The rapid development of intelligent ophthalmology research in recent years still faces some challenges in its clinical application or clinical translation process. Two important issues that urgently need to be addressed in the development of intelligent ophthalmology are: promoting clinical application and maintaining medical equity. In response to the aforementioned issues, this article analyzes the reasons and current situation of the insufficient promotion of clinical application and the potential challenges of medical equity, and proposes that promoting clinical application and maintaining medical equity are key issues in the development of intelligent ophthalmology. At the same time, it systematically proposes corresponding specific measures to promote the development of intelligent ophthalmology.

Glaucoma is an eye disease characterized by pathologically elevated intraocular pressure, optic nerve atrophy, and visual field defects, which can lead to irreversible vision loss. In recent years, the rapid development of artificial intelligence(AI)technology has provided new approaches for the early diagnosis and management of glaucoma. By classifying and annotating glaucoma-related images, AI models can learn and recognize the specific pathological features of glaucoma, thereby achieving automated image analysis and classification. Research on glaucoma imaging classification and annotation mainly involves color fundus photography(CFP), optical coherence tomography(OCT), anterior segment optical coherence tomography(AS-OCT), and ultrasound biomicroscopy(UBM)images. Color fundus photography is primarily used for the annotation of the optic cup and disc, OCT is used for measuring and annotating of the thickness of the retinal nerve fiber layer, and AS-OCT and UBM focus on the annotation of the anterior chamber angle structure and the measurement of anterior segment structural parameters. To standardize the classification and annotation of glaucoma images, enhance the quality and consistency of annotated data, and promote the clinical application of intelligent ophthalmology, this guideline has been developed. This guideline systematically elaborates on the principles, methods, processes, and quality control requirements for the classification and annotation of glaucoma images, providing standardized guidance for the classification andannotation of glaucoma images.

Objective:s To investigate the risk factors for delayed encephalopathy after acute carbon monoxide poisoning (DEACMP) in patients with acute carbon monoxide poisoning (ACOP) and to develop predictive models based on machine learning algorithms.Methods:Patients with ACOP hospitalized at the First Affiliated Hospital of Zhengzhou University from August 2019 to October 2024 were included, with the occurrence of DEACMP as the outcome measure. The dataset was randomly divided into training and validation sets at a ratio of 7:3. Lasso regression was used to select features influencing the outcome in training sets. Nine machine learning models—including Random Forest (RF), Extreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM)—were constructed. Receiver operating characteristic (ROC) curves were plotted and the area under the curve (AUC) calculated for each model. Calibration curves were used to assess accuracy, and decision curve analysis (DCA) was applied to evaluate clinical utility. The SHapley Additive exPlanations (SHAP) method was employed to visualize and interpret the best-performing model.Results:A total of 264 ACOP patients were included, of whom 54 (20.5%) developed DEACMP. Lasso regression identified eight key feature variables. Based on these factors, predictive models were constructed, showing good AUC stability across the nine machine learning models in both training (0.92–0.99) and validation sets (0.85–0.91). The RF model performed best, with an AUC of 0.99 in the training set and 0.90 in the validation set; its calibration curve and DCA curve also demonstrated excellent performance. SHAP analysis of the RF model revealed the importance ranking of factors from highest to lowest as follows: Glasgow Coma Scale (GCS) score, duration of coma, age, history of coronary heart disease, CK-MB level, monocyte count, diastolic blood pressure (DBP), and drinking history.Conclusions:The RF model exhibited the highest predictive performance for DEACMP occurrence in ACOP patients. The influencing factors, ranked in order of importance from highest to lowest, are as follows: GCS score, duration of coma, age, history of coronary heart disease, CK-MB level, monocyte count, DBP, and drinking history.

This paper provides a comprehensive analysis of the current state of intelligent ophthalmology in China, including technological advancements, academic exchange platforms, policy support, future challenges, and potential solutions. Technologically, remarkable progress have been made in various areas of intelligent ophthalmology in China, including diabetic retinopathy, fundus image analysis, and crucial aspects such as quality assessment of medical artificial intelligence products, clinical research methods, technological evaluation, and industrial standards. Researchers are constantly improving the safety and standardization of intelligent ophthalmology technology by formulating clinical application guidelines and standards. Academic exchange platforms have been established to provide extensive collaboration opportunities for professionals across diverse fields, and various academic journals serve as publication platforms for intelligent ophthalmology research. Regarding public policy, the Chinese government has not only established a supportive policy environment for the advancement of intelligent ophthalmology through various documents and regulations, but provided a legal basis and management framework. However, there are still challenges to overcome, such as technological innovation, data privacy and security, outdated regulations, and talent shortages. To tackle these issues, there is a requirement for increased technological research and development, the establishment of regulatory frameworks, talent cultivation, and greater awareness and acceptance of new technologies among patients. By comprehensively addressing these challenges, intelligent ophthalmology in China is expected to continue leading the industry's global development, bringing more innovation and convenience to the field of ophthalmic healthcare.

