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 To explore the clinical efficacy of Wuhuang Shengji decoction irrigation combined with inci-sion and hanging suture in patients with perianal abscess.METHODS A total of 121 patients with perianal abscess admitted to the Anorectal Department of Ningbo Traditional Chinese Medicine Hospital from Jan.2022 to Jan.2024 were selected as the study subjects.According to the treatment methods,they were divided into a control group(n=37),a positive control group(n=41)anda research group(n=43).The control group was treated with incision and hanging suture,the positive control group was treated with recombinant human epidermal growth factor combined with incision and hanging suture,and the research group was treated with Wuhuang Shengji Decoction irrigation combined with incision and hanging suture.The clinical efficacy,the time of necrotic tissue shedding,new skin appearing,wound itch disappearing and wound healing and the recurrence rate were ob-served.The visual analogue scale(VAS),wound secretion score and expression levels of vascular endothelial growth factor(VEGF)and platelet-derived endothelial cell growth factor(PD-ECGF)in wound secretions were compared before and 14 days after treatment in the three groups.RESULTS The clinical efficacy of the study group(90.70%)was higher than that of the positive control group(87.80%)and control group(70.27%);the recur-rence rate of the study group(2.33%)was lower than that of the positive control group(9.76%)and the control group(18.92%),and the differences were statistically significant(P<0.05).The time required for necrotic tissue shedding,new skin appearing,wound itch disappearing and wound healing followed the trend of study group

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.

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.

With the rapid advancement of artificial intelligence (AI) technology, particularly breakthroughs in large models, AI applications in healthcare are becoming increasingly widespread.Ophthalmology, as a critical branch of medicine, has emerged as a clinical specialty with comprehensive AI research and applications, especially in the AI-driven analysis of ophthalmic imaging.Currently, AI in ophthalmology is undergoing profound transformation driven by large model technology.AI large models, with their robust data comprehension and multimodal interaction capabilities, offer new possibilities for the diagnosis, treatment, and health education of ophthalmic diseases, powerfully propelling the evolution of current AI paradigms in ophthalmology.This article explores the novel opportunities brought by the extensive application of AI large models in ophthalmic research and practice, and provides recommendations for ophthalmologists and insights for industry development.

In recent years, generative artificial intelligence (AI) technologies have achieved remarkable progress in the early screening, risk prediction, disease progression assessment, and clinical trial design of glaucoma.Using advanced algorithms, such as generative adversarial networks, variational autoencoders, and diffusion models, researchers have synthesized high-quality structural images of the optic disc, macular region, and retinal nerve fiber layer, which effectively alleviates the limitations of scarce clinical imaging data and label imbalance.These methods have substantially improved the accuracy and generalization of deep learning models in visual field defect prediction, structure-function mapping, and longitudinal disease progression simulation.Meanwhile, multimodal generative approaches that integrate imaging data, visual field tests, and clinical features have facilitated individualized prediction of glaucoma progression.In addition, large language models have shown preliminary potential in ophthalmic image interpretation, clinical text information extraction, and decision support, providing new insights into intelligent ophthalmic diagnosis and treatment.However, the clinical implementation of generative AI in glaucoma faces challenges.The pathological authenticity and cross-device consistency of generated images require further validation, which may affect the reliability of early glaucoma detection.The heterogeneous characteristics of different glaucoma subtypes, such as open-angle and angle-closure glaucoma, also limit the generalization of synthetic data.Moreover, issues related to model interpretability (" black-box" nature), artifact generation, data privacy, and ethical governance remain key barriers to clinical translation.In the future, it is expected that establishing large-scale training frameworks that incorporate multicenter, multimodal, and multiethnic datasets will enhance model robustness and clinical applicability.Furthermore, generative AI may contribute to remote ophthalmic care and personalized precision therapy by enhancing low-quality image, reconstructing missing data, and simulating dynamic disease courses.This article reviews the current applications, core technologies, and challenges of generative AI in glaucoma diagnosis and management, and discusses its future directions and translational potential in clinical ophthalmology.

With the rapid advancement of artificial intelligence (AI) technology, particularly breakthroughs in large models, AI applications in healthcare are becoming increasingly widespread.Ophthalmology, as a critical branch of medicine, has emerged as a clinical specialty with comprehensive AI research and applications, especially in the AI-driven analysis of ophthalmic imaging.Currently, AI in ophthalmology is undergoing profound transformation driven by large model technology.AI large models, with their robust data comprehension and multimodal interaction capabilities, offer new possibilities for the diagnosis, treatment, and health education of ophthalmic diseases, powerfully propelling the evolution of current AI paradigms in ophthalmology.This article explores the novel opportunities brought by the extensive application of AI large models in ophthalmic research and practice, and provides recommendations for ophthalmologists and insights for industry development.

