Study: ChatGPT Health failed to recognise medical emergencies in tests
Signal de tendance 
3
mentions (7j)
3
mentions (30j)
1 mars 2026
premier signal
1
pays concernés
Contexte et analyse
Cette tendance "Study: ChatGPT Health failed to recognise medical emergencies in tests" a été détectée dans la catégorie Santé & Médecine avec un score de 79/100. Cette tendance montre des signes de ralentissement après une période d'intérêt.
Entités liées
Extraits des sources
‘Unbelievably dangerous’: experts sound alarm after ChatGPT Health fails to recognise medical emergencies | ChatGPT | The Guardian =============== ! - [x] Eight times out of 10, ChatGPT Health sent a suffocating woman to a future appointment she would not live to see, researches discovered. Photograph: Dado Ruvić/Reuters Eight times out of 10, ChatGPT Health sent a suffocating woman to a future appointment she would not live to see, researches discovered. Photograph: Dado Ruvić/Reuters...
— theguardian.com
Ce que disent les sources
"A study found ChatGPT Health did not recommend hospital care when medically necessary in more than half of tested cases, prompting expert warnings that the tool can be 'unbelievably dangerous.'"
"ChatGPT Health, a widely used consumer artificial intelligence (AI) tool that provides health guidance directly to the public—including advice about how..."
"Tension: ChatGPT's health feature failed to recognize textbook medical emergencies in testing — including heart attacks, strokes, and pulmonary embolisms..."
Article gratuit
Générez un article sur ce sujet tendance, gratuitement.
Recevez l'article par email dès qu'il est prêt.