Author commentary on Marcello Maida et al.

Marcello Maida et al. The role of generative language systems in increasing patient awareness of colon cancer screening

Answers generated by ChatGPT to questions on colorectal cancer (CRC) screening were rated by 20 gastroenterology experts, 20 nonexperts, and 100 patients. Experts rated the overall accuracy (scale 1–6) as 4.8, and completeness and comprehensibility (scales 1–3) as 2.1 and 2.8, respectively. Patients rated the responses as complete, comprehensible, and trustable in 97 % to 100 % of cases. Nonetheless, these results must be interpreted with caution as they refer to a specific setting and cannot be generalized to overall ChatGPT performance.

Publication History

Article published online:
26 February 2025