Research Committee of Young Otolaryngologists of the International Federation of Otorhinolaryngological Socities (IFOS), Paris, France.
Division of Laryngology and Broncho-Esophagology, Department of Otolaryngology-Head Neck Surgery, UMONS Research Institute for Health Sciences and Technology, EpiCURA Hospital, University of Mons (UMons), Mons, Belgium.
Eur Arch Otorhinolaryngol. 2024 Jan;281(1):319-333. doi: 10.1007/s00405-023-08282-5. Epub 2023 Oct 24.
To study the performance of ChatGPT in the management of laryngology and head and neck (LHN) cases.
History and clinical examination of patients consulting at the Otolaryngology-Head and Neck Surgery department were presented to ChatGPT, which was interrogated for differential diagnosis, management, and treatment. The ChatGPT performance was assessed by two blinded board-certified otolaryngologists using the following items of a composite score and the Ottawa Clinic Assessment Tool: differential diagnosis; additional examination; and treatment options. The complexity of clinical cases was evaluated with the Amsterdam Clinical Challenge Scale test.
Forty clinical cases were submitted to ChatGPT, accounting for 14 (35%), 12 (30%), and 14 (35%) easy, moderate and difficult cases, respectively. ChatGPT indicated a significant higher number of additional examinations compared to practitioners (p = 0.001). There was a significant agreement between practitioners and ChatGPT for the indication of some common examinations (audiometry, ultrasonography, biopsy, gastrointestinal endoscopy or videofluoroscopy). ChatGPT never indicated some important additional examinations (PET-CT, voice quality assessment, or impedance-pH monitoring). ChatGPT reported highest performance in the proposition of the primary (90%) or the most plausible differential diagnoses (65%), and the therapeutic options (60-68%). The ChatGPT performance in the indication of additional examinations was lowest.
ChatGPT is a promising adjunctive tool in LHN practice, providing extensive documentation about disease-related additional examinations, differential diagnoses, and treatments. The ChatGPT is more efficient in diagnosis and treatment, rather than in the selection of the most adequate additional examination.
研究 ChatGPT 在喉科学和头颈部（LHN）病例管理中的性能。
将耳鼻喉头颈外科就诊患者的病史和临床检查结果提交给 ChatGPT，询问其鉴别诊断、管理和治疗方法。由两名经过认证的耳鼻喉科医生使用综合评分和渥太华诊所评估工具的以下项目评估 ChatGPT 的性能：鉴别诊断；其他检查；和治疗选择。使用阿姆斯特丹临床挑战量表测试评估临床病例的复杂性。
向 ChatGPT 提交了 40 个临床病例，分别为 14 个（35%）、12 个（30%）和 14 个（35%）简单、中等和困难病例。与医生相比，ChatGPT 指示进行了更多的额外检查（p=0.001）。医生和 ChatGPT 对一些常见检查（听力测试、超声检查、活检、胃肠内窥镜检查或荧光透视检查）的指示有显著的一致性。ChatGPT 从未指示进行一些重要的额外检查（PET-CT、语音质量评估或阻抗 pH 监测）。ChatGPT 在提出主要（90%）或最合理的鉴别诊断（65%）和治疗方案（60-68%）方面表现最好。ChatGPT 在指示额外检查方面的表现最低。
ChatGPT 是 LHN 实践中一种很有前途的辅助工具，它提供了与疾病相关的额外检查、鉴别诊断和治疗的广泛文档。ChatGPT 在诊断和治疗方面更有效，而不是在选择最合适的额外检查方面。
