Pilot applications of GPT-4 in radiation oncology: Summarizing patient symptom intake and targeted chatbot applications

David Jh Wu; Jean-Emmanuel Bibault

doi:10.1016/j.radonc.2023.109978

Pilot applications of GPT-4 in radiation oncology: Summarizing patient symptom intake and targeted chatbot applications

Radiother Oncol. 2024 Jan:190:109978. doi: 10.1016/j.radonc.2023.109978. Epub 2023 Oct 30.

Authors

David Jh Wu¹, Jean-Emmanuel Bibault²

Affiliations

¹ Department of Radiation Oncology, University of Minnesota Medical School, Minneapolis, MN, USA.
² Radiation Oncology Department, Georges Pompidou European Hospital, 75015, Paris, France; INSERM UMR1138, Centre de Recherche des Cordeliers, 75006, Paris, France. Electronic address: jean-emmanuel.bibault@aphp.fr.

PMID: 37913954
DOI: 10.1016/j.radonc.2023.109978

Abstract

This study explores using GPT-4 for radiation toxicity monitoring in prostate cancer treatments. Two methods were tested: a summarization method and a chatbot interface. Surveyed radiation oncologists preferred the summarization method for its accuracy and potential for adoption (median rating 8 vs 4, p =.002). Both methods saved time.

Keywords: ChatGPT; Machine Learning; Toxicity.

MeSH terms

Humans
Male
Pelvis
Prostate
Prostatic Neoplasms* / radiotherapy
Radiation Injuries*
Radiation Oncology*