Deep learning (DL) methods utilize large numbers of images and annotating them is very labor-intensive. In contrast, in clinical practice such large numbers are not needed. Under the DL framework, how to integrate knowledge and data is unknown. We established an ensemble deep learning system (EDLS) that could integrate knowledge and data to automatically detect Glaucomatous Optic Neuropathy (GON), pathologic myopia and diabetic retinopathy using fundus images. An EDLS for the classification of GON was developed using 4225 fundus images obtained from Beijing Tongren Hospital. The generalization of the EDLS was tested on three testing datasets. Two EDLSs for the classification of pathologic myopia and diabetic retinopathy were developed and tested on two datasets obtained from websites respectively. For the classification of GON, the area under the receiver operating characteristic curve (AUC) of EDLS was 0.998 (95

Purpose:This study aimed to propose a new deep learning (DL) approach to automatically predict the retinal nerve fiber layer thickness (RNFLT) around optic disc regions in fundus photography trained by optical coherence tomography (OCT) and diagnose glaucoma based on the predicted comprehensive information about RNFLT. Methods:A total of 1403 pairs of fundus photographs and OCT RNFLT scans from 1403 eyes of 1196 participants were included. A residual deep neural network was trained to predict the RNFLT for each local image in a fundus photograph, and then a RNFLT report was generated based on the local images. Two indicators were designed based on the generated report. The support vector machines (SVM) algorithm was used to diagnose glaucoma based on the two indicators. Results:A strong correlation was found between the predicted and actual RNFLT values on local images. On three testing datasets, we found the Pearson r to be 0.893, 0.850, and 0.831, respectively, and the mean absolute error of the prediction to be 14.345, 17.780, and 19.250 μm, respectively. The area under the receiver operating characteristic curves for discriminating glaucomatous from healthy eyes was 0.860 (95 % confidence interval, 0.799-0.921). Conclusions:We established a novel local image-based DL approach to provide comprehensive quantitative information on RNFLT in fundus photographs, which was used to diagnose glaucoma. In addition, training a deep neural network based on local images to predict objective detail information in fundus photographs provided a new paradigm for the diagnosis of ophthalmic diseases.

Introduction: To describe a case of unilateral exudative retinal detachment and severe uveitis with a large subretinal deposit in a 6-year-old girl presenting with left thigh lymphadenitis. Case Presentation: A metagenome next-generation sequencing (mNGS) of the vitreous body was performed, revealing Bartonella henselae. The patient showed the resolution of retinal detachment and uveitis, as well as improvement of left thigh lymphadenitis, in response to systemic and ocular antibiotics and corticosteroids. Conclusion: Bartonella henselae neuroretinitis may manifest as exudative retinal detachment with extensive subretinal lesions and uveitis. The treatment involving systemic and ocular antibiotics and corticosteroids proved to be effective.

Importance:Postzygotic mutations in the GNAQ/GNA11 genes, which encode the G-protein nucleotide binding protein alpha subunits, have been identified in patients with phakomatosis pigmentovascularis (PPV). However, little is known about the Chinese population. Objective:To identify pathogenic mutations in pediatric patients with PPV within the Chinese population. Methods:We performed whole-exome sequencing (WES) using skin lesion tissues from pediatric patients diagnosed with PPV. Additionally, ultradeep-targeted sequencing was conducted to validate the somatic mutations. A genotype-phenotype correlation was analyzed by integrating data from previous reports with the findings of the present study. Results:Thirteen patients were enrolled, all diagnosed with the cesioflammea type of PPV, except for one patient with an unclassifiable type. We identified somatic GNA11 c.547C>T (p.R183C) variant in seven patients and GNAQ c.548G>A (p.R183Q) in four patients, with low allelic fractions ranging from 2.1% to 8.6% through ultradeep sequencing. Besides, a GNAQ c.548G>A (p.R183Q) variant was detected through targeted sequencing in one of two patients who did not exhibit detectable variants via WES. The genotype-phenotype correlation analysis, involving 15 patients with a GNA11 variant and 10 with a GNAQ variant, revealed that facial capillary malformation (87% vs. 50%, P = 0.075) and ocular melanocytosis (80% vs. 40%, P = 0.087) appeared to be more frequent in patients with GNA11 mutation compared to those with GNAQ mutations. All four patients diagnosed with cesiomarmorata type or overlapping cesioflammea and cesiomarmorata type PPV carried the GNA11 variant. Interpretation:Our study demonstrated that the majority of PPV patients in the Chinese population carried a postzygotic variant of GNAQ/GNA11, thus further confirming the pathogenic role of GNAQ/GNA11 mosaicism in the development of PPV cesioflammea type.

