Boyd Carter J, Hemal Kshipra, Sorenson Thomas J, Patel Parth A, Bekisz Jonathan M, Choi Mihye, Karp Nolan S
From the Hansjörg Wyss Department of Plastic Surgery, NYU Langone, New York, N.Y.
Wellstar Medical College of Georgia, Augusta, Ga.
Plast Reconstr Surg Glob Open. 2024 Feb 2;12(2):e5580. doi: 10.1097/GOX.0000000000005580. eCollection 2024 Feb.
Given the dialogistic properties of ChatGPT, we hypothesized that this artificial intelligence (AI) function can be used as a self-service tool where clinical questions can be directly answered by AI. Our objective was to assess the content, accuracy, and accessibility of AI-generated content regarding common perioperative questions for reduction mammaplasty.
ChatGPT (OpenAI, February Version, San Francisco, Calif.) was used to query 20 common patient concerns that arise in the perioperative period of a reduction mammaplasty. Searches were performed in duplicate for both a general term and a specific clinical question. Query outputs were analyzed both objectively and subjectively. Descriptive statistics, tests, and chi-square tests were performed where appropriate with a predetermined level of significance of less than 0.05.
From a total of 40 AI-generated outputs, mean word length was 191.8 words. Readability was at the thirteenth grade level. Regarding content, of all query outputs, 97.5% were on the appropriate topic. Medical advice was deemed to be reasonable in 100% of cases. General queries more frequently reported overarching background information, whereas specific queries more frequently reported prescriptive information ( < 0.0001). AI outputs specifically recommended following surgeon provided postoperative instructions in 82.5% of instances.
Currently available AI tools, in their nascent form, can provide recommendations for common perioperative questions and concerns for reduction mammaplasty. With further calibration, AI interfaces may serve as a tool for fielding patient queries in the future; however, patients must always retain the ability to bypass technology and be able to contact their surgeon.
鉴于ChatGPT的对话特性，我们推测这种人工智能（AI）功能可作为一种自助工具，临床问题可由AI直接回答。我们的目的是评估关于缩乳术常见围手术期问题的AI生成内容的内容、准确性和可及性。
使用ChatGPT（OpenAI，2月版本，加利福尼亚州旧金山）查询缩乳术围手术期出现的20个常见患者关注点。对一般术语和特定临床问题均进行了重复搜索。对查询输出进行了客观和主观分析。在适当情况下进行描述性统计、检验和卡方检验，预定显著性水平小于0.05。
在总共40个AI生成的输出中，平均单词长度为191.8个单词。可读性处于十三年级水平。关于内容，在所有查询输出中，97.5%与适当主题相关。在100%的案例中，医疗建议被认为是合理的。一般查询更频繁地报告总体背景信息，而特定查询更频繁地报告规范性信息（P<0.0001）。在82.5%的情况下，AI输出特别建议遵循外科医生提供的术后指导。
目前可用的AI工具，以其初始形式，可以为缩乳术的常见围手术期问题和关注点提供建议。经过进一步校准，AI界面未来可能作为解答患者疑问的工具；然而，患者必须始终能够绕过技术并能够联系他们的外科医生。
