npj Digital Medicine, Published online: 07 April 2026; doi:10.1038/s41746-026-02593-7

Lightweight liquid neural networks decipher salivary metabolic fingerprinting for high-risk periodontitis screening in diabetes

npj Digital Medicine, Published online: 07 April 2026; doi:10.1038/s41746-026-02605-6

Evaluation of artificial intelligence-generated vignettes depicting patient chatbot use in psychiatric contexts

npj Digital Medicine, Published online: 07 April 2026; doi:10.1038/s41746-026-02615-4

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.

npj Digital Medicine, Published online: 07 April 2026; doi:10.1038/s41746-026-02470-3

Interpretable machine learning models for stroke risk prediction in patients with newly diagnosed atrial fibrillation

npj Digital Medicine, Published online: 06 April 2026; doi:10.1038/s41746-026-02600-x

Towards a physics informed digital twin to predict cerebral blood flow and cerebral vascular regulation

npj Digital Medicine, Published online: 06 April 2026; doi:10.1038/s41746-026-02525-5

Evaluating a digital serious game for learning medical terminology in a randomized controlled trial

npj Digital Medicine, Published online: 06 April 2026; doi:10.1038/s41746-026-02621-6

GenAI is increasingly used to draft replies to patient portal messages to reduce clinician workload. Evidence shows modest utilization and measurable workflow effects, alongside safety risks when clinicians miss errors or accept drafts with minimal editing. As deployments scale with deeper EHR integration and expanding transparency mandates, this Comment proposes governance that preserves efficiency without normalizing unsafe delegation: scoped use, risk tiering, accountable human authorship, auditability, and patient-facing transparency.