Schwarzkopf Sophie-Caroline, Bereuter Jean-Paul, Geissler Mark Enrik, Weitz Jürgen, Distler Marius, Kolbinger Fiona R
Department of Visceral, Thoracic and Vascular Surgery, University Hospital and Faculty of Medicine Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany.
Department of Obstetrics and Gynecology, University Hospital and Faculty of Medicine Carl Gustav Carus, TUD Dresden University of Technology, Dresden, Germany.
PLOS Digit Health. 2025 Aug 1;4(8):e0000933. doi: 10.1371/journal.pdig.0000933. eCollection 2025 Aug.
Managing postoperative complications is an essential part of surgical care and largely depends on the medical team's experience. Large Language Models (LLMs) have demonstrated immense potential in supporting medical professionals. To evaluate the potential of LLMs in surgical patient care, we compared the performance of three state-of-the-art LLMs in managing postoperative complications to that of a panel of medical professionals based on six postsurgical patient cases. Six realistic postoperative patient cases were queried using GPT-3, GPT-4, and Gemini-Advanced and presented to human surgical caregivers. Humans and LLMs provided a triage assessment, an initial suspected diagnosis, and an acute management plan, including initial diagnostic and therapeutic measures. Responses were compared based on medical contextual correctness, coherence, and completeness. In comparison to human caregivers, GPT-3 and GPT-4 possess considerable competencies in correctly identifying postoperative complications (humans: 76.3% vs. GPT-3: 75.0% vs. GPT-4: 96.7%, p = 0.47) as well as triaging patients accordingly (humans: 84.8% vs. GPT-3: 50% vs. GPT-4: 38.3%, p = 0.19). With regard to diagnostic and therapeutic management of postoperative complications, GPT-3 and GPT-4 provided comprehensive management plans. Gemini-Advanced often provided no diagnostic or therapeutic recommendations and censored its outputs. In summary, LLMs can accurately interpret postoperative care scenarios and provide comprehensive management recommendations. These results showcase the improvements in LLMs performance with regard to postoperative surgical use cases and provide evidence for their potential value to support and augment surgical routine care.
处理术后并发症是外科护理的重要组成部分，很大程度上取决于医疗团队的经验。大语言模型（LLMs）在支持医疗专业人员方面已展现出巨大潜力。为评估大语言模型在外科患者护理中的潜力，我们基于六个术后患者病例，将三种最先进的大语言模型在处理术后并发症方面的表现与一组医疗专业人员的表现进行了比较。使用GPT-3、GPT-4和Gemini-Advanced查询了六个真实的术后患者病例，并将其呈现给人类外科护理人员。人类和大语言模型提供了分诊评估、初步疑似诊断和急性管理计划，包括初始诊断和治疗措施。根据医学背景的正确性、连贯性和完整性对回答进行了比较。与人类护理人员相比，GPT-3和GPT-4在正确识别术后并发症方面具有相当的能力（人类：76.3%，GPT-3：75.0%，GPT-4：96.7%，p = 0.47），并能据此对患者进行分诊（人类：84.8%，GPT-3：50%，GPT-4：38.3%，p = 0.19）。在术后并发症的诊断和治疗管理方面，GPT-3和GPT-4提供了全面的管理计划。Gemini-Advanced通常不提供诊断或治疗建议，并对其输出进行审查。总之，大语言模型可以准确解读术后护理场景并提供全面的管理建议。这些结果展示了大语言模型在术后外科用例方面的性能提升，并为其支持和增强外科常规护理的潜在价值提供了证据。
