Your browser doesn't support javascript.
loading
Conversational artificial intelligence (chatGPT™) in the management of complex colorectal cancer patients: early experience.
Choo, Jeong Min; Ryu, Hyo Seon; Kim, Ji Seon; Cheong, Ju Yong; Baek, Se-Jin; Kwak, Jung Myun; Kim, Jin.
Afiliação
  • Choo JM; Korea University Anam Hospital, Division of Colon and Rectal Surgery, Department of Surgery, Korea University College of Medicine, Seoul, South Korea.
  • Ryu HS; Korea University Anam Hospital, Division of Colon and Rectal Surgery, Department of Surgery, Korea University College of Medicine, Seoul, South Korea.
  • Kim JS; Korea University Anam Hospital, Division of Colon and Rectal Surgery, Department of Surgery, Korea University College of Medicine, Seoul, South Korea.
  • Cheong JY; Korea University Anam Hospital, Division of Colon and Rectal Surgery, Department of Surgery, Korea University College of Medicine, Seoul, South Korea.
  • Baek SJ; Korea University Anam Hospital, Division of Colon and Rectal Surgery, Department of Surgery, Korea University College of Medicine, Seoul, South Korea.
  • Kwak JM; Korea University Anam Hospital, Division of Colon and Rectal Surgery, Department of Surgery, Korea University College of Medicine, Seoul, South Korea.
  • Kim J; Korea University Anam Hospital, Division of Colon and Rectal Surgery, Department of Surgery, Korea University College of Medicine, Seoul, South Korea.
ANZ J Surg ; 94(3): 356-361, 2024 Mar.
Article em En | MEDLINE | ID: mdl-37905713
ABSTRACT

INTRODUCTION:

In 2022 chatGPT™ (OpenAI, San Francisco) was introduced to the public. The complex reasoning and the natural language processing (NLP) ability of the AI platform has generated much excitement about the potential applications. This study conducted a preliminary analysis of the chatGPT™'s ability to formulate a management plan in accordance with oncological principles for patients with colorectal cancer.

METHODOLOGY:

Colorectal cancer cases discussed in the multidisciplinary tumor (MDT) board at a single tertiary institution between September 2022 and January 2023 were prospectively collected. The treatment recommendations made by the chatGPT™ for Stage IV, recurrent, synchronous colorectal cancer were analysed for adherence to oncological principles. The recommendations by chatGPT™ were compared with the decision plans made by the MDT.

RESULTS:

In all cases, the chatGPT™ was able to adhere to oncological principles. The recommendations in all 30 cases factored in the patient's overall health and functional status. The oncological management recommendation concordance rate between chatGPT™ and the MDT was 86.7%.

CONCLUSIONS:

This study shows a high concordance rate of the chatGPT™'s recommendations with that given by the MDT in the management of complex colorectal patients. This will need to be verified in a larger prospective study.
Assuntos
Palavras-chave

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Inteligência Artificial / Neoplasias Colorretais Limite: Humans Idioma: En Ano de publicação: 2024 Tipo de documento: Article

Texto completo: 1 Base de dados: MEDLINE Assunto principal: Inteligência Artificial / Neoplasias Colorretais Limite: Humans Idioma: En Ano de publicação: 2024 Tipo de documento: Article