Page 98 - Read Online

Brochu et al. Art Int Surg 2024;4:411-26 https://dx.doi.org/10.20517/ais.2024.61 Page 425

4 has been shown to be more accurate but not necessarily more complete, its results could be more
comprehensive but are not guaranteed to be. This presents an important direction for future research. This
study compared ChatGPT’s responses to articles on the ASPS website. This may not accurately represent
how patients obtain their information. Additionally, our method of assessing accuracy and completeness
was limited. This study compares ChatGPT to information patients are likely to use, such as articles.
However, articles are not peer-reviewed and may not have entirely accurate or precise information even
when they are from reputable sources, such as the ASPS. We also did not utilize any numeric system of
comparison, which could be beneficial in the objective evaluation of these responses. Future studies could
create a numeric system of comparison based on current literature or reputable sources such as UpToDate,
or they could compare ChatGPT’s answers to the responses of plastic surgeons. Additional investigation
should focus on different types of surgeries and procedures to see if these results are generalizable. Finally,
our methodology also makes the assessment of comprehensibility and practicality difficult, so future
research could assess these topics by asking patients to rate these features.

Recommendation
While ChatGPT cannot replace the initial consultation with a surgeon, it could be recommended to patients
prior to these consultations to make them more efficient. Physicians could provide a pre-visit pamphlet as
part of virtual check-in that had instructions on the use of ChatGPT and potential questions patients could
ask prior to their visit. This would give patients at least a basic understanding of their procedure and
possible complications, so the majority of the visit could be spent on clarifying or patient-specific concerns.
Additionally, patients would have had time prior to the visit to digest some of the procedure-specific
information, reducing their possibility of becoming overwhelmed and allowing them to have a more
informed discussion. Guidelines could be established on which questions are best for patients to address
before the visit. Potentially, standardized, understanding-based questions could be asked by the physician at
the visit to ensure the pre-visit education has been successful. This could be further improved if the patient
was also referred to a reputable site like the ASPS, which would make their pre-consultation education even
more comprehensive.

In conclusion, this study provides support for ChatGPT’s usage as a tool to improve the efficiency of
consultations for aesthetic plastic surgery procedures and provides insight into the consistency of responses
to the same question across procedures. It is, however, important to recognize ChatGPT’s limitations in
answering questions in a patient/procedure-specific way. Therefore, it cannot replace an in-person
consultation with an experienced surgeon. Further research is needed to fully assess the reliability of
ChatGPT across days and accounts before it can be recommended as a patient learning tool.

DECLARATIONS
Authors’ contributions
Performed data acquisition as well as manuscript transcription and contribution to the design of the study:
Brochu BM
Made substantial contributions to the conception and design of the study, as well as assisting in manuscript
revision and technical support: Mirsky NA
Made substantial contributions to the conception and design of the study, as well as providing
administrative support and assisting in manuscript revisions: Thaller SR

Availability of data and materials
The data that support the findings of this study are available from the corresponding author upon reasonable
request.