Exploring The Boundaries Of GPT-4 In Radiology
Liu Qianchu, Hyland Stephanie, Bannur Shruthi, Bouzid Kenza, Castro Daniel C., Wetscherek Maria Teodora, Tinn Robert, Sharma Harshita, Pérez-garcía Fernando, Schwaighofer Anton, Rajpurkar Pranav, Khanna Sameer Tajdin, Poon Hoifung, Usuyama Naoto, Thieme Anja, Nori Aditya V., Lungren Matthew P., Oktay Ozan, Alvarez-valle Javier. Arxiv 2023
[Paper]
The recent success of general-domain large language models (LLMs) has significantly changed the natural language processing paradigm towards a unified foundation model across domains and applications. In this paper, we focus on assessing the performance of GPT-4, the most capable LLM so far, on the text-based applications for radiology reports, comparing against state-of-the-art (SOTA) radiology-specific models. Exploring various prompting strategies, we evaluated GPT-4 on a diverse range of common radiology tasks and we found GPT-4 either outperforms or is on par with current SOTA radiology models. With zero-shot prompting, GPT-4 already obtains substantial gains (\(\approx\) 10% absolute improvement) over radiology models in temporal sentence similarity classification (accuracy) and natural language inference (\(F_1\)). For tasks that require learning dataset-specific style or schema (e.g. findings summarisation), GPT-4 improves with example-based prompting and matches supervised SOTA. Our extensive error analysis with a board-certified radiologist shows GPT-4 has a sufficient level of radiology knowledge with only occasional errors in complex context that require nuanced domain knowledge. For findings summarisation, GPT-4 outputs are found to be overall comparable with existing manually-written impressions.
Similar Work