Bartonella henselae is a Gram-negative bacillus, mainly parasitizing on cats. When a child is scratched by a cat, they may present with the disease symptoms including regional lymphadenopathy, malaise, fever, and splenomegaly, which is known as cat-scratch disease (CSD). Ocular manifestations occur in 5–10% of patients with CSD. Neuroretinitis is the most common, and, in addition, Parinaud oculoglandular syndrome, endophthalmitis, retinochoroiditis, vascular occlusions, multiple mass-like lesions resembling ocular metastases, serous macular detachments, and retinal vasoproliferative lesions may also occur. We report a case of unilateral exudative retinal detachment and uveitis with a large subretinal deposit on the macula in a 6-year-old female with CSD, along with lymphadenitis on her left thigh. To the best of our knowledge, this case of exudative retinal detachment and uveitis with a large subretinal deposit under the retina affecting the macular area above the optic disc has not been previously reported.

PurposeWe designed a dual-modal fusion network to detect glaucomatous optic neuropathy, which utilized both retinal nerve fiber layer thickness from optical coherence tomography reports and fundus images.MethodsA total of 327 healthy subjects (410 eyes) and 87 glaucomatous optic neuropathy patients (113 eyes) were included. The retinal nerve fiber layer thickness from optical coherence tomography reports and fundus images were used as predictors in the dual-modal fusion network to diagnose glaucoma. The area under the receiver operation characteristic curve, accuracy, sensitivity, and specificity were measured to compare our method and other approaches.ResultsThe accuracy of our dual-modal fusion network using both retinal nerve fiber layer thickness from optical coherence tomography reports and fundus images was 0.935 and we achieved a significant larger area under the receiver operation characteristic curve of our method with 0.968 (95% confidence interval, 0.937-0.999). For only using retinal nerve fiber layer thickness, we compared the area under the receiver operation characteristic curves between our network and other three approaches: 0.916 (95% confidence interval, 0.855, 0.977) with our optical coherence tomography Net; 0.841 (95% confidence interval, 0.749, 0.933) with Clock sectors division; 0.862 (95% confidence interval, 0.757, 0.968) with inferior, superior, nasal temporal sectors division and 0.886 (95% confidence interval, 0.815, 0.957) with optic disc sectors division. For only using fundus images, we compared the area under the receiver operation characteristic curves between our network and other two approaches: 0.867 (95% confidence interval: 0.781-0.952) with our Image Net; 0.774 (95% confidence interval: 0.670, 0.878) with ResNet50; 0.747 (95% confidence interval: 0.628, 0.866) with VGG16.ConclusionOur dual-modal fusion network utilizing both retinal nerve fiber layer thickness from optical coherence tomography reports and fundus images can diagnose glaucoma with a much better performance than the current approaches based on optical coherence tomography only or fundus images only.

Purpose To develop and validate deep learning algorithms that can identify and classify angle-closure (AC) mechanisms using anterior segment optical coherence tomography (AS-OCT) images. Methods This cross-sectional study included participants of the Handan Eye Study aged ≥ 35 years with AC detected via gonioscopy or on the AS-OCT images. These images were classified by human experts into the following to indicate the predominant AC mechanism (ground truth): pupillary block, plateau iris configuration, or thick peripheral iris roll. A deep learning architecture, known as comprehensive mechanism decision net (CMD-Net), was developed to simulate the identification of image-level AC mechanisms by human experts. Cross-validation was performed to optimize and evaluate the model. Human-machine comparisons were conducted using a held-out and separate test sets to establish generalizability. Results In total, 11,035 AS-OCT images of 1,455 participants (2,833 eyes) were included. Among these, 8,828 and 2.207 images were included in the cross-validation and held-out test sets, respectively. A separate test was formed comprising 228 images of 35 consecutive patients with AC detected via gonioscopy at our eye center. In the classification of AC mechanisms, CMD-Net achieved a mean area under the receiver operating characteristic curve (AUC) of 0.980, 0.977, and 0.988 in the cross-validation, held-out, and separate test sets, respectively. The best-performing ophthalmologist achieved an AUC of 0.903 and 0.891 in the held-out and separate test sets, respectively. And CMD-Net outperformed glaucoma specialists, achieving an accuracy of 89.9% and 93.0% compared to 87.0% and 86.8% for the best-performing ophthalmologist in the held-out and separate test sets, respectively. Conclusions Our study suggests that CMD-Net has the potential to classify AC mechanisms using AS-OCT images, though further validation is needed.

