[关键词]
[摘要]
干眼(dry eye， DE)是世界范围内最常见的眼科疾病之一，患病率在5%～50%。由于病因复杂且诊断的相应设备有限，干眼尚不能得到及时、精准的诊断。近年来，随着人工智能(artificial intelligence，AI)在医学领域的广泛应用，利用机器学习和深度学习辅助检查干眼也得到了深入研究，如干涉测量、裂隙灯检查和睑板腺图像的分类和评估等。研究发现人工智能能够对干眼患者的测量数据和图像进行准确分析，灵敏度和特异度均可达90%以上。人工智能将在辅助临床医生客观诊断干眼、改善干眼患者生活质量方面具有巨大潜力。在这篇综述中，我们总结了人工智能在干眼领域的应用现状以及应用中潜在的挑战，展望了人工智能辅助诊断干眼的前景。
[Key word]
[Abstract]
Dry eye(DE)is one of the most common eye diseases worldwide, with prevalence ranging from 5% to 50%. DE cannot be diagnosed timely and accurately due to its complex etiology and the limitations of testing equipment. In recent years, with the widespread use of artificial intelligence(AI)in the medical field, the application of machine learning and deep learning in the detection of dry eye has been deeply studied, such as interferometry, slit lamp examination and the classification and evaluation of meibomian gland images. Studies have found that the AI models can accurately analyze the measured data and images of patients with dry eye and with sensitivity and specificity of more than 90%. AI has great potential to assist clinicians in the objective diagnosis of dry eye and improve the quality of life of patients with dry eye. In this review, we summarized the current status of AI in dry eye, the potential challenges in clinical application, and look forward to the prospect of AI-assisted diagnosis of dry eye.
[中图分类号]
[基金项目]
南京市医学科技发展一般性课题(No.YKK17273)
