Transforming free-text radiology reports into structured reports using ChatGPT: A study on thyroid ultrasonography

The importance of structured radiology reports has been fully recognized, as they facilitate efficient data extraction and promote collaboration among healthcare professionals. Our purpose is to assess the accuracy and reproducibility of ChatGPT, a large language model, in generating structured thyr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:European journal of radiology 2024-06, Vol.175, p.111458-111458, Article 111458
Hauptverfasser: Jiang, Huan, Xia, ShuJun, Yang, YiXuan, Xu, JiaLe, Hua, Qing, Mei, ZiHan, Hou, YiQing, Wei, MinYan, Lai, LiMei, Li, Ning, Dong, YiJie, Zhou, JianQiao
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The importance of structured radiology reports has been fully recognized, as they facilitate efficient data extraction and promote collaboration among healthcare professionals. Our purpose is to assess the accuracy and reproducibility of ChatGPT, a large language model, in generating structured thyroid ultrasound reports. This is a retrospective study that includes 184 nodules in 136 thyroid ultrasound reports from 136 patients. ChatGPT-3.5 and ChatGPT-4.0 were used to structure the reports based on ACR-TIRADS guidelines. Two radiologists evaluated the responses for quality, nodule categorization accuracy, and management recommendations. Each text was submitted twice to assess the consistency of the nodule classification and management recommendations. On 136 ultrasound reports from 136 patients (mean age, 52 years ± 12 [SD]; 61 male), ChatGPT-3.5 generated 202 satisfactory structured reports, while ChatGPT-4.0 only produced 69 satisfactory structured reports (74.3 % vs. 25.4 %, odds ratio (OR) = 8.490, 95 %CI: 5.775–12.481, p 
ISSN:0720-048X
1872-7727
DOI:10.1016/j.ejrad.2024.111458