Login
Comparison of AI-generated radiology impressions: a multi-stakeholder evaluation
npj Digital Medicine, Published online: 04 April 2026; doi:10.1038/s41746-026-02586-6
Comparison of AI-generated radiology impressions: a multi-stakeholder evaluation
Reading view
Decipher-MR: a vision-language foundation model for 3D MRI representations
npj Digital Medicine, Published online: 04 April 2026; doi:10.1038/s41746-026-02596-4
Decipher-MR: a vision-language foundation model for 3D MRI representations
Understanding digital health technology implementation in rehabilitation and development of the Rehabilitation Technologies Implementation model
npj Digital Medicine, Published online: 04 April 2026; doi:10.1038/s41746-026-02599-1
Understanding digital health technology implementation in rehabilitation and development of the Rehabilitation Technologies Implementation model
An operational target trial emulation framework for causal inference using electronic health record data
npj Digital Medicine, Published online: 04 April 2026; doi:10.1038/s41746-026-02563-z
An operational target trial emulation framework for causal inference using electronic health record data
A neural-symbolic AI agent system for biomedical concept mapping
npj Digital Medicine, Published online: 04 April 2026; doi:10.1038/s41746-026-02594-6
A neural-symbolic AI agent system for biomedical concept mapping
HoloTrauma 3X Triadic AI Co reasoning for robot assisted emergency maxillofacial reconstruction
npj Digital Medicine, Published online: 04 April 2026; doi:10.1038/s41746-026-02573-x
HoloTrauma 3X Triadic AI Co reasoning for robot assisted emergency maxillofacial reconstruction
Developing psychosocial phenotypes to understand engagement with digital health technologies for heart failure
npj Digital Medicine, Published online: 04 April 2026; doi:10.1038/s41746-026-02571-z
Developing psychosocial phenotypes to understand engagement with digital health technologies for heart failure
New model, old risks: sociodemographic bias and adversarial hallucinations vulnerability in GPT-5
npj Digital Medicine, Published online: 04 April 2026; doi:10.1038/s41746-026-02584-8
We re-evaluated GPT-5 using our published pipelines: 500 emergency vignettes across 32 sociodemographic labels for bias, and adversarial prompts with fabricated details. GPT-5 showed no measurable improvement over GPT-4o in sociodemographic-linked decision variation, with several LGBTQIA+ groups flagged for mental-health screening in 100% of cases. Adversarial hallucination rates were higher (65% vs 53% for GPT-4o); a mitigation prompt reduced this to 7.67%.