关键词: Abdominoplasty Artificial intelligence ChatGPT ChatGPT-4 Chatbot

Mesh : Humans Abdominoplasty / methods Artificial Intelligence Referral and Consultation Female Patient Education as Topic / methods Surgery, Plastic / methods Surveys and Questionnaires

来  源:   DOI:10.1007/s00266-023-03660-0

Abstract:
BACKGROUND: With the increasing integration of artificial intelligence (AI) in health care, AI chatbots like ChatGPT-4 are being used to deliver health information.
OBJECTIVE: This study aimed to assess the capability of ChatGPT-4 in answering common questions related to abdominoplasty, evaluating its potential as an adjunctive tool in patient education and preoperative consultation.
METHODS: A variety of common questions about abdominoplasty were submitted to ChatGPT-4. These questions were sourced from a question list provided by the American Society of Plastic Surgery to ensure their relevance and comprehensiveness. An experienced plastic surgeon meticulously evaluated the responses generated by ChatGPT-4 in terms of informational depth, response articulation, and competency to determine the proficiency of the AI in providing patient-centered information.
RESULTS: The study showed that ChatGPT-4 can give clear answers, making it useful for answering common queries. However, it struggled with personalized advice and sometimes provided incorrect or outdated references. Overall, ChatGPT-4 can effectively share abdominoplasty information, which may help patients better understand the procedure. Despite these positive findings, the AI needs more refinement, especially in providing personalized and accurate information, to fully meet patient education needs in plastic surgery.
CONCLUSIONS: Although ChatGPT-4 shows promise as a resource for patient education, continuous improvements and rigorous checks are essential for its beneficial integration into healthcare settings. The study emphasizes the need for further research, particularly focused on improving the personalization and accuracy of AI responses.
METHODS: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .
摘要:
背景:随着人工智能(AI)在医疗保健中的日益融合,像ChatGPT-4这样的人工智能聊天机器人正被用来提供健康信息。
目的:本研究旨在评估ChatGPT-4在回答与腹部成形术相关的常见问题方面的能力,评估其作为患者教育和术前咨询辅助工具的潜力。
方法:对ChatGPT-4提交了关于腹部成形术的各种常见问题。这些问题来自美国整形外科学会提供的问题列表,以确保它们的相关性和全面性。一位经验丰富的整形外科医生仔细评估了ChatGPT-4在信息深度方面产生的反应,反应衔接,和能力,以确定人工智能在提供以患者为中心的信息方面的熟练程度。
结果:研究表明ChatGPT-4可以给出明确的答案,使其对回答常见的查询有用。然而,它挣扎着个性化的建议,有时提供不正确或过时的参考。总的来说,ChatGPT-4可以有效地共享腹部成形术信息,这可以帮助患者更好地理解手术。尽管有这些积极的发现,人工智能需要更多的改进,特别是在提供个性化和准确的信息方面,充分满足整形外科患者的教育需求。
结论:尽管ChatGPT-4有望成为患者教育的资源,持续的改进和严格的检查对于将其有利地融入医疗保健环境至关重要。研究强调需要进一步研究,特别侧重于提高人工智能响应的个性化和准确性。
方法:本期刊要求作者为每篇文章分配一定程度的证据。对于这些循证医学评级的完整描述,请参阅目录或在线作者说明www。springer.com/00266.
公众号