Glaucoma is a serious eye disease and glaucoma optic disc hemorrhage (GODH) is an important diagnostic indicator for glaucoma. Deep-learning-based medical image segmentation methods for automatic optic cup and disc segmentation have made tremendous progress. However, when it comes to the segmentation of GODH, classical deep learning technologies face two main challenges: the difficulties in distinguishing GODH from the end points or bending points of blood vessels, and the imbalance between the pixel classes of the target area and the background area. In this paper, we proposed a deep learning framework integrating expert knowledge (E-Net) for the segmentation of GODH in fundus images. This E-Net consisted of a primary network for GODH segmentation and two auxiliary networks for extraction of optic disc (OD) and blood vessels. The segmentation probability maps from the two auxiliary networks were used to improve the segmentation accuracy of GODH, via expert knowledge loss functions and attention mechanism. Moreover, we designed a weighted segmentation accuracy loss function to balance the segmentation accuracy of the target and background region, thus fully mining the substantial information in the fundus images. The proposed E-Net was verified on a GODH dataset from Beijing Tongren Hospital. The experiments showed that the proposed E-Net achieved state-of-the-art results on this dataset.

Abstract Background Sturge–Weber Syndrome (SWS) is a rare disease involving the eye, skin, and brain. Port-wine stain (PWS) and glaucoma are common clinical manifestations. This study analysed the clinical characteristics of infants with PWS and glaucoma secondary to SWS. Methods Children with PWS and glaucoma secondary to SWS were enrolled. Data were extracted from ophthalmic and systemic examination findings. Ocular examinations included intraocular pressure, anterior segment and fundus examination, and ocular A-scan and B-scan ultrasonography. Results Fifty-seven patients were included, with a mean age of 9.9 ± 11.9 months, and 34 (59.6%) patients were male. In all, 61 eyes were diagnosed with glaucoma. Forty-one patients (71.9%) had unilateral facial PWS and glaucoma occurred on the same side. Eight patients (14.0%) had Mongolian spots and ten patients (17.5%) had epilepsy. Corneal changes included corneal oedema (n = 36 eyes, 59.0%), corneal opacity (n = 15 eyes, 24.6%), and Haab lines (n = 13 eyes, 21.3%). Mean corneal diameter and thickness in the eyes with glaucoma was larger than those in the unaffected eyes (12.2 ± 0.7 mm vs 10.8 ± 0.6 mm, P < 0.001; 681.2 ± 106.4 µm vs 578.2 ± 58.2 µm, P < 0.001). The eyes with glaucoma had higher IOP and larger axial length and C/D ratio (19.3 ± 6.2 mmHg vs 11.6 ± 4.2 mmHg, P < 0.001; 21.23 ± 1.93 mm vs 19.68 ± 1.61 mm, P < 0.001; and 0.57 ± 0.18 vs 0.24 ± 0.15, P < 0.001). Thirty-three (57.9%) and 25 (43.9%) patients showed diffuse choroidal haemangioma (DCH) and conjunctival/episcleral haemangiomas, respectively. Ten patients (17.5%) showed iris anterior insertion or hyperpigmentation in the anterior chamber angles. Six of them had Mongolian spots at the same time. Conclusions Monocular glaucoma, DCH, and conjunctival/episcleral haemangiomas are common in SWS patients with PWS and glaucoma. Glaucomatous eyes have larger corneal diameter and axial length and thicker cornea. Patients with Mongolian spots have higher incidence of iris anterior insertion or hyperpigmentation in anterior chamber angle.