The rapid development of artificial intelligence(AI)technology has driven the intelligentization of medicine.In recent years,due to the continuous improvement of machine learning and deep learning technologies,AI technology has made rapid progress in the diagnosis and treatment of ocular fundus diseases,including retinal vascular disease,macular disease,retinal detachment,and retinal pigment degeneration.Early diagnosis and treatment are of great significance for the prognosis of ocular fundus diseases.This article gives a guide for the application of AI in automatic segmentation of ret-inal images and disease diagnosis,providing a reference for further research and appIication of AI in this field.

To enhance the learning stickiness, improve low completion rate of online teaching, and promote teaching quality has become the key to solve the contradiction in online teaching. In this paper, taking the teaching of biochemistry as example, based on the trigger mechanism, maintenance mechanism and migration mechanism of sticky learning, guided by the three-dimensional goal of "knowledge and skills, process and method, emotional attitude and values", the BOPPPS (bridge-in, objective, pre-assessment, participatory-learning, post-assessment, summary) teaching model was combined with online teaching. According to the interactive behavior in the course learning space, the Spearman rank correlation analysis was performed by SPSS 18.0 software to comprehensively evaluate the learning stickiness degree. The research has found that, due to its "micro but refined, compact structure and student-centered" characteristics, BOPPPS combining with online teaching can effectively make up for the time and space limitations of offline teaching and the excessively broad online teaching, bring benefits from the perspectives of "inclusion, attraction and production", promote students' active learning, and practically improve learning stickiness. The research provides a new idea for creating online "golden" courses.

Objective:To solve international students' problems of learning difficulties and passive learning caused by language barriers in the process of biochemistry learning from the perspective of teachers in this specialty.Methods:Eighty international students were randomly divided into experimental group and control group. In the experimental group, the regional management mode was introduced in teaching, allowing students to speak mother tongues or English for group discussions on well-designed questions, and at the same time, classroom quizzes and stage tests were given, introducing formative evaluation to supervise students' learning and assess their learning performance. The control group received conventional teaching. The learning effects were assessed through a final exam and questionnaire survey. SPSS 25.0 was used to perform the Kruskal-Wallis H test and Nemenyi test. Results:Twenty-seven (75.00%) students believed that group discussion by region could deepen the discussion of questions; 27 (75.00%) no longer felt difficult, or even felt easy, to learn biochemistry; and nearly 90.00% of the students affirmed the formative evaluation mode, believing that it had positive effects on their learning attitude and behavior. In addition, the median exam score of the experimental group was 36.94% higher than that of the control class in the same year.Conclusions:Regional management combined with formative evaluation can promote international students' learning enthusiasm, improve their comprehensive achievement, and positively affect their learning behavior.

Objective:To analyze the epidemiological characteristics of reinfection of 2019-nCoV and influencing factors, and provide evidence for effective prevention and control of COVID-19 epidemic.Methods:The incidence data of COVID-19 in Ningbo from January 1, 2020 to November 30, 2022 were collected from the infectious disease surveillance system of Chinese information system for disease control and prevention. The incidence of reinfection of 2019-nCoV was investigated by using questionnaire. logistic regression analysis was used to analyze the influences of gender, age, time interval from the first infection, history of underlying disease, 2019-nCoV vaccination dose and disease severity on the reinfection.Results:A total of 897 previous 2019-nCoV infection cases were investigated, of which 115 experienced the reinfection of 2019-nCoV, the reinfection rate was 12.82%. The interval between the two infections M( Q1, Q3) was 1 052 (504, 1 056) days. Univariate analysis showed that age, 2019-nCoV vaccination dose, history of underlying disease, type of 2019-nCoV variant causing the first infection, time interval from the first infection and severity of the first infection were associated with the reinfection rate (all P<0.05). Multivariate logistic regression analysis showed that the risk for reinfection in age group 30- years was higher than that in age group ≥60 years ( OR=2.10, 95% CI: 1.11-3.97). No reinfection occurred in those with time interval from the first infection of <6 months, and the risk for reinfection was higher in those with the time interval of ≥12 months than in those with the time interval of 6- months ( OR=6.68, 95% CI: 3.46-12.90). The risk for reinfection was higher in the common or mild cases than in the asymptomatic cases ( OR=2.64, 95% CI: 1.18-5.88; OR=2.79, 95% CI: 1.27-6.11). Conclusion:The time interval from the first infection was an important influencing factor for the reinfection of 2019-nCoV, and the probability of the reinfection within 6 months was low.

