{"type":"ScholarlyArticle","title":"X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models","authors":[{"name":"Jie Huang","slug":"jie-huang","given":"Jie","family":"Huang","affiliation":""},{"name":"Pengfei Yin","slug":"pengfei-yin","given":"Pengfei","family":"Yin","affiliation":""},{"name":"Zihan Xu","slug":"zihan-xu","given":"Zihan","family":"Xu","affiliation":""},{"name":"Daniel Capurro","slug":"daniel-capurro","given":"Daniel","family":"Capurro","affiliation":""},{"name":"Mike Conway","slug":"mike-conway","given":"Mike","family":"Conway","affiliation":""},{"name":"Ting Dang","slug":"ting-dang","given":"Ting","family":"Dang","affiliation":""}],"abstract":"Foundation Models for Electronic Health Records (FEMRs) are pretrained on large-scale structured patient data, enabling them to convert longitudinal patient trajectories into generalizable representations for diverse clinical prediction tasks. Despite their effectiveness, FEMRs remain black-box models, raising concerns about bias, interpretability, and clinical trust. To address this, we propose the first token-level explainability approach for FEMRs. We train a Transformer-based surrogate model on input-output pairs from the FEMR across two prediction tasks, approximating its behavior while preserving temporal dynamics. We identify the most influential tokens, providing insights into how FEMRs leverage different aspects of patient history for predictions. To evaluate clinical relevance, we introduce a novel clinical alignment metric that quantifies the correspondence between the surrogate model’s key tokens and clinically validated features. Our results demonstrate that the surrogate closely approximates FEMR predictions and that token-level explanations align well with clinical knowledge, offering a practical framework for interpretable and trustworthy clinical AI.","doi":"10.24963/ijcai.2026/749","url":"https://ijcai.org/proceedings/2026/749","pdf":"https://ijcai.org/proceedings/2026/0749.pdf","markdown":"https://ijcai.org/proceedings/2026/749.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/749","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"AI and Health","track":"AI and Health","number":749,"pages":{"first":6734,"last":6742},"keywords":["Health data mining: Health data mining","EHR analysis: EHR analysis","Multimodal data: Multimodal data","Explainable AI: Explainable AI","Clinical decision support system: Clinical decision support system"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}