阿尔茨海默病(Alzheimer’s disease，AD)是发生于老年期或老年前期的中枢神经系统退行性病变，以进行性认知功能障碍为特征。随着社会老龄化加剧，AD已成为全球公共卫生问题，亟需研发更敏感、便捷和经济的筛查技术进行早期防控。眼球运动与认知功能密切相关，且眼球运动检查有非侵入性、成本低、检查时间短等优点。研究眼球运动异常和认知功能障碍之间的相关性，有助于研发更简便易操作的认知功能障碍筛查工具。随着人工智能技术的发展，机器学习算法强大的特征提取和计算能力对处理眼球运动检查结果有显著优势。本文对既往AD患者与眼球运动异常之间的相关性研究进行综述，并对机器学习算法模型辅助下，基于眼球运动异常模式进行认知功能障碍早期筛查技术开发的研究前景予以展望。

Alzheimer’s disease (AD) is a degenerative disease of the central nervous system that occurs in old age or early old age. It is characterized by progressive cognitive dysfunction. With the world population aging, AD has become a global public health problem. The development of a more sensitive, convenient, and economic screening technology for AD is urgently needed. The eye movement function is closely related to cognitive function. Moreover, eye movement examination has advantages including non-invasiveness, low cost, and short examination time. Researches on the correlation between abnormal eye movement and cognitive dysfunction can help to develop a simple and easy-to-use screening tool for cognitive dysfunction. With the development of artificial intelligence technology, the dominant feature extraction and computing capabilities of machine learning algorithms have a significant advantage in processing eye movement inspection results. This article reviews the correlation between AD and eye movement abnormalities aiming to provide the research prospects of early screening technology development for cognitive dysfunction based on abnormal eye movement with the application of machine learning models.

目的：调查新疆喀什地区英吉沙县芒辛镇60岁及以上老年人群眼底疾病患病率及其分布特征，分析该地区眼底疾病流行病学现状，为西部高海拔地区眼底疾病防控策略制定和基层眼健康服务体系建设提供科学依据和数据支撑。方法：采用横断面研究设计，于2024年5—6月对芒辛镇60岁及以上常住人口进行调查。纳入标准为年龄≥60岁、在当地连续居住≥6个月、自愿参与并签署知情同意书者。=采用标准化眼科检查包括视力测定、眼压、裂隙灯显微镜检查、眼底照相等，同时进行结构化问卷调查收集基本信息、生命体征测量和实验室检查。眼底疾病诊断严格按照国内外相关诊断标准执行，采用SPSS24.0软件进行统计分析，计算各类眼底疾病患病率及其95%置信区间。结果：共调查1 310名老年人，响应率为76.76%。研究对象中男性669人（51.1%），女性641人（48.9%），平均年龄68.4±6.6岁。眼底疾病总患病率为16.1%（95% CI：14.2~18.0）。各类眼底疾病患病率依次为：年龄相关性黄斑变性5.9%（77例），视神经萎缩2.8%（36例），黄斑前膜2.3%（30例），糖尿病性视网膜病变1.8%（23例），其他黄斑病变1.07%（14例）、高血压性视网膜病变0.99%（13例）。其他眼底疾病包括高度近视眼底改变、视网膜色素变性、黄斑裂孔、血管炎、视网膜出血等，患病率均低于0.38%。在糖尿病患者中，糖尿病性视网膜病变患病率为20.8%，与国内外相关研究结果基本一致。结论：新疆芒辛镇老年人群眼底疾病患病率较高，年龄相关性黄斑变性是最主要的眼底疾病类型。研究结果填补了西部高海拔地区眼底疾病流行病学数据空白，提示应建立针对性的分层筛查和防控体系，重点关注老年人的眼底健康管理，推广便携式眼底照相结合远程医疗的筛查模式，提升基层眼健康服务的可及性与质量。

