近年来随着医疗领域数字化、信息化建设的加速推进，人工智能的应用越来越广泛，在眼科医学方面尤为突出。婴幼儿处于视觉系统发育的关键时期，此时发生的眼病往往会造成不可逆的视功能损伤，带来沉重的家庭和社会负担。然而，由于婴幼儿群体的特殊性以及小儿眼科医生的短缺，开展大规模小儿眼病筛查工作十分困难。最新研究表明：人工智能在先天性白内障、先天性青光眼、斜视、早产儿视网膜病变以及视功能评估等领域已经得到相关应用，在多种婴幼儿眼病的早期筛查、诊断分期、治疗建议等方面都有令人瞩目的表现，有效解决了许多临床难点与痛点。但目前婴幼儿眼科人工智能仍然不如成年人眼科发展充分，亟须进一步的探索和研发。

In recent years, with the acceleration of digitalization and informatization in medical field, artificial intelligence (AI) is more and more widely applied, especially in ophthalmology. Infants are in the critical period of visual development, during which eye diseases can lead to irreversible visual impairment and bring heavy burden to family and society. Due to the particularity of infants and the shortage of pediatric ophthalmologists, it is challenging to carry out large-scale screening for eye diseases of infants. According to the latest studies, AI has been studied and applied in the fields of congenital cataract, congenital glaucoma, strabismus, amblyopia, retinopathy of prematurity, and evaluation of visual function, and it has achieved remarkable performance in the early screening, diagnosis stage and treatment suggestions, solving many clinical difficulties and pain points effectively. However, AI for infantile ophthalmology is not as developed as for adult ophthalmology, so it needs further exploration and development.

青光眼是一组以视盘萎缩凹陷、视野缺损以及视力下降为共同特征的视神经退行性疾病，也是世界首位不可逆性致盲眼病，导致患者生活质量降低、引起极大卫生经济负担。但其发病机制尚不明确，促进房水排出从而降低眼内压仍是目前减缓疾病进展的唯一治疗手段。房水排出的主要途径是经由小梁网进入Schlemm's管最后汇入巩膜外静脉，因此小梁网在调节房水排出以及平衡眼内压方面发挥重要作用。近年来，体内以及体外房水排出测量技术和小梁网成像技术不断突破，众多研究表明小梁网存在压力依赖的节律性搏动，在房水的脉冲式排出中起到关键作用，但在青光眼中这种搏动随疾病的进展减弱甚至消失。文章以小梁网的泵理论为核心，总结青光眼中房水排出的最新研究进展，并从恢复小梁网功能的角度出发探索可能有效的治疗策略，为青光眼的临床诊治提供新的思路。

Glaucoma, a group of optic nerve degenerative diseases, is characterized by papillary atrophy, visual field defects, and decreased vision. It is also the leading cause of irreversible blindness worldwide, significantly reducing patients’ the quality of life of patients and posing considerable health economic burdens. However, the pathogenesis of glaucoma remains unclear, and promoting aqueous humor outflow to reduce intraocular pressure is the only treatment option available to slow disease progression. The main pathway for aqueous humor outflow is through the trabecular meshwork into Schlemm's canal and finally into the episcleral veins, highlighting the crucial role of the trabecular meshwork in regulating aqueous humor outflow and maintaining intraocular pressure balance. In recent years, there have been notable breakthroughs in in vivo and in vitro aqueous humor outflow measurement techniques and trabecular meshwork imaging technologies.Many studies suggest that the trabecular meshwork exhibits pressure-dependent rhythmic pulsation, playing a crucial role in the pulse-like outflow of aqueous humor. Unfortunately, in glaucoma, this pulsation weakens or even disappears as the disease progresses. This article focuses on the trabecular meshwork's pump theory and summarizes the latest research progress in aqueous humor outflow in glaucoma, exploring potential effective therapeutic strategies aimed at restoring trabecular meshwork function. This provides new insights for the clinical diagnosis and treatment of glaucoma.

