Multilingual Natural Language Processing Model for Radiology Reports -- The Summary is all you need!

TL;DR

This study developed a multilingual radiology report summarization model that outperforms existing single-language and general models, achieving high clinical reliability across English, Portuguese, and German reports.

Contribution

It introduces a fine-tuned multilingual Transformer model capable of summarizing radiology reports in multiple languages, filling a gap in current research.

Findings

70% of summaries matched or exceeded human quality in blind tests

Multilingual model outperformed single-language and general models

Model demonstrated substantial clinical reliability

Abstract

The impression section of a radiology report summarizes important radiology findings and plays a critical role in communicating these findings to physicians. However, the preparation of these summaries is time-consuming and error-prone for radiologists. Recently, numerous models for radiology report summarization have been developed. Nevertheless, there is currently no model that can summarize these reports in multiple languages. Such a model could greatly improve future research and the development of Deep Learning models that incorporate data from patients with different ethnic backgrounds. In this study, the generation of radiology impressions in different languages was automated by fine-tuning a model, publicly available, based on a multilingual text-to-text Transformer to summarize findings available in English, Portuguese, and German radiology reports. In a blind test, two board-certified radiologists indicated that for at least 70% of the system-generated summaries, the quality matched or exceeded the corresponding human-written summaries, suggesting substantial clinical reliability. Furthermore, this study showed that the multilingual model outperformed other models that specialized in summarizing radiology reports in only one language, as well as models that were not specifically designed for summarizing radiology reports, such as ChatGPT.