Evaluating GPT-4.1 Mini and GPT-5 in Postmastectomy Lymphedema Patient Education: A Comparative Study of Usefulness and Reliability

Vollständiger Abstract

Worum geht es in dieser Arbeit?

Aim: To compare the reliability and usefulness of GPT-4.1 mini and GPT-5 in postmastectomy lymphedema patient education.Materials and Methods: Twenty patient-centered questions were developed from reputable sources. Responses from both models were independently rated by three blinded physiatrists using 7-point Likert scales for reliability and usefulness.Results: GPT-5 demonstrated higher usefulness and reliability scores compared to GPT-4.1 mini (p = 0.005 and p = 0.021, respectively).Conclusions: Both models produced reliable and useful responses for lymphedema education. GPT-5 demonstrated higher usefulness and reliability scores, although these differences appear to reflect incremental improvements rather than substantial differences in clinical applicability. GPT-4.1 mini may already support basic patient education tasks. Future research should integrate patient usability data and real-time clinical resources to optimize AI-assisted rehabilitation.