Back

ChatGPT for automating lung cancer staging: feasibility study on open radiology report dataset

Nakamura, Y.; Kikuchi, T.; Yamagishi, Y.; Hanaoka, S.; Nakao, T.; Miki, S.; Yoshikawa, T.; Abe, O.

2023-12-13 radiology and imaging
10.1101/2023.12.11.23299107 medRxiv
Show abstract

ObjectivesCT imaging is essential in the initial staging of lung cancer. However, free-text radiology reports do not always directly mention clinical TNM stages. We explored the capability of OpenAIs ChatGPT to automate lung cancer staging from CT radiology reports. MethodsWe used MedTxt-RR-JA, a public de-identified dataset of 135 CT radiology reports for lung cancer. Two board-certified radiologists assigned clinical TNM stage for each radiology report by consensus. We used a part of the dataset to empirically determine the optimal prompt to guide ChatGPT. Using the remaining part of the dataset, we (i) compared the performance of two ChatGPT models (GPT-3.5 Turbo and GPT-4), (ii) compared the performance when the TNM classification rule was or was not presented in the prompt, and (iii) performed subgroup analysis regarding the T category. ResultsThe best accuracy scores were achieved by GPT-4 when it was presented with the TNM classification rule (52.2%, 78.9%, and 86.7% for the T, N, and M categories). Most ChatGPTs errors stemmed from challenges with numerical reasoning and insufficiency in anatomical or lexical knowledge. ConclusionsChatGPT has the potential to become a valuable tool for automating lung cancer staging. It can be a good practice to use GPT-4 and incorporate the TNM classification rule into the prompt. Future improvement of ChatGPT would involve supporting numerical reasoning and complementing knowledge. Clinical relevance statementChatGPTs performance for automating cancer staging still has room for enhancement, but further improvement would be helpful for individual patient care and secondary information usage for research purposes. Key pointsO_LIChatGPT, especially GPT-4, has the potential to automatically assign clinical TNM stage of lung cancer based on CT radiology reports. C_LIO_LIIt was beneficial to present the TNM classification rule to ChatGPT to improve the performance. C_LIO_LIChatGPT would further benefit from supporting numerical reasoning or providing anatomical knowledge. C_LI Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=119 SRC="FIGDIR/small/23299107v1_ufig1.gif" ALT="Figure 1"> View larger version (24K): org.highwire.dtl.DTLVardef@15e92c2org.highwire.dtl.DTLVardef@1f53392org.highwire.dtl.DTLVardef@10cf0b1org.highwire.dtl.DTLVardef@8e0150_HPS_FORMAT_FIGEXP M_FIG C_FIG

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.