A Comparison of ChatGPT and Multidisciplinary Team Meeting Treatment Recommendations in 10 Consecutive Cervical Cancer Patients

Background The preparation of multidisciplinary team (MDT) meetings can be time-consuming. In addition to the clinical data being available digitally in subsystems, the preparation of more complex cases requires literature research. Several expert systems have been developed to support this process. However, the interaction with these systems has to be trained. Current development enables linguistic interaction with such artificial intelligence (AI) systems. To the best of our knowledge, these have not been tested as premedical screening tools for MDT. Methods This is a retrospective consecutive case series of 10 cervical cancer cases comparing the medical recommendations of the MDT and artificial intelligence (AI) on a low level (i.e., surgery, systemic treatment, and radiotherapy). Results The clinical cases ranged from primary diagnosis via suspected recurrence to palliative settings. The AI repeatedly stated that medical professionals need to be consulted before treatment decisions. The AI answers ranged from no agreement to overachievement by mentioning treatment options for preexisting risk factors (such as obesity). In standard cases, the AI answer matched well with the expert recommendations. In some cases, the AI answers were contrary to our treatment recommendation. Conclusion The interaction with current language AIs is temptingly easy, and the replies are very understandable. Despite the AI warning regarding medical recommendations in the majority of our cases, there was a good match with the MDT recommendations. However, in some cases, the medical evidence behind the answers was missing or in the worst case fictional. In our case series, the AI did not meet the requirements to support a clinical MDT meeting by prescreening the therapeutic options. However, it did exceed the expectations regarding the risk factors of the patients.