Real-world Deployment and Evaluation of PErioperative AI CHatbot (PEACH) -- a Large Language Model Chatbot for Perioperative Medicine

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ke, Yu He, Jin, Liyuan, Elangovan, Kabilan, Ong, Bryan Wen Xi, Oh, Chin Yang, Sim, Jacqueline, Loh, Kenny Wei-Tsen, Soh, Chai Rick, Cheng, Jonathan Ming Hua, Lee, Aaron Kwang Yang, Ting, Daniel Shu Wei, Liu, Nan, Abdullah, Hairil Rizal
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912168982609920
author Ke, Yu He
Jin, Liyuan
Elangovan, Kabilan
Ong, Bryan Wen Xi
Oh, Chin Yang
Sim, Jacqueline
Loh, Kenny Wei-Tsen
Soh, Chai Rick
Cheng, Jonathan Ming Hua
Lee, Aaron Kwang Yang
Ting, Daniel Shu Wei
Liu, Nan
Abdullah, Hairil Rizal
author_facet Ke, Yu He
Jin, Liyuan
Elangovan, Kabilan
Ong, Bryan Wen Xi
Oh, Chin Yang
Sim, Jacqueline
Loh, Kenny Wei-Tsen
Soh, Chai Rick
Cheng, Jonathan Ming Hua
Lee, Aaron Kwang Yang
Ting, Daniel Shu Wei
Liu, Nan
Abdullah, Hairil Rizal
contents Large Language Models (LLMs) are emerging as powerful tools in healthcare, particularly for complex, domain-specific tasks. This study describes the development and evaluation of the PErioperative AI CHatbot (PEACH), a secure LLM-based system integrated with local perioperative guidelines to support preoperative clinical decision-making. PEACH was embedded with 35 institutional perioperative protocols in the secure Claude 3.5 Sonet LLM framework within Pair Chat (developed by Singapore Government) and tested in a silent deployment with real-world data. Accuracy, safety, and usability were assessed. Deviations and hallucinations were categorized based on potential harm, and user feedback was evaluated using the Technology Acceptance Model (TAM). Updates were made after the initial silent deployment to amend one protocol. In 240 real-world clinical iterations, PEACH achieved a first-generation accuracy of 97.5% (78/80) and an overall accuracy of 96.7% (232/240) across three iterations. The updated PEACH demonstrated improved accuracy of 97.9% (235/240), with a statistically significant difference from the null hypothesis of 95% accuracy (p = 0.018, 95% CI: 0.952-0.991). Minimal hallucinations and deviations were observed (both 1/240 and 2/240, respectively). Clinicians reported that PEACH expedited decisions in 95% of cases, and inter-rater reliability ranged from kappa 0.772-0.893 within PEACH and 0.610-0.784 among attendings. PEACH is an accurate, adaptable tool that enhances consistency and efficiency in perioperative decision-making. Future research should explore its scalability across specialties and its impact on clinical outcomes.
format Preprint
id arxiv_https___arxiv_org_abs_2412_18096
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Real-world Deployment and Evaluation of PErioperative AI CHatbot (PEACH) -- a Large Language Model Chatbot for Perioperative Medicine
Ke, Yu He
Jin, Liyuan
Elangovan, Kabilan
Ong, Bryan Wen Xi
Oh, Chin Yang
Sim, Jacqueline
Loh, Kenny Wei-Tsen
Soh, Chai Rick
Cheng, Jonathan Ming Hua
Lee, Aaron Kwang Yang
Ting, Daniel Shu Wei
Liu, Nan
Abdullah, Hairil Rizal
Artificial Intelligence
Large Language Models (LLMs) are emerging as powerful tools in healthcare, particularly for complex, domain-specific tasks. This study describes the development and evaluation of the PErioperative AI CHatbot (PEACH), a secure LLM-based system integrated with local perioperative guidelines to support preoperative clinical decision-making. PEACH was embedded with 35 institutional perioperative protocols in the secure Claude 3.5 Sonet LLM framework within Pair Chat (developed by Singapore Government) and tested in a silent deployment with real-world data. Accuracy, safety, and usability were assessed. Deviations and hallucinations were categorized based on potential harm, and user feedback was evaluated using the Technology Acceptance Model (TAM). Updates were made after the initial silent deployment to amend one protocol. In 240 real-world clinical iterations, PEACH achieved a first-generation accuracy of 97.5% (78/80) and an overall accuracy of 96.7% (232/240) across three iterations. The updated PEACH demonstrated improved accuracy of 97.9% (235/240), with a statistically significant difference from the null hypothesis of 95% accuracy (p = 0.018, 95% CI: 0.952-0.991). Minimal hallucinations and deviations were observed (both 1/240 and 2/240, respectively). Clinicians reported that PEACH expedited decisions in 95% of cases, and inter-rater reliability ranged from kappa 0.772-0.893 within PEACH and 0.610-0.784 among attendings. PEACH is an accurate, adaptable tool that enhances consistency and efficiency in perioperative decision-making. Future research should explore its scalability across specialties and its impact on clinical outcomes.
title Real-world Deployment and Evaluation of PErioperative AI CHatbot (PEACH) -- a Large Language Model Chatbot for Perioperative Medicine
topic Artificial Intelligence
url https://arxiv.org/abs/2412.18096