目的：比较单眼发作的原发性急性房角关闭(acute primary angle closure，APAC)患者发作眼与未发作眼眼部生物学参数的差异，分析急性房角关闭发作的可能危险因素。方法：回顾性分析2008年1月至2020年3月中山眼科中心青光眼科222例45岁以上单眼发作的APAC病例。排除双眼发作、另眼有发作史及晶状体源性、外伤性等继发因素。A超测量晶状体厚度、眼轴长度，超生生物显微镜测前房深度。对单眼发作APAC患者的发作眼与未发作眼眼轴长度、前房深度、晶状体厚度、晶状体相对位置等进行统计学分析。结果：患者发作年龄为(62.57±9.14)岁。发作眼与未发作眼前房深度分别为(1.75±0.27) mm和(1.88±0.31) mm，眼轴长度分别为(22.34±0.80) mm和(22.35±0.83) mm，晶状体厚度分别为(5.14±0.38) mm和(5.17±0.42) mm，晶状体相对位置分别为0.195和0.198。发作眼前房深度较浅，晶状体相对位置较靠前，差异有统计学意义(均P<0.001)，发作眼的眼轴长度、晶状体厚度较未发作眼差异无统计学意义(P>0.05)。APAC发作年龄较小(45~59岁)的患者双眼眼轴均短于发作年龄较大(60~69、70岁以上)的患者；发作年龄70岁以上患者双眼前房深度均较浅，双眼晶状体相对位置均较靠前，差异均有统计学意义(P<0.05)。相关性分析表明APAC发作年龄较小的患者双眼眼轴均较短(P<0.001)。结论：APAC发作眼的前房较浅、晶状体相对位置靠前。短眼轴、女性与不同个体的APAC发作相关。浅前房、晶状体厚、晶状体相对位置靠前可能是高龄人群APAC发作的危险因素。

Objective: To compare the ocular biometric parameters between the acute primary angle closure (APAC) eyes and the fellow eyes as well as the risk factors associated with APAC. Methods: From January 2008 to March 2020,222 monocular APAC patients over 45 years old from the Glaucoma Department of Zhongshan Ophthalmic Center, Sun Yat-sen University were retrospectively studied. Patients with binocular attack, previous attack in the fellow eyes, and secondary factors such as lens-induced and traumatic glaucoma were excluded. Ocular biometric parameters including axial length (AL) and lens thickness (LT) were measured with A-scan ultrasound, while the anterior chamber depth (ACD) was measured by ultrasonic biological microscope. AL, ACD, LT and relative lens position (RLP) were compared between the APAC and the fellows eyes. Results: The average age of onset was (62.57±9.14) years. The ACD was (1.75±0.27) and (1.88±0.31) mm, AL was (22.34±0.80) and (22.35±0.83) mm,LT was (5.14±0.38) and (5.17±0.42) mm, and the RLP was 0.195 and 0.198 for the APAC and the fellow eyes,respectively. Compared with the fellow eyes, the ACD of the APAC eyes was shallower, and the RLP was more anterior (both P<0.001), while the differences of AL and LT were not statistically significant (both P>0.05).Furthermore, AL of patients with a younger age of onset (aged 45 to 59 years) was shorter than that of those with an older age of onset (aged 60 to 69 or over 70 years); patients with an onset age of over 70 years have shallower ACD and more anterior RLP, all statistically significant (P<0.05). In addition, correlation analysis indicated that younger onset age was significantly correlated to shorter axial length of APAC eyes (P<0.001). Conclusion:APAC eyes had shallower ACD and more anterior RLP. Shorter AL and female were associated with APAC attack between individuals. Shallower ACD, thicker lens and more anterior RLP are potential risk factors for APAC among aged population.

目的：分析医学人工智能通识课程“眼科人工智能的研发与应用”的开展效果，为相关医学人工智能通识课程的开展提供参考和借鉴。方法：纵向观察性研究。观察分析2020年秋季学期眼科人工智能的研发与应用通识课程学生人群，课程考核结果以及学生对课程的整体评价。结果：共有118名本科生同学参与了课程学习。其中大部分为低年级临床医学专业本科生。期中考核得分为77.21±10.07，有56位同学(47.46%)达到80分以上。期末考核得分为82.24±6.77，有91位同学(77.12%)达到80分以上。同学对课程的评分为98.76±3.55，超过90%的同学表示课程备课认真、授课条理清晰、表达准确。结论：本课程的顺利进展证明医学人工智能联合教学模式的可行性，理论和实践穿插的教学设置帮助同学们更好地掌握知识技术，完成教学目标。

Objective: To analyze the effectiveness of medical education curriculum named “Development and Application of Ophthalmic Artificial Intelligence”, and provide reference for the development of other related curriculums. Methods: Longitudinal observational study method was adopted. During the fall semester of 2020, we conducted an education curriculum named “Development and Application of Ophthalmic Artificial Intelligence” and analyzed the results of mid-term and final examinations, and curriculum evaluation of students. Results: There were 118 undergraduate students taking the course and most of them were junior students majoring in clinical medicine. The score of the mid-term examination was in the range of 77.2±10.07, and 56 students (47.46%) got more than 80 points. The score of the final examination was in the range of 82.24±6.77, and 91 students (77.12%) got more than 80 points. The score of course evaluation of students was in the range of 98.76±3.55, and more than 90% of the students thought that teachers have made full preparations before class, together with clear teaching logic and accurate expressions in class. Conclusion: The smooth progress of our course proved the feasibility of medical artificial intelligence teaching. The teaching setting interspersed with theory and practice could help students to master knowledge and technology better, so as to achieve the teaching objectives.