Patient safety concerns with LLM chatbots.
🔍 Claude's problematic responses: 21.6%
📊 Llama's problematic responses: 43.2%
🚨 Unsafe replies: Claude (5%), GPT-4o & Llama (13%)
#HealthcareAI #PatientSafety
https://tnyp.me/gUOAqKzA/m
#patientsafety — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #patientsafety, aggregated by home.social.
-
-
Title: Non-lexical Sounds in ASR for Clinical Documentation
⚠️ NLCS poorly recognized in clinical ASR
📉 Google WER: 11.8%, Amazon WER: 12.8%
🚫 Clinically relevant NLCS misrecognized with 94.7% (Google) and 98.7% (Amazon) error rates
mastodon
#ClinicalDocumentation #ASR #PatientSafety #NLP #HealthcareTech