Purpose:By comparing the performance of different models between artificial intelligence (AI) and doctors, we aim to evaluate and identify the optimal model for future usage of AI.Methods:A total of 500 fundus images of glaucoma and 500 fundus images of normal eyes were collected and randomly divided into five groups, with each group corresponding to one round. The AI system provided diagnostic suggestions for each image. Four doctors provided diagnoses without the assistance of the AI in the first round and with the assistance of the AI in the second and third rounds. In the fourth round, doctor B and doctor D made diagnoses with the help of the AI and the other two doctors without the help of the AI. In the last round, doctor A and doctor B made diagnoses with the help of AI and the other two doctors without the help of the AI.Results:Doctor A, doctor B, and doctor D had a higher accuracy in the diagnosis of glaucoma with the assistance of AI in the second (p=0.036, p=0.003, and p ≤ 0.000) and the third round (p=0.021, p ≤ 0.000, and p ≤ 0.000) than in the first round. The accuracy of at least one doctor was higher than that of AI in the second and third rounds, in spite of no detectable significance (p=0.283, p=0.727, p=0.344, and p=0.508). The four doctors' overall accuracy (p=0.004 and p ≤ 0.000) and sensitivity (p=0.006 and p ≤ 0.000) as a whole were significantly improved in the second and third rounds.Conclusions:This "Doctor + AI" model can clarify the role of doctors and AI in medical responsibility and ensure the safety of patients, and importantly, this model shows great potential and application prospects.

Purpose: We design three new indexes of retinal nerve fiber layer thickness (RNFLT) by functional data analysis (FDA) methods and evaluate the diagnostic performance of support vector machines (SVM) based on these three new indexes and average RNFLT. Method: A total of 217 healthy eyes (122 subjects) and 88 glaucoma eyes (49 patients) were included. Three new indexes (minimum of RNFLT curve, range of derivative curve and ISNT score) of RNFLT from optical coherence tomography (OCT) and average RNFLT were used as predictors in the SVM. The sensitivity, specificity and area under the re-ceiver operating characteristic curve (AUC) were used to evaluate the diagnostic performance of the proposed and compared methods. Results: The sensitivity of the proposed method was 97.73%, 95.45%, and 79.55%, respectively, at the specificity of 90%, 95%, and 99%.A significantly larger AUC of 98.81% (95% con-fidence interval (CI), 97.84%-99.78%) was obtained using the proposed method compared with a previous study -artificial neural networks based on RNFLT of four sectors under three division methods: 93.97% (95% CI, 90.63%-97.63%) with clock sectors division, 94.55% (95% CI, 91.43%-98.58%) with ISNT (inferior -superior-nasal-temporal) sectors division and 92.90% (95% CI, 88.87%-97.62%) with planimetric sectors division. Conclusions: The three new indexes based on RNFLT curves combined with SVM can be used to distinguish glaucoma from healthy subjects with high accuracy, performing better than conventional methods.

Purpose: To analyze the relationship between the severity of type 1 retinopathy of prematurity (ROP) and the level of vascular endothelial growth factor (VEGF) in aqueous fluid. Methods: The aqueous VEGF levels of 49 patients (88 eyes) with type 1 ROP were retrospectively analyzed. These eyes were categorized into three groups according to the severity of disease: aggressive retinopathy of prematurity (A-ROP), threshold of ROP (T-ROP), and type 1 pre-threshold ROP (P-T-1). The differences in aqueous VEGF levels among these three groups were compared. The relationship between the aqueous VEGF level and the retinal changes of ROP, including the vessel tortuosity in zone I, and the location and stage of the ROP lesions, were also analyzed. Results: The aqueous VEGF level of the A-ROP group was the highest among the three groups, followed by those of the T-ROP and P-T-1 groups. The aqueous VEGF level was negatively correlated with the zone and the stage of the ROP diseases, while it was positively correlated with the venous tortuosity in zone I and had no relevance with the artery tortuosity in zone I. Conclusions: The aqueous VEGF level in A-ROP was the highest in type I ROP. The location of the ROP lesions and the venous tortuosity in zone I correlated with the aqueous VEGF level and could indicate the severity of ROP.

