Cargando…
AI chatbots not yet ready for clinical use
As large language models (LLMs) expand and become more advanced, so do the natural language processing capabilities of conversational AI, or “chatbots”. OpenAI's recent release, ChatGPT, uses a transformer-based model to enable human-like text generation and question-answering on general domain...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10130576/ https://www.ncbi.nlm.nih.gov/pubmed/37122812 http://dx.doi.org/10.3389/fdgth.2023.1161098 |
_version_ | 1785030986783784960 |
---|---|
author | Au Yeung, Joshua Kraljevic, Zeljko Luintel, Akish Balston, Alfred Idowu, Esther Dobson, Richard J. Teo, James T. |
author_facet | Au Yeung, Joshua Kraljevic, Zeljko Luintel, Akish Balston, Alfred Idowu, Esther Dobson, Richard J. Teo, James T. |
author_sort | Au Yeung, Joshua |
collection | PubMed |
description | As large language models (LLMs) expand and become more advanced, so do the natural language processing capabilities of conversational AI, or “chatbots”. OpenAI's recent release, ChatGPT, uses a transformer-based model to enable human-like text generation and question-answering on general domain knowledge, while a healthcare-specific Large Language Model (LLM) such as GatorTron has focused on the real-world healthcare domain knowledge. As LLMs advance to achieve near human-level performances on medical question and answering benchmarks, it is probable that Conversational AI will soon be developed for use in healthcare. In this article we discuss the potential and compare the performance of two different approaches to generative pretrained transformers—ChatGPT, the most widely used general conversational LLM, and Foresight, a GPT (generative pretrained transformer) based model focused on modelling patients and disorders. The comparison is conducted on the task of forecasting relevant diagnoses based on clinical vignettes. We also discuss important considerations and limitations of transformer-based chatbots for clinical use. |
format | Online Article Text |
id | pubmed-10130576 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-101305762023-04-27 AI chatbots not yet ready for clinical use Au Yeung, Joshua Kraljevic, Zeljko Luintel, Akish Balston, Alfred Idowu, Esther Dobson, Richard J. Teo, James T. Front Digit Health Digital Health As large language models (LLMs) expand and become more advanced, so do the natural language processing capabilities of conversational AI, or “chatbots”. OpenAI's recent release, ChatGPT, uses a transformer-based model to enable human-like text generation and question-answering on general domain knowledge, while a healthcare-specific Large Language Model (LLM) such as GatorTron has focused on the real-world healthcare domain knowledge. As LLMs advance to achieve near human-level performances on medical question and answering benchmarks, it is probable that Conversational AI will soon be developed for use in healthcare. In this article we discuss the potential and compare the performance of two different approaches to generative pretrained transformers—ChatGPT, the most widely used general conversational LLM, and Foresight, a GPT (generative pretrained transformer) based model focused on modelling patients and disorders. The comparison is conducted on the task of forecasting relevant diagnoses based on clinical vignettes. We also discuss important considerations and limitations of transformer-based chatbots for clinical use. Frontiers Media S.A. 2023-04-12 /pmc/articles/PMC10130576/ /pubmed/37122812 http://dx.doi.org/10.3389/fdgth.2023.1161098 Text en © 2023 Au Yeung, Kraljevic, Luintel, Balston, Idowu, Dobson and Teo. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) (https://creativecommons.org/licenses/by/4.0/) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Digital Health Au Yeung, Joshua Kraljevic, Zeljko Luintel, Akish Balston, Alfred Idowu, Esther Dobson, Richard J. Teo, James T. AI chatbots not yet ready for clinical use |
title | AI chatbots not yet ready for clinical use |
title_full | AI chatbots not yet ready for clinical use |
title_fullStr | AI chatbots not yet ready for clinical use |
title_full_unstemmed | AI chatbots not yet ready for clinical use |
title_short | AI chatbots not yet ready for clinical use |
title_sort | ai chatbots not yet ready for clinical use |
topic | Digital Health |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10130576/ https://www.ncbi.nlm.nih.gov/pubmed/37122812 http://dx.doi.org/10.3389/fdgth.2023.1161098 |
work_keys_str_mv | AT auyeungjoshua aichatbotsnotyetreadyforclinicaluse AT kraljeviczeljko aichatbotsnotyetreadyforclinicaluse AT luintelakish aichatbotsnotyetreadyforclinicaluse AT balstonalfred aichatbotsnotyetreadyforclinicaluse AT idowuesther aichatbotsnotyetreadyforclinicaluse AT dobsonrichardj aichatbotsnotyetreadyforclinicaluse AT teojamest aichatbotsnotyetreadyforclinicaluse |