Your browser doesn't support javascript.
loading
Transcending Language Barriers: Can ChatGPT Be the Key to Enhancing Multilingual Accessibility in Healthcare?
Gulati, Vaibhav; Roy, Shambo Guha; Moawad, Ahmed; Garcia, Daniela; Babu, Aparna; Poot, Jeffrey D; Teytelboym, Oleg M.
Afiliação
  • Gulati V; Department of Radiology, Mercy Catholic Medical Center, Darby, PA. Electronic address: vaibhav-gulati@outlook.com.
  • Roy SG; Department of Radiology, Mercy Catholic Medical Center, Darby, PA; Present affiliation: Department of Radiology, Massachusetts General Hospital, Boston, MA.
  • Moawad A; Department of Radiology, Mercy Catholic Medical Center, Darby, PA.
  • Garcia D; Department of Radiology, Mercy Catholic Medical Center, Darby, PA.
  • Babu A; Department of Radiology, Mercy Catholic Medical Center, Darby, PA.
  • Poot JD; Department of Radiology, Mercy Catholic Medical Center, Darby, PA.
  • Teytelboym OM; Department of Radiology, Mercy Catholic Medical Center, Darby, PA.
J Am Coll Radiol ; 2024 Jun 14.
Article em En | MEDLINE | ID: mdl-38880289
ABSTRACT

OBJECTIVE:

To explore the capabilities of ChatGPT for the purpose of simplifying and translating radiology reports into Spanish, Hindi, and Russian languages, with comparisons to its performance in simplifying to the English language.

METHODS:

50 deidentified abdomen-pelvis CT reports were fed to ChatGPT (4.0), instructing it to simplify and translate the report. The processed reports were rated on factual correctness (I), potential harmful errors (II), completeness (III), and explanation of medical terms (IV). The translated versions were also rated on the quality of translation (V). The scores in each category were compared between the translated versions and each translated version was compared with the English version in the first four categories. The original reports and the simplified English reports were rated on the Flesch Reading Ease Score (FRES) and the Flesch Kincaid Grade Level (FKRL).

RESULTS:

The Spanish translation outperformed the Hindi and Russian version significantly in categories I and III (p<0.05). All translated versions performed significantly worse compared to the English version in category IV (p<0.001). Notably, the Hindi translated version performed significantly worse in all 4 categories (p<0.05). The Russian translated version was also significantly worse in category III (p<0.05). In the first three categories, the Spanish translation, and the Russian translation in the first two categories demonstrated no statistically significant difference from the English version. No statistically significant difference was observed in the FRES and FKRL of the simplified English reports. Typographical errors in the original reports negatively affected the translation.

CONCLUSION:

ChatGPT demonstrates potential ability in translating reports and communicating pertinent clinical information with limited errors. More training and tailoring are required for languages that are not as commonly used in medical literature. LLMs can be used for translating and simplifying radiology reports, potentially improving access to healthcare, and helping reduce healthcare costs.
Palavras-chave

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Ano de publicação: 2024 Tipo de documento: Article

Texto completo: 1 Coleções: 01-internacional Base de dados: MEDLINE Idioma: En Ano de publicação: 2024 Tipo de documento: Article