Objective: To investigate the prevalence and distribution characteristics of fundus diseases among the elderly population aged 60 and above in Mangxin Town, Yengisar County, Kashgar Prefecture, Xinjiang, and to analyze the epidemiological status of fundus diseases in this region, thereby providing a scientific basis and data support for the development of fundus disease prevention and control strategies and the construction of a primary eye health service system in high-altitude areas of Western China. Methods: A cross-sectional study was conducted from May to June 2024 among the permanent residents aged 60 and above in Mangxin Town. Inclusion criteria were age ≥ 60 years, local residence for ≥ 6 months, and voluntary participation with signed informed consent. Data were collected through standardized ophthalmological examinations (including visual acuity testing, intraocular pressure measurement, slit-lamp microscopy, and fundus photography), structured questionnaire surveys, vital sign measurements, and laboratory tests. Diagnoses of fundus diseases were strictly based on domestic and international diagnostic criteria. Statistical analysis was performed using SPSS 24.0 to calculate the prevalence rates of various fundus diseases and their 95% confidence intervals. Results: A total of 1,310 elderly individuals were included, with a response rate of 76.76%. Among them, 669 (51.1%) were male and 641 (48.9%) were female, with a mean age of 68.4 ± 6.6 years. The overall prevalence of fundus diseases was 16.1% (95% CI: 14.2–18.0). The prevalence rates of specific fundus diseases were as follows: age-related macular degeneration, 5.9% (77 cases); optic atrophy, 2.8% (36 cases); epiretinal membrane, 2.3% (30 cases); diabetic retinopathy, 1.8% (23 cases); other macular diseases, 1.07% (14 cases); and hypertensive retinopathy, 0.99% (13 cases). Other fundus diseases, including high myopia-related fundus changes, retinitis pigmentosa, macular hole, vasculitis, and retinal hemorrhage, each had a prevalence of less than 0.38%. Among diabetic patients, the prevalence of diabetic retinopathy was 20.8%, which is consistent with previous domestic and international studies. Conclusions: The prevalence of fundus diseases among the elderly in Mangxin Town, Xinjiang, is relatively high, with age-related macular degeneration being the most common type. This study fills a gap in the epidemiological data on fundus diseases in high-altitude regions of Western China. The findings highlight the need to establish a targeted stratified screening and prevention system, strengthen fundus health management in the elderly, and promote a screening model combining portable fundus photography with telemedicine to improve the accessibility and quality of primary eye health services.

手术前常规检查在临床诊疗中被广泛应用，但在一些低风险择期手术前对患者进行常规检查，对提高医疗质量并无帮助，反而降低了医疗效率，增加了医疗费用。为提高效率，一些地区、机构和专家学者陆续通过宣传教育、发表共识、制定指南等方式控制无指征术前常规检查，但效果仍依赖于执业者的重视程度和专业水平。大数据机器学习方法以其标准化、自动化的特点为解决这一问题提供了新的思路。在回顾已有研究的基础上，我们抽取2017至2019年在中山大学中山眼科中心进行眼科手术的3.4万名患者的病史和体格检查资料大数据，涵盖年龄、性别等口学信息，诊断、既往疾病等病史信息，视功能、入院时身体质量指数(BMI)等体格检查信息。并以此为基础使用机器学习方法预测术前胸部X线检查是否存在异常，受试者操作特性曲线(receiver operating characteristic curve，ROC)曲线下面积达到0.864，预测准确率可达到81.2%，对大数据机器学习精简术前常规检查的新方式进行了先期探索。

Preoperative routine tests are widely prescribed in clinical settings. However, these tests do not help improving the quality of medical care in low-risk elective surgery. Instead, they are associated with lower efficiency and increasing fees. To improve the efficiency, many regions, institutions, and scholars have attempted to reduce preoperative routine tests without indications through propaganda, education, consensus, and guidelines. Nevertheless, the effects are still highly dependent on the expertise and emphasis of practitioners. Machine learning based on big data provide a new solution with its standardization and automation. Through literature review, we extracted the big data, including demographic features such as sex and age, histories including diagnosis and chronic diseases, and physical examination features such as visual function and body mass index. A total of 34 000 patients undergone ocular surgeries in Zhongshan Ophthalmic Center, Sun Yat-sen university from 2017 to 2019. Machine learning was adopted to predict the risk of finding abnormalities in chest X-ray examination, with an accuracy of 81.2%. Area under the Receiver Operating Characteristic curve was 0.864. The study could be an early exploration into the field of simplifying preoperative tests by machine learning.