Researchers tested APOLLAI, an AI system that detects stroke-related neurological deficits from video and audio recordings. They compared it with emergency medical services (EMS) personnel in 295 patients with suspected stroke at Nimes University Hospital. Seven stroke neurologists scored five National Institutes of Health Stroke Scale items: gaze, facial palsy, arm weakness, aphasia and dysarthria. Their combined scores formed the reference standard, and about 15 EMS raters assessed each patient. Overall, APOLLAI had 78.5% sensitivity versus 59.4% for EMS, specificity of 87.0% versus 85.9%, and AUC 0.882. Neurologist agreement was only moderate (mean kappa 0.541), and all assessments used recordings at one centre.
Why it is interesting: Nearly one-third of strokes go unrecognised before hospital arrival. On the same recordings, the AI system flagged more deficits than EMS raters while keeping specificity.
Cite this item
BibTeX
Free sign-up. A digest of the new papers twice a week, grouped by domain.
Other drivers in Data, models and systems
-
Forecasts and their record
How the forecasts are made, how well they explained the past, and how well mortality can be forecast — and by whom.
4 this week -
What linked data reveals
What linked registries make it possible to know about whole populations
8 this week -
AI in medicine
Whether machine learning predicts, detects and decides better than the tools we have, and whether that has yet changed an outcome for a population.
3 this week -
Health systems and access
What the health system can provide, who gets it, and whether the gaps in health between groups are widening.
4 this week -
Value in health
What a treatment, health programme or policy is worth against what it costs, and how far the models that decide it can be trusted.
5 this week -
Revisions and new sources
What the figures are built from, what is newly available, and how much the numbers move when they are revised.
6 this week