PURPOSE:To investigate the clinical and histopathological features of congenital fibrovascular pupillary membrane (CFPM) in Chinese patients. METHODS:This retrospective study reviewed CFPM cases treated at Beijing Children's Hospital. The clinical manifestations, approaches of treatment, outcomes, and histopathological findings were collected and analyzed. RESULTS:A total of 33 patients with CFPM were reviewed. All patients had unilateral eye involvement. A total of 21 eyes (63.64%) had a white membrane that partially covered the pupil and 12 eyes (36.36%) had a membrane that completely covered the pupil. Of the 12 eyes with a complete pupillary membrane, 6 (50%) had glaucoma. For eyes with a partial pupillary membrane, 11 eyes (52.38%) were followed up at the outpatient clinic without surgery and 10 eyes (47.62%) underwent membranectomy and pupilloplasty due to visual axis blockage. For the 12 eyes with a complete pupillary membrane, 6 eyes (50%) with normal intraocular pressure (IOP) received membranectomy and pupilloplasty combined with iridectomy, and 1 (16.67%) of these 6 eyes underwent a reoperation after 5 months due to a recurrent membrane. Furthermore, 6 eyes (50%) with glaucoma had membranectomy, pupilloplasty, iridectomy, and goniosynechialysis. Among these 6 eyes, 2 eyes (33.33%) underwent a reoperation due to the recurrence of a membrane and 4 eyes (66.67%) had a pale optic disc. The histopathological findings revealed that these membranes were mainly composed of fibrous tissue, lymphocytes, pigment epithelial cells, and vascular tissues. CONCLUSIONS:CFPM has diverse manifestations, including a partial pupillary membrane, a complete pupillary membrane with normal IOP, and a complete pupillary membrane with glaucoma. Timely diagnosis and treatment are critical when the visual axis is blocked and/or the IOP is high. [J Pediatr Ophthalmol Strabismus. 2021;58(2):105-111.].

青光眼是世界第二大致盲性眼病,视网膜神经纤维层(RNFL)缺损是诊断青光眼的重要特征.在临床应用中主要采用光学相干断层扫描(OCT)测量RNFL厚度.然而在我国的多数中小型医院和体检中心,只有眼底照相机而不具备OCT设备.因此利用眼底照和OCT的多模态数据,设计了一种基于眼底照来预测RNFL厚度的深度残差回归神经网络.该网络通过眼底照中的局部区域信息预测此区域的RNFL厚度,并对视盘外围一周范围内的RNFL厚度给出全面的刻画.在一个来自北京同仁医院的真实数据集上的实验结果显示,本文算法预测的RNFL厚度值与OCT测量值具有高度的一致性(对于正常眼平均绝对误差EMA=14.884,Pearson相关系数r=0.885,决定系数R2 =0.781;对于青光眼EMA=15.108,r=0.872,R2=0.754).评估结果表明所提方法对基于眼底照预测RN-FL厚度具有良好的临床实用性.

The application of deep learning algorithms for medical diagnosis in the real world faces challenges with transparency and interpretability. The labeling of large-scale samples leads to costly investment in developing deep learning algorithms. The application of human prior knowledge is an effective way to solve these problems. Previously, we developed a deep learning system for glaucoma diagnosis based on a large number of samples that had high sensitivity and specificity. However, it is a black box and the specific analytic methods cannot be elucidated. Here, we establish a hierarchical deep learning system based on a small number of samples that comprehensively simulates the diagnostic thinking of human experts. This system can extract the anatomical characteristics of the fundus images, including the optic disc, optic cup, and appearance of the retinal nerve fiber layer to realize automatic diagnosis of glaucoma. In addition, this system is transparent and interpretable, and the intermediate process of prediction can be visualized. Applying this system to three validation datasets of fundus images, we demonstrate performance comparable to that of human experts in diagnosing glaucoma. Moreover, it markedly improves the diagnostic accuracy of ophthalmologists. This system may expedite the screening and diagnosis of glaucoma, resulting in improved clinical outcomes.

We report the clinical features, treatments, and outcomes of 9 infants with glaucoma secondary to congenital fibrovascular pupillary membrane. The clinical features included unilateral low vision, high intraocular pressure (IOP), enlarged and cloudy cornea, loss of anterior chamber, and pupillary membrane. All patients underwent membranectomy, peripheral iridectomy, pupilloplasty, and goniosynechialysis as primary treatment. The membranes were posterior to the iris in all 9 eyes. In 5 eyes, the membrane covered the ciliary processes, and in 1 eye the membrane reached the posterior lens capsule. Following primary surgery, 3 patients developed membrane recurrence, 4 had refractory elevated IOP, and 2 developed lens opacities. All 4 eyes with poor postoperative IOP control had iris root insertion anterior to the scleral spur. Five patients received additional surgeries including membranectomy, pupilloplasty, goniosynechialysis, cyclocryotherapy, ciliary photocoagulation, Amhed valve implantation, and lensectomy. One patient had refractory elevated IOP at last follow-up. IOP in the other 8 eyes was well controlled. None of the affected eyes was able to fix and follow at last follow-up.

