Work

The portability paradox of foundation models for clinical decision support

Year: 2026

Type: article

Abstract: Yakdan et al. demonstrate that foundation models (FMs) trained to predict cervical spondylotic myelopathy from electronic health record data outperform traditional models on internal datasets but lose their advantage during external validation. This suggests that the feature-dense patterns learned by FMs may reduce their portability across settings, particularly for rare outcomes. As FMs approach clinical deployment, local validation, subgroup analysis, and attention to implementation burden are essential to inform health system planning and stewardship.

Source: npj Digital Medicine

DOI: 10.1038/s41746-026-02615-4

Authors: Kyra L. Rosen, Margaret Sui, Ariel Yuhan Ong, Joseph C. Kvedar

Institutions: Harvard University, Dana-Farber Cancer Institute, Moorfields Eye Hospital NHS Foundation Trust, NIHR Moorfields Biomedical Research Centre, University College London

Language: English

Topic: Machine Learning in Healthcare

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $4,090