Alabdalhussein Ali, Al-Khafaji Mohammed Hasan, Al-Busairi Rusul, Al-Dabbagh Shahad, Khan Waleed, Anwar Fahid, Raheem Taghreed Sami, Elkrim Mohammed, Sahota Raguwinder Bindy, Mair Manish
Department of Otolaryngology, University Hospitals of Leicester, Leicester LE1 5WW, UK.
Independent Researcher, Leicester LE2 2AD, UK.
Curr Oncol. 2025 Jun 9;32(6):338. doi: 10.3390/curroncol32060338.
(1) Background: The early detection of laryngeal cancer is crucial for achieving superior patient outcomes and preserving laryngeal function. Artificial intelligence (AI) methodologies can expedite the triage of suspicious laryngeal lesions, thereby diminishing the critical timeframe required for clinical intervention. (2) Methods: We included all studies published up to February 2025. We conducted a systematic search across five major databases: MEDLINE, EMCARE, EMBASE, PubMed, and the Cochrane Library. We included 15 studies, with a total of 17,559 patients. A risk of bias assessment was performed using the QUADAS-2 tool. We conducted data synthesis using the Meta Disc 1.4 program. (3) Results: A meta-analysis revealed that AI demonstrated high sensitivity (78%) and specificity (86%), with a Pooled Diagnostic Odds Ratio of 53.77 (95% CI: 27.38 to 105.62) in detecting laryngeal cancer. The subset analysis revealed that CNN-based AI models are superior to non-CNN-based models in image analysis and lesion detection. (4) Conclusions: AI can be used in real-world settings due to its diagnostic accuracy, high sensitivity, and specificity.
（1）背景：喉癌的早期检测对于实现更好的患者预后和保留喉功能至关重要。人工智能（AI）方法可以加快可疑喉部病变的分诊，从而缩短临床干预所需的关键时间框架。（2）方法：我们纳入了截至2025年2月发表的所有研究。我们在五个主要数据库中进行了系统检索：MEDLINE、EMCARE、EMBASE、PubMed和Cochrane图书馆。我们纳入了15项研究，共17559名患者。使用QUADAS - 2工具进行偏倚风险评估。我们使用Meta Disc 1.4程序进行数据合成。（3）结果：一项荟萃分析显示，AI在检测喉癌方面表现出高敏感性（78%）和特异性（86%），合并诊断比值比为53.77（95%CI：27.38至105.62）。亚组分析显示，基于卷积神经网络（CNN）的AI模型在图像分析和病变检测方面优于非基于CNN的模型。（4）结论：由于其诊断准确性、高敏感性和特异性，AI可用于实际临床环境。
