastle University, Newcastle upon Tyne, England, United Kingdom
• ² Freeman Hospital, Newcastle upon Tyne, United Kingdom
• ³ Department of Surgery and Cancer, Faculty of Medicine, Imperial College London, London, England, United Kingdom

Notorious for its 70-80% recurrence rate, Non-muscle-invasive Bladder Cancer (NMIBC) imposes a significant human burden and is one of the costliest cancers to manage. Current prediction tools for NMIBC recurrence rely on scoring systems that often overestimate risk and have poor accuracy. This is where Machine learning (ML) and artificial intelligence are tranforming oncological urology by leveraging molecular and clinical data. This comprehensive review critically analyses ML-based frameworks for predicting NMIBC recurrence, focusing on their statistical robustness and algorithmic efficacy. We meticulously examine the strengths and weaknesses of each study, by focusing on various data modalities, and ML models, highlighting their performance alongside inherent limitations. A diverse array of ML algorithms, including neural networks, deep learning, and random forests, demonstrates immense potential in enhancing predictive accuracy by leveraging multimodal data spanning radiomics, clinical, histopathological, and genomic domains. However, the path to widespread adoption faces challenges concerning the generalizability, interpretability and explainaibility, emphasising the need for collaborative efforts, robust datasets, and the incorporation of cost-effectiveness. Our detailed categorization and in-depth analysis illuminate the nuances, complexities, and contexts that influence real-world advancement and adoption of these AI-driven techniques in precision oncology. This rigorous analysis equips researchers with a deeper understanding of the intricacies of the ML algorithms employed. Actionable insights are provided for researchers aiming to refine algorithms, optimise multimodal data utilisation, and bridge the gap between predictive accuracy and clinical utility. This review serves as a roadmap to advance real-world AI applications in oncological care.