GPT-5 needs structured MRI descriptions to grade endolymphatic hydrops reliably
OBJECTIVE To evaluate GPT-5 for grading cochlear and vestibular endolymphatic hydrops (EH) on delayed gadolinium-enhanced 3D-FLAIR MRI in Ménière's disease (MD) and to assess prompting strategies and human-AI collaboration. MATERIALS AND METHODS This retrospective study included 436 patients with MD (872 ears). GPT-5 graded cochlear and vestibular EH under multiple prompting strategies and was compared with junior and senior neuroradiologists in independent and GPT-5-assisted workflows. Accuracy (ACC), AUC, F1 score, agreement, and expert-rated clinical usefulness were assessed. RE...
LLMs in mental health care show promise but evidence still too uncertain for routine use
BACKGROUND General-purpose large language models (LLMs) are increasingly being tested in mental health care, where language is central to assessment, diagnosis, risk evaluation, therapeutic interaction, monitoring, and patient education. However,
ECG foundation model shows broad potential for cardiovascular diagnosis
A large-scale ECG foundation model trained on more than 1.7 million ECGs paired with clinician reports consistently outperformed supervised and non-ECG foundation models across cardiovascular diagnosis and prediction tasks. The model, called ECG-C...
