ChatGPT failed to spot over 50% of medical emergencies, study finds.
The AI responses were compared with assessments provided by doctors. Their tests showed ChatGPT ‘under-triaged’ more than half the cases it was presented with, the researchers found. #ClimateChange #Health #Science
https://www.pulsetoday.co.uk/news/clinical-areas/respiratory/chatgpt-failed-to-spot-over-50-of-medical-emergencies-study-finds/
Climate News Now
npub1y6…fm48s
2026-04-15 21:00:31 UTC
Author Public Key
npub1y60j2mgvr3a9ha534trtf2ngdj9npn8yvxw5ca4tfgg2vf95lzes9fm48sSeen on
wss://relay.ditto.pubPublished at
2026-04-15 21:00:31 UTCEvent JSON
{
"id": "82e4e87f45ef2b89871a2d75b78655fb5431b262938368c163c81a4e2690f02b",
"pubkey": "269f256d0c1c7a5bf691aac6b4aa686c8b30cce4619d4c76ab4a10a624b4f8b3",
"created_at": 1776286831,
"kind": 1,
"tags": [
[
"t",
"climatechange"
],
[
"t",
"health"
],
[
"t",
"science"
],
[
"proxy",
"https://mastodon.social/users/climatenewsnow/statuses/116410733800458113",
"activitypub"
],
[
"client",
"Mostr",
"31990:6be38f8c63df7dbf84db7ec4a6e6fbbd8d19dca3b980efad18585c46f04b26f9:mostr",
"wss://relay.ditto.pub"
]
],
"content": "ChatGPT failed to spot over 50% of medical emergencies, study finds.\n\nThe AI responses were compared with assessments provided by doctors. Their tests showed ChatGPT ‘under-triaged’ more than half the cases it was presented with, the researchers found. #ClimateChange #Health #Science\n\nhttps://www.pulsetoday.co.uk/news/clinical-areas/respiratory/chatgpt-failed-to-spot-over-50-of-medical-emergencies-study-finds/",
"sig": "b935ed700d643a8ed003a15090883eba51dfb708517ea98a7343d6e911684b0dd49157e2412c88fe510f879277f0f8e47fb0456d061645fa875355c613b9cc27"
}