As a guest user you are not logged in or recognized by your IP address. You have
access to the Front Matter, Abstracts, Author Index, Subject Index and the full
text of Open Access publications.
Triage is used in emergency departments to ensure timely patient care according to urgency of treatment. However, triage accuracy and efficiency remain challenging due to time-constraints and high demand. This proof-of-concept study evaluates an AI-powered triage system that leverages speech recognition (STT) and large language models (LLMs) to process patient interactions in triage and to assign an Emergency Severity Index (ESI) triage level and a classification of the main presenting complaint according to the Canadian Emergency Department Information System (CEDIS). In Switzerland, different Swiss German dialects add to the complexity of the task. STT models achieved word error rates (WER) of 2.3% for High German and 17.66% for Swiss German. Despite the high WER, the AI’s classification accuracy reached 90–100% for ESI levels and CEDIS codes. These results highlight the potential of integrating AI into triage workflows, enhancing consistency and reducing the documentation burden for clinical staff. Future research should address multi-language adaptation and data security to ensure seamless implementation in real-world settings.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.
This website uses cookies
We use cookies to provide you with the best possible experience. They also allow us to analyze user behavior in order to constantly improve the website for you. Info about the privacy policy of IOS Press.