Assessing ChatGPT’s summarization of 68Ga PSMA PET/CT reports for patients

Abstract

Purpose: ChatGPT has recently been the subject of many studies, and its responses to medical questions have been successful. We examined ChatGPT-4’s evaluation of structured 68Ga prostate-specific membrane antigen (PSMA) PET/CT reports of newly diagnosed prostate cancer patients. Methods: 68Ga PSMA PET/CT reports of 164 patients were entered to ChatGPT-4. ChatGPT-4 was asked to respond the following questions according to the PET/CT reports: 1-Has the cancer in the prostate extended to organs adjacent to the prostate? 2-Has the cancer in the prostate spread to neighboring lymph nodes? 3-Has the cancer in the prostate spread to lymph nodes in distant areas? 4-Has the cancer in the prostate spread to the bones? 5-Has the cancer in the prostate spread to other organs? ChatGPT-4’s responses were scored on a Likert-type scale for clarity and accuracy. Results: The mean scores for clarity were 4.93 ± 0.32, 4.95 ± 0.25, 4.96 ± 0.19, 4.99 ± 0.11, and 4.96 ± 0.30, respectively. The mean scores for accuracy were 4.87 ∓ 0.61, 4.87 ∓ 0.62, 4.79 ± 0.83, 4.96 ± 0.25, and 4.93 ± 0.45, respectively. Patients with distant lymphatic metastases had a lower mean accuracy score than those without (4.28 ± 1.45 vs. 4.94 ± 0.39; p < 0.001). ChatGPT-4’s responses in 13 patients (8%) had the potential for harmful information. Conclusion: ChatGPT-4 successfully interprets structured 68Ga PSMA PET/CT reports of reports of newly diagnosed prostate cancer patients. However, it is unlikely that ChatGPT-4 evaluations will replace physicians’ evaluations today, especially since it can produce fabricated information.