Page 96 - Read Online
P. 96
Brochu et al. Art Int Surg 2024;4:411-26 https://dx.doi.org/10.20517/ais.2024.61 Page 423
Similarly to the corresponding breast lift section, there is no blog on the timeline for blepharoplasty
recovery. There is an article that explains what to expect during recovery. ChatGPT’s points on following
postoperative instructions, including the use of cold compresses, are reflected here. The ASPS article
mentions that most patients can go out in public 10-14 days after surgery. No specific timeline is included in
the ChatGPT response. However, no other recovery timeline (like when to resume strenuous activity) is
mentioned. Nothing is mentioned by the ASPS regarding the assistance the patient may need during this
recovery.
How long will my eyelid surgery last?
This response begins with a short paragraph discussing how results vary and blepharoplasty does not stop
the natural aging process. It then lists the following considerations with 2-3 sentences of explanation: aging
process, genetics, sun protection, lifestyle choices, skincare, weight fluctuations, and follow-up care. It ends
by discussing how results can vary, the potential need for secondary procedures, the importance of realistic
expectations, and the necessity of choosing a qualified and experienced surgeon.
An article on eyelid surgery results by the ASPS is much less detailed compared to the ChatGPT response. It
discusses how results can vary, will be long-lasting, can be affected by aging, and how sun protection can
help maintain the results. Follow-up care is the only other point discussed by ChatGPT that is addressed in
the ASPS article. None of the points are addressed in as much detail as in the ChatGPT response.
DISCUSSION
Overall, these results demonstrate that ChatGPT is capable of providing accurate, organized, and
grammatically correct responses to common patient questions. Across the three procedures, ChatGPT
provided a list of complications that was similarly comprehensive to the corresponding ASPS article. It
included additional details on the complications. There were also complications listed in every section, such
as anesthesia risks. Conversely, ChatGPT’s response on recovery periods was less detailed than the
corresponding ASPS articles except in regard to the assistance needed during the recovery period. However,
there were no articles on recovery periods for breast lift and eyelid surgery. The formats of the answers to
the repeated questions were the same, indicating reliability in answer structure. Some of the sections were
also identical or near identical across procedures, again indicating reliability, but also showing a lack of
specificity.
For the procedure-specific questions, ChatGPT was more detailed than the corresponding ASPS article 2/5
times and less detailed 1/5 times. In the remaining two instances, the ChatGPT and ASPS articles provided
dissimilar responses. ChatGPT’s response to the questions on tummy tucks and pregnancy did not
emphasize the importance of waiting until after childbearing to undergo a tummy tuck. This was the only
instance where ChatGPT’s answer missed the main point of the corresponding ASPS article. The
comprehensiveness of the overall data is represented in Figure 4. Though there does not seem to be any
literature directly comparing ChatGPT’s responses with those found on reputable websites, our results do
seem consistent with papers that found it to be a reliable and organized source of basic preoperative
information that does not provide patient-specific advice [12-14] . There was no evidence to suggest ChatGPT
may be able to outperform physicians in this area, as some articles claim. This was not directly tested.
This study demonstrates that ChatGPT is a reliable source of preoperative information most of the time. It
may not be specific or detailed enough for patients to get all the information they need prior to a procedure.
ChatGPT is able to generate responses for questions that may not have reputable answers on sites like the
ASPS, making it a good source of information in those cases. This supports past literature indicating that