Objective:To analyze the clinical characteristics of patients with acute glyphosate herbicide poisoning and the differences in the severity of poisoning.Methods:A retrospective analysis was performed on patients with acute glyphosate herbicide poisoning admitted to the First Affiliated Hospital of Zhengzhou University from January 2014 to December 2020. The general information, exposure time, poisoning dose, poisoning cause, poisoning route, clinical manifestations, laboratory examination results during hospitalization, treatment measures, hospital stays and prognosis of the patients were collected. The patients were graded according to the poisoning severity scoring standard of Chinese Expert Consensus on Diagnosis and Treatment of Acute Poisoning in 2016. The highest severity score during hospitalization was used as the final grade. According to the final grade, asymptomatic and mild patients were included in the mild group, and moderate, severe and death patients were included in the severe group. The independent sample T test or Mann-Whitney U test was used for measurement data, and χ2 test or Fisher's exact test was used for counting data. The differences of general data and clinical data between the two groups were compared. Results:According to the inclusion and exclusion criteria, 83 patients with acute glyphosate herbicide poisoning were selected as the study subjects. All patients survived, mainly mild poisoning (56.6%), with a male to female ratio of 33∶50, and an average age of 39 years. The number of poisoning cases increased yearly (the highest in 2019), and most cases occurred in spring and summer. The main cause of poisoning was suicide (71.1%), direct oral administration (83.1%) was the primary route of poisoning, and the dominating clinical manifestations were digestive symptoms (71.1%). Laboratory tests showed increased white blood cell count (WBC), neutrophil percentage (NEUT %) and D-dimer, and decreased hemoglobin and potassium. Compared with the mild group, patients in the severe group were older [(51±17) years vs. (35±19) years], had a higher proportion of suicide and direct oral administration, a longer hospital stay [8.0 (4.8, 12.0) d vs. 3.0 (2.0, 5.5) d], a higher dose of poisoning [200.0 (50.0, 200.0) mL vs. 30.0 (11.3, 57.5) mL], and higher NEUT % within 24 h of admission [(83.4±10.4) vs. (73.2±12.8)]. The increase of WBC, NEUT %, aspartate aminotransferase, prothrombin time, D-dimer and the decrease of serum potassium were more common in the severe group than the mild group, with statistical significance (all P<0.05). Conclusions:The number of patients with acute glyphosate herbicide poisoning is increasing yearly. Generally, the condition is mild and the prognosis is satisfying. The severity is more serious in the middle-aged and elderly patients andthose with direct oral administration, high toxic dose, and high NEUT % within 24 h of admission. Severe poisoning is more likely to cause changes in laboratory indicators.

Objective:To investigate the infection rate in close contacts of COVID-19 patients before and after the last negative nucleic acid test, evaluate the effect of dynamic nucleic acid test in determining the infectivity of COVID-19 patients.Methods:Dynamic nucleic acid test results of COVID-19 cases were collected in a retrospective cohort study. COVID-19 cases with negative nucleic acid test results before their first positive nucleic acid tests were selected as study subjects. Close contacts of the index cases and the secondary close contacts were kept isolation for medical observation to assess their risk of infection.Results:This study included 89 confirmed cases from two local COVID-19 epidemics in Ningbo. A total of 5 609 close contacts were surveyed, the overall infection rate was 0.20%. No close contacts of the COVID-19 cases before the last negative nucleic acid test were infected, and the infection rate in the close contacts of the COVID-19 cases after the last negative nucleic acid test was 1.33%, all of these close contacts lived together with the index cases. No secondary close contacts were infected.Conclusion:COVID-19 patient becomes infectious after the last nucleic acid is negative, and has no infectivity before the last nucleic acid negative.