BACKGROUND Children with congenital glaucoma are often accompanied by acquired epiblepharon in the lower eyelid, which causes entropion of the lower eyelid and damages the cornea. AIM To infer the possible causes of lower eyelid entropion by comparing the difference of ocular axis and corneal diameter between inverted and non-inverted ciliary eyes in children with congenital glaucoma. METHODS A total of 15 patients (11 males and 4 females) diagnosed with congenital glaucoma between July 2016 and January 2019 at Tongren Hospital were included. Five patients had bilateral glaucoma, and ten had unilateral glaucoma. Each patient had only one eye with lower eyelid entropion which is associated with congenital glaucoma. All the patients had no entropion in another eye. The clinical data were collected. Main outcome measures were the ocular axis and corneal diameter. RESULTS The average age of the 15 patients was 1.85 ± 0.49 years. Paired t-test showed that the average ocular axis of congenital glaucoma eyes with lower eyelid entropion (24.86 ± 3.44 mm) was significantly longer than that of congenital glaucoma eyes without lower eyelid entropion (20.79 ± 1.34 mm; P < 0.001). The average corneal diameter of congenital glaucoma eyes with lower eyelid entropion (13.61 ± 0.88 mm) was also significantly greater than that of congenital glaucoma eyes without lower eyelid entropion (11.63 ± 0.48; P < 0.001). CONCLUSION The rapid growth of the ocular axis and corneal diameter may be the main cause of congenital glaucoma with acquired lower eyelid entropion. Therefore, children with poor control of intraocular pressure and excessive growth of ocular axis and corneal diameter must be observed for the existence of acquired epiblepharon.

Glaucoma is a chronic eye disease that can cause permanent visual loss and is difficult to detect early. Retinal nerve fiber layer defect (RNFLD) is clinical evidence for the diagnosis of glaucoma. Classical deep learning based methods can be used to segment RNFLD from fundus images. However, the segmentation results of these methods do not have the specific geometry of RNFLD, and the segmentation errors of fundus images with special styles are large. In this paper, we present a novel conditional adversarial shuffle U-shaped network (CASU-Net) to segment RNFLD, which consists of a generator and a discriminator. For the generator, a mixed loss is designed, which consists of an adaptive weighted segmentation loss and an adversarial loss. This adaptive weighted segmentation loss can balance the segmentation accuracy of the target and background region, and assign more attention to the hard samples, thus ensuring the consistent improvement of the segmentation accuracy of all fundus images. The adversarial loss not only helps to improve the pixel-wise segmentation accuracy but also makes the geometry of the RNFLD segmentation closer to the ground truth. In addition, in the generator, a shuffle module was designed to fully mine the information of all channels to improve the feature extraction capability of the model. The proposed CASU-Net is verified on a RNFLD dataset from Beijing Tongren Hospital. The experiments show that the CASU-Net achieves state-of-the-art results on this dataset.

设计了一种蚁群算法,用于进行基因多位点组合与连续型表型的关联分析.在欧洲生物信息学研究所发布的一项基因及眼压的数据集上,评估了本文设计方法的性能,实验结果表明,利用本文设计的蚁群算法能够发现与眼压显著相关的基因双位点组合,这为研究青光眼的发病机制提供了新的线索.另外,对于研究其他疾病的多位点组合和连续型表型的关联,本文设计的蚁群算法提供了一种新的思路.

目的 探究以综合护理干预方式对微导管辅助小梁切开术治疗儿童青光眼术后护理康复效果的影响.方法 选取2018年1月至2018年12月进行微导管辅助小梁切开术的41例青光眼患儿.对照组采取青光眼手术常规护理,干预组进行综合护理干预.比较两组术后并发症发生率,家长积极心理情绪状况.结果 干预组患儿术后并发症发生率较对照组患儿降低,家属的积极心理情绪率显著高于对照组.结论 对微导管辅助小梁切开术后的青光眼患儿采取综合护理干预,能够降低患儿术后并发症发生率,保证术后康复效果,改善家长心理情绪状态.