Turkish Journal of Pathology

Türk Patoloji Dergisi

Turkish Journal of Pathology

Turkish Journal of Pathology

E-pub Ahead Of Print

Large Language Models as a Rapid and Objective Tool for Pathology Report Data Extraction

Beyza BOLAT 1, Ozgur Can EREN 2,3,4, A. Humeyra DUR KARASAYAR 3, Cisel AYDIN MERICOZ 2, Cigdem GUNDUZ-DEMIR 1,5,6, Ibrahim KULAC 2,3,5,7

1 Koc University School of Medicine, Koc University, ISTANBUL, TURKEY
2 Department of Pathology, School of Medicine, Koc University, ISTANBUL, TURKEY
3 Graduate School of Health Sciences, Koc University, ISTANBUL, TURKEY
4 Koc University IsBank Research Center for Infectious Diseases, ISTANBUL, TURKEY
5 Koc University & Is Bank Artificial Intelligence Center, ISTANBUL, TURKEY
6 Department of Computer Engineering, Koc University, ISTANBUL, TURKEY
7 Research Center for Translational Medicine, Koc University, ISTANBUL, TURKEY

DOI: 10.5146/tjpath.2024.13256
Viewed: 461
 - 
Downloaded : 71

Medical institutions continuously create a substantial amount of data that is used for scientific research. One of the departments with a great amount of archived data is the pathology department. Pathology archives hold the potential to create a case series of valuable rare entities or large cohorts of common entities. The major problem in creation of these databases is data extraction which is still commonly done manually and is highly laborious and error prone. For these reasons, we offer using large language models to overcome these challenges. Ten pathology reports of selected resection specimens were retrieved from electronic archives of Koç University Hospital for the initial set. These reports were de-identified and uploaded to ChatGPT and Google Bard. Both algorithms were asked to turn the reports in a synoptic report format that is easy to export to a data editor such as Microsoft Excel or Google Sheets. Both programs created tables with Google Bard facilitating the creation of a spreadsheet from the data automatically. In conclusion, we propose the use of AI-assisted data extraction for academic research purposes, as it may enhance efficiency and precision compared to manual data entry.

Keywords : Large language models (LLMs), Pathology, Generative pre-trained transformer-4 (GPT-4), ChatGPT, Bard