Artificial intelligence (AI) is becoming a clinical tool for prostate pathology, but generalization across variations in sample preparation and preservation over prolonged time periods remains poorly understood. We evaluated GleasonAI, an end-to-end attention-based multiple instance learning model, on an independent validation cohort comprising 10,366 biopsy cores from 1,028 patients across 14 Swedish regions, using archival diagnostic specimens from the ProMort cohorts collected between 1998-2015. The model achieved an overall quadratic-weighted kappa of 0.86 for core-level ISUP grading, comparable to several experienced pathologists and consistent across geographic regions. Notably, performance remained stable across the 17-year collection period, demonstrating robustness to time-related variation in archival material, a property not consistently observed with foundation model-based approaches, with exploratory analysis demonstrating a significant prognostic gradient across AI-assigned grade groups for prostate cancer-specific mortality. These findings support the generalizability of the AI grading model and demonstrate the potential of pathology archives as a large-scale resource for AI development, validation, and retrospective prognostic research.
@article{arxiv.2605.02614,
title = {Validation of an AI-based end-to-end model for prostate pathology using long-term archived routine samples},
author = {Xiaoyi Ji and Renata Zelic and Oskar Aspegren and Nita Mulliqi and Michelangelo Fiorentino and Francesca Giunchi and Luca Molinaro and Sol Erika Boman and Lorenzo Richiardi and Andreas Pettersson and Per Henrik Vincent and Martin Eklund and Olof Akre and Kimmo Kartasalo},
journal= {arXiv preprint arXiv:2605.02614},
year = {2026}
}