文献速递咽喉与嗓音

ChatGPT-4在解读喉部常见病变临床图像中的一致性

ChatGPT-4 Consistency in Interpreting Laryngeal Clinical Images of Common Lesions and Disorders.
PubMed 文献 · Otolaryngol Head Neck Surg · 2024-07-24

这项前瞻性多中心非对照研究将40例患者的病史和动态喉镜图像提交给ChatGPT-4进行鉴别诊断与治疗建议,并由3名盲法喉科医生用人工智能性能工具评估。ChatGPT-4图像解读一致性均值为2.46±1.42,仅6例(15%)被完美分析,原发诊断正确率为20.0%至25.0%。结论认为ChatGPT-4在原发诊断上比在图像分析、选择最合适额外检查和治疗上更有效。

要点

  • ChatGPT-4图像解读一致性均值2.46±1.42,仅6例(15%)完美分析。
  • ChatGPT-4原发诊断正确率为20.0%至25.0%,与评估者一致性高者5例(12.5%)。
  • ChatGPT-4与执业者分别提出153和63项额外检查(P = .001)。

核心结论

  • ChatGPT-4在原发诊断方面比在图像分析、选择最合适额外检查和治疗方面更有效。

研究设计与样本

  • 前瞻性非对照研究,多中心设计,纳入40例患者,平均复杂度评分2.60±1.15。
  • 将患者病史和临床动态喉镜图像提交给ChatGPT-4进行鉴别诊断、管理和治疗。
  • 由3名盲法喉科医生使用人工智能性能工具(AIPI)评估ChatGPT-4的回答,并用5点李克特量表评估病例复杂度和执业者与ChatGPT-4之间图像解读的一致性。

主要发现

  • ChatGPT-4图像解读平均一致性评分为2.46±1.42。
  • ChatGPT-4在6例(15%;5/5)中完美分析临床图像,与评估者一致性高者5例(12.5%;4/5)。
  • 评估者一致性评分组内相关系数(ICC)为0.965(P = .001)。
  • ChatGPT-4错误记录声带不规则(肿块或病变)21例(52.5%)、声门关闭不全2例(0.05%)、声带麻痹5例(12.5%)。
  • ChatGPT-4和执业者分别提出153项和63项额外检查(P = .001);ChatGPT-4原发诊断正确率为20.0%至25.0%;临床图像一致性评分与AIPI评分显著相关(rs = 0.830;P = .001)。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

OBJECTIVE: To investigate the consistency of Chatbot Generative Pretrained Transformer (ChatGPT)-4 in the analysis of clinical pictures of common laryngological conditions. STUDY DESIGN: Prospective uncontrolled study. SETTING: Multicenter study. METHODS: Patient history and clinical videolaryngostroboscopic images were presented to ChatGPT-4 for differential diagnoses, management, and treatment(s). ChatGPT-4 responses were assessed by 3 blinded laryngologists with the artificial intelligence performance instrument (AIPI). The complexity of cases and the consistency between practitioners and ChatGPT-4 for interpreting clinical images were evaluated with a 5-point Likert Scale. The intraclass correlation coefficient (ICC) was used to measure the strength of interrater agreement. RESULTS: Forty patients with a mean complexity score of 2.60 ± 1.15. were included. The mean consistency score for ChatGPT-4 image interpretation was 2.46 ± 1.42. ChatGPT-4 perfectly analyzed the clinical images in 6 cases (15%; 5/5), while the consistency between GPT-4 and judges was high in 5 cases (12.5%; 4/5). Judges reported an ICC of 0.965 for the consistency score (P = .001). ChatGPT-4 erroneously documented vocal fold irregularity (mass or lesion), glottic insufficiency, and vocal cord paralysis in 21 (52.5%), 2 (0.05%), and 5 (12.5%) cases, respectively. ChatGPT-4 and practitioners indicated 153 and 63 additional examinations, respectively (P = .001). The ChatGPT-4 primary diagnosis was correct in 20.0% to 25.0% of cases. The clinical image consistency score was significantly associated with the AIPI score (rs = 0.830; P = .001). CONCLUSION: The ChatGPT-4 is more efficient in primary diagnosis, rather than in the image analysis, selecting the most adequate additional examinations and treatments.

来源:Otolaryngol Head Neck Surg,查看原文。版权归原作者所有。

引用

  1. Maniaci A, Chiesa-Estomba CM, Lechien JR, et al. ChatGPT-4 Consistency in Interpreting Laryngeal Clinical Images of Common Lesions and Disorders. Otolaryngol Head Neck Surg. 2024. PMID: 39045737. doi:10.1002/ohn.897

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。