13TH INTERNATIONAL GASTROINTESTINAL CANCERS CONFERENCE, Antalya, Türkiye, 30 Kasım - 03 Aralık 2023, ss.9-10
THE ACCURACY OF THE PATIENT INFORMATION
DATA PROVIDED BY CHATGPT ABOUT GASTRIC
CANCER
Duygu Ercan Uzundal, Burcu Ulaş Kahya, Nuriye Özdemir
Gazi University Faculty of Medicine, Department of Medical Oncology,
Ankara, Turkey
Aim: This study aims to evaluate the accuracy and reliability
of ChatGPT’s responses to frequently asked questions regarding
the prevention, diagnosis and treatment of gastric cancer
Methods: A set of 25 questions covering topics related to disease risk factors, screening, symptoms, treatment, and treatment
side effects were asked to ChatGPT, and two clinical oncologists
evaluated the responses independently. The questions were determined by reviewing the Stomach Cancer Patient Guideline of
ESMO and ASCO’s patient information website, cancer.net.
Results: Of the responses given by ChatGPT, 20 out of 25
(%80) were deemed accurate, two (%8) were rated as inaccurate, and the remaining three (%12) were considered insufficient.
There was no question that ChatGPT answered thoroughly incorrectly; answers considered insufficient included partially correct information. The answers of both physicians were consistent
with each other. (Figure 1)
Conclusion: The study’s findings suggest that ChatGPT provides patients with highly accurate information about stomach
cancer. However, it is important to remember that more research
is required to validate the use of AI chatbots in the context of
gastric/stomach cancer, particularly for those people for whom
the psychological effects of the disease may have a significant
impact. Additionally, given the complexity and individuality of
medical care, AI chatbots should not be considered a replacement for medical professionals but rather a supplementary tool
that can help patients access reliable information and support.
Overall, this study contributes to AI chatbots and their potential
use in oncology, highlighting both the benefits and limitations of
these technologies.
Keywords: ChatGPT, gastric cancer, patient information