Abstract Artificial intelligence (AI) applications are rapidly evolving, disruptive technologies that recently attracted tremendous public awareness including euphoria, bull runs at stock exchanges but also criticism and skepticism. Pathology, a crucial clinical diagnostic discipline, faces significant challenges despite its critical role and broad scope. A notable issue is the declining interest among medical graduates in pursuing further training in Surgical Pathology and Molecular Pathology. This disinterest is compounded by a trend towards part-time work and the aging demographic in Western industrial nations, which increases the demand for precise cancer diagnoses, molecular pathology and advanced oncological treatments. As the need for skilled pathologists grows, the availability of these professionals is steadily decreasing. Furthermore, political policies in heavily regulated healthcare systems (e.g., Germany) are exacerbating the shortage by limiting residency and specialist training positions despite the growing need. Adding to the reluctance among medical graduates to consider pathology as discipline is the looming “threat”” of replacing the field with Artificial Intelligence (AI) technologies. However, historical precedents suggest that necessity often spurs significant innovation. AI's role in pathology is expanding, reshaping the field with new technological advancements. AI, broadly encompassing various computational algorithms designed to perform tasks typically requiring human intelligence such as learning, reasoning, and pattern recognition, is now being applied extensively across different domains including medical diagnostics. Recent implementations in pathology include AI-driven algorithms that automate processes such as the Gleason grading of prostate biopsies, lymph node metastasis detection, detection of molecular bladder cancer subtypes or grading of kidney cancer showing high accuracy levels, speed and reproducibility in delivering results. These tools, while they do not replace pathologists, significantly reduce their workload by automating routine tasks, thus freeing up time for more complex diagnostic activities or simply dealing with the increasing workload. Despite the exciting possibilities, the use of AI in predicting molecular alterations, such as FGFR3 mutations in bladder cancer, faces limitations due to insufficient sensitivity and specificity, indicating that such technologies are not yet suitable for screening purposes. In conclusion, AI is increasingly vital in addressing the challenges of modern pathology, particularly in compensating for the shortage of pathologists. As technology advances, its integration into clinical practice offers promising solutions to enhance diagnostic accuracy and efficiency in uropathology, paving the way for more personalized and effective patient care. Citation Format: Markus Eckstein. AI in bladder cancer pathology and research: What can we expect and what not? [abstract]. In: Proceedings of the AACR Special Conference on Bladder Cancer: Transforming the Field; 2024 May 17-20; Charlotte, NC. Philadelphia (PA): AACR; Clin Cancer Res 2024;30(10_Suppl):Abstract nr IA022.
Read full abstract