Evaluating the quality and usability of responses generated by GPT Chat AI in response to common questions about prostate cancer prevention

Background and Aims: Prostate cancer is the most common malignant cancer in men and the second leading cause of cancer death in men after lung cancer. In describing the epidemiology of prostate cancer, it is considered a preventable disease. In addition to enduring the physical hardships caused by this disease, a person with cancer is also psychologically damaged. The incidence of this disease among men is increasing day by day. Now we decided to use artificial intelligence to examine common questions about prostate cancer prevention. Methods: This descriptive survey study answered ۲۳ questions of the Prostate Cancer Prevention Questionnaire via ChatGPT version ۴. We used Ecoa and Duval criteria, which collected a set of measurable criteria for metadata quality. To better understand the criteria, we examined the dimensions of comprehensiveness, accuracy, information richness, and inherent precision. The questions were completely generated by artificial intelligence, and the results of this study were analyzed by considering a negative score for each incorrect answer. Results: GPT Chat version ۴ provided answers. After matching the generated answers on prostate cancer prevention with the Echoa and Duval tool, it was shown that out of a total of ۲۳ questions, ۲۰ were answered correctly and one question was incomplete. The average confidence percentage in answering the questionnaire questions was ۸۶%. Conclusion: The findings of this study show that AI Chat GPT version ۴ effectively answers prostate cancer prevention questions. The results of the study showed that prevention can lead to changes in patients' self-care behaviors. Therefore, it is suggested that this model can be used as a useful approach in the health system to improve prostate cancer prevention behaviors.

کلیدواژه ها:

GPT Chat ، Cancer Prevention ، Prostate Cancer Patients