phaidra.vetmeduni.ac.at o:5089 DOI 10.1371/journal.pone.0337261 Beyond accuracy: Quantifying the reliability of multiple instance learning for whole slide image classification Machine learning models have become integral to many fields, but their reliability, defined as producing dependable, trustworthy, and domain-consistent predictions, remains a critical concern. Multiple Instance Learning (MIL) models designed for Whole Slide Image (WSI) classification in computational pathology are rarely evaluated in terms of reliability, leaving a key gap in understanding their suitability for high-stakes applications like clinical decision-making. In this paper, we address this gap by introducing three quantitative metrics for reliability assessment and applying them to several widely used MIL architectures across three region-wise annotated pathology datasets. Our findings indicate that the mean pooling instance (MEAN-POOL-INS) model demonstrates superior reliability compared to other networks, despite its simple architectural design and computational efficiency. These findings underscore the need of reliability evaluation alongside predictive performance in MIL models and establish MEAN-POOL-INS as a strong, trustworthy baseline for future research. eng Machine Learning Cancers And Neoplasms Sequence Alignment Breast Cancer Tissue Distribution Genome Annotation Reliability Learning Curves 2026-05-05T12:55:46.120Z LOMv1.0 Author BEGIN:VCARD VERSION:3.0 N:Keshvarikhojasteh;Hassan; FN:Hassan Keshvarikhojasteh X-ORCID:https://orcid.org/0000-0002-5025-0468 END:VCARD BEGIN:VCARD VERSION:3.0 N:Aubreville;Marc; FN:Marc Aubreville END:VCARD BEGIN:VCARD VERSION:3.0 N:Bertram;Christof A.; FN:Christof A. Bertram X-ORCID:https://orcid.org/0000-0002-2402-9997 END:VCARD BEGIN:VCARD VERSION:3.0 N:Pluim;Josien P. W.; FN:Josien P. W. Pluim END:VCARD BEGIN:VCARD VERSION:3.0 N:Veta;Mitko; FN:Mitko Veta END:VCARD https://w3id.org/kim/hcrt/scheme https://w3id.org/kim/hcrt/text Textdokument Text LOMv1.0 yes https://creativecommons.org/licenses/by/4.0 application/pdf 13799670 https://phaidra.vetmeduni.ac.at/o:5089 https://phaidra.vetmeduni.ac.at/api/object/o:5089/thumbnail LOMv1.0 discipline