X-FEMR: A Token-level Explainable Approach for Electronic Health Records Foundation Models using Transformer-based Models
arXiv:2607.06163v1 Announce Type: cross 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 pr
The increasing deployment of Foundation Models in sensitive domains like healthcare necessitates robust explainability methods to build trust and ensure ethical use.
This development addresses a critical barrier to the widespread adoption of AI in healthcare by providing transparency into 'black-box' models, which is crucial for clinical validation and regulatory compliance.
The ability to explain token-level outputs from FEMRs transforms these models from opaque decision-makers into auditable tools that clinical professionals can better understand and integrate into practice.
- · AI in Healthcare Developers
- · Healthcare Providers
- · Patients
- · Regulatory Bodies
- · Companies with opaque AI models
- · Traditional diagnostic methods
Improved trust and accelerated adoption of AI in clinical settings.
Reduced physician skepticism towards AI-driven diagnostics and treatment recommendations, leading to better patient outcomes.
The development of new regulatory frameworks specifically designed for explainable AI in medicine, setting a precedent for other high-stakes AI applications.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI