文献速递咽喉与嗓音头颈外科

喉镜图像人工智能诊断分类模型的多中心临床验证

Multicenter Clinical Validation of an Artificial Intelligence Diagnostic Classification Model for Laryngoscopy Images.
PubMed 文献 · Otolaryngol Head Neck Surg · 2026-02-16

本研究开发并外部验证了一种基于人工智能的计算机辅助诊断(CADx)模型,用于将喉镜图像中的喉部病变分类为高风险(HR)和低风险(LR)。研究回顾性收集了来自意大利、印度、中国、希腊和西班牙的多中心超过20000张图像,训练深度学习模型并在两个外部数据集上评估。模型在内外部数据集上区分HR与LR病变的准确率/AUC分别为0.90/0.89(内部)、0.85/0.85(希腊)和0.88/0.88(西班牙),性能与耳鼻咽喉科医生和喉科专家非劣效,优于全科医生和ChatGPT-4o。

要点

  • CADx模型在外部数据集上区分喉部高风险与低风险病变的准确率/AUC为0.85/0.85(希腊)和0.88/0.88(西班牙)。
  • 模型性能与耳鼻咽喉科医生和喉科专家非劣效,且优于全科医生和ChatGPT-4o。
  • 该模型有望辅助诊断,尤其在资源有限环境中,但需前瞻性临床试验评估实际应用。

核心结论

  • CADx模型在区分喉部低风险与高风险病变方面表现出泛化性,性能与临床医生相当。

研究设计与样本

  • 回顾性多中心研究,开发并外部验证基于深度学习的CADx模型,使用超过20000张喉镜图像,图像标注基于组织病理学或专家共识。

主要发现

  • 模型区分HR与LR病变的准确率/AUC为0.90/0.89(内部数据集)、0.85/0.85(希腊数据集)、0.88/0.88(西班牙数据集)。
  • 模型准确率与耳鼻咽喉科医生和喉科专家相比非劣效,优于全科医生和ChatGPT-4o。

临床怎么用

  • 该模型可能辅助喉部病变的诊断分类,尤其在资源有限环境中,但需前瞻性多中心临床试验评估实际临床实施。

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 develop and externally validate a computer-aided diagnosis (CADx) model using artificial intelligence (AI) for classifying laryngeal lesions from laryngoscopy images into high-risk (HR), low-risk (LR). STUDY DESIGN: Retrospective multicenter development of a CADx model and external validation on independent cohorts. SETTING: Multicenter tertiary referral hospitals (Italy, India, China, Greece, and Spain). METHODS: Over 20,000 images derived from laryngoscopic examinations were retrieved. Images were annotated based on histopathology or expert consensus. A deep learning model was trained using an internal dataset and evaluated on 2 external datasets to assess generalizability. The CADx model classifies only images containing visible lesions, discriminating between LR and HR categories. Diagnostic performance was measured using standard metrics, including accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC). Model performance was compared with physicians of varying expertise and ChatGPT-4o. RESULTS: The computer-aided diagnosis model achieved a similar performance across internal and external datasets in distinguishing HR from LR lesions, with accuracy/AUC of 0.90/0.89 internally, 0.85/0.85 on the Greek dataset, and 0.88/0.88 on the Spanish dataset. The model's accuracy was statistically noninferior to that of otolaryngologists and expert laryngologists, and superior to general practitioners and ChatGPT-4o. CONCLUSION: This is a large multicenter clinical validation of a CADx model for laryngeal endoscopy, demonstrating generalizability and performance comparable to clinicians in discriminating between LR and HR lesions. The model's success supports its potential role in augmenting diagnostic capabilities, especially in resource-limited settings. A prospective multicenter clinical trial is underway to assess real-world clinical implementation.

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

引用

  1. Sampieri C, Mora F, Peretti G, et al. Multicenter Clinical Validation of an Artificial Intelligence Diagnostic Classification Model for Laryngoscopy Images. Otolaryngol Head Neck Surg. 2026. PMID: 41696998. doi:10.1002/ohn.70153

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。