RESUMO
OBJECTIVE: This study sought to explore the unexamined capabilities of ChatGPT in describing the surgical steps of a specialized operation, the Fisher cleft lip repair. DESIGN: A chat log within ChatGPT was created to generate the procedural steps of a cleft lip repair utilizing the Fisher technique. A board certified craniomaxillofacial (CMF) surgeon then wrote the Fisher repair in his own words blinded to the ChatGPT response. Using both responses, a voluntary survey questionnaire was distributed to residents of plastic and reconstructive surgery (PRS), general surgery (GS), internal medicine (IM), and medical students at our institution in a blinded study. SETTING: Authors collected information from residents (PRS, GS, IM) and medical students at one institution. MAIN OUTCOME MEASURES: Primary outcome measures included understanding, preference, and author identification of the procedural prompts. RESULTS: Results show PRS residents were able to detect more inaccuracies of the ChatGPT response as well as prefer the CMF surgeon's prompt in performing the surgery. Residents with less expertise in the procedure not only failed to detect who wrote what procedure, but preferred the ChatGPT response in explaining the concept and chose it to perform the surgery. CONCLUSIONS: In applications to surgical education, ChatGPT was found to be effective in generating easy to understand procedural steps that can be followed by medical personnel of all specialties. However, it does not have expert capabilities to provide the minute detail of measurements and specific anatomy required to perform medical procedures.
RESUMO
Background: Palatal fistulas are the most common postoperative complications in primary cleft palate surgery, with incidence rates ranging from 10% to 30%. Functional indications for repair include food regurgitating from the nose, food impaction resulting in malodor, and hypernasality with speech. Anterior palatal fistulas (APFs), in particular, present difficult reconstructive cases due to lack of available local tissue. Here, we describe a case series of 3 patients who underwent APF repair with a random pattern labial flap. Methods: The 3 patients included in this report underwent surgical repair of APF. The size of defects measured 2 × 1cm, 2.5 × 1.5cm, and 3 × 2cm. In each case, the labial flap was elevated on the free border of the superior lip mucosa and advanced through the alveolar cleft to cover the oral layer of the fistula. After 3 weeks, the proximal part of the pedicled flap was incised and inset to the alveolar ridge. Results: From 2020 through 2021, 2 lip flaps were successful in providing full coverage to the oral fistula. In one patient, a 3-year-old who did not cooperate with postoperative care, one of the flaps dehisced before division. Conclusions: APFs are common postoperative complications in patients with primary palate repairs and present difficult reconstructions due to lack of local tissue flaps. Here, we describe a 2-stage method in which a random pattern labial flap is used to provide oral fistula coverage. We recommend this procedure when multiple prior traditional attempts at closure have been unsuccessful and the patient can comply with postoperative care.