Objective:To evaluate the short-term and long-term outcomes of patients with locally advanced low rectal cancer who achieved clinical complete response (cCR) or near-clinical complete response (near-cCR) after neoadjuvant chemoradiotherapy (nCRT) and then underwent local excision.Methods:This was a descriptive case series study. Clinical data of patients with low rectal cancer who received neoadjuvant therapy, achieved cCR or near-cCR, underwent local excision, and had complete postoperative follow-up data were retrospectively analyzed. The study period was from May, 2015 to October, 2024, and the patients were treated at Fujian Medical University Union Hospital. Indications for local excision in this study were as follows: pathologically confirmed rectal adenocarcinoma, with the lower edge of the tumor ≤ 6 cm from the anal verge; maximum diameter of the lesion ≤ 2 cm after nCRT; no regional lymph node metastasis detected by transrectal endoscopic ultrasound (ERUS), pelvic magnetic resonance imaging (MRI), or positron emission tomography-computed tomography (PET-CT) after nCRT; MRI showing fibrosis of the primary lesion with a small amount of high signal on diffusion-weighted imaging (DWI), consistent with ymrT0-1 stage; serum carcinoembryonic antigen level within the normal range (< 5 μg/L) after nCRT; complicated with severe underlying diseases such as cardiovascular and cerebrovascular diseases and assessed as unable to tolerate radical surgery through comprehensive evaluation; and signed informed consent for local excision. The contraindications were: colonoscopic pathology indicating poorly differentiated adenocarcinoma or signet ring cell carcinoma; suspected lateral lymph node metastasis before neoadjuvant therapy; patients with residual lesions exceeding 3 cm in range after treatment. A total of 153 patients were included in this study, including 84 males and 69 females. The median age was 62 years, and the median distance from the tumor to the anal verge after neoadjuvant therapy was 4.0 cm. The short-term efficacy indicators of this study included postoperative complications of local excision and postoperative pathological results, and the long-term efficacy indicators included oncological prognosis (3-year cumulative local recurrence rate, 3-year cumulative distant metastasis rate, 3-year progression-free survival, and 3-year overall survival) and anal function at 1 year after surgery evaluated using the Low Anterior Resection Syndrome (LARS) scale where the total score is 42 points such that 0-20 points indicate no LARS, 21-29 points indicate mild LARS, and 30-42 points indicate severe LARS.Results:Postoperative pathology showed 122 cases (79.7%) of ypT0 stage, 10 cases (6.5%) of ypT1 stage, 18 cases (11.8%) of ypT2 stage, and 3 cases (2.0%) of ypT3 stage. The incidence of surgery-related complications was 42.5% (65/153), and the main complications included perianal pain (39.9%, 61/153), intestinal wall incision dehiscence (21.6%, 33/153), and intestinal wall incision infection (18.3%, 28/153). The proportion of patients who received hypofractionated radiotherapy before surgery and developed intestinal wall incision dehiscence was 65.2% (15/23), which was higher than that in the conventional long-course (13.6%, 16/118) and short-course radiotherapy groups (16.7%,2/12) (χ 2=30.55, P<0.001); of the 20 patients who received additional immunotherapy before surgery, 13 developed intestinal wall incision dehiscence was 65.0%, which was higher than that in the group without additional immunotherapy [15.0%(20/133),χ 2=25.66, P<0.001]. The median follow-up time of the entire group was 35.4 months. During the follow-up period, there were 9 cases of postoperative local recurrence, with a 3-year cumulative local recurrence rate of 7.9% and 5 cases of distant metastasis, with a 3-year cumulative distant metastasis rate of 5.0%. The 3-year progression-free survival rate was 89.0%, and the 3-year overall survival rate was 95.9%. At 1 year after surgery, 10 cases (10.5%, 10/95) had severe anal dysfunction, and the median LARS score of the entire group was 5.0 (range: 0-41.0) points. Conclusions:For patients with locally advanced low rectal cancer who achieve cCR or near-cCR after neoadjuvant therapy, local excision results in favorable oncological prognosis and anal function preservation effects; however, the incidence of complications is relatively high.

In recent years, generative artificial intelligence (AI) technologies have achieved remarkable progress in the early screening, risk prediction, disease progression assessment, and clinical trial design of glaucoma.Using advanced algorithms, such as generative adversarial networks, variational autoencoders, and diffusion models, researchers have synthesized high-quality structural images of the optic disc, macular region, and retinal nerve fiber layer, which effectively alleviates the limitations of scarce clinical imaging data and label imbalance.These methods have substantially improved the accuracy and generalization of deep learning models in visual field defect prediction, structure-function mapping, and longitudinal disease progression simulation.Meanwhile, multimodal generative approaches that integrate imaging data, visual field tests, and clinical features have facilitated individualized prediction of glaucoma progression.In addition, large language models have shown preliminary potential in ophthalmic image interpretation, clinical text information extraction, and decision support, providing new insights into intelligent ophthalmic diagnosis and treatment.However, the clinical implementation of generative AI in glaucoma faces challenges.The pathological authenticity and cross-device consistency of generated images require further validation, which may affect the reliability of early glaucoma detection.The heterogeneous characteristics of different glaucoma subtypes, such as open-angle and angle-closure glaucoma, also limit the generalization of synthetic data.Moreover, issues related to model interpretability (" black-box" nature), artifact generation, data privacy, and ethical governance remain key barriers to clinical translation.In the future, it is expected that establishing large-scale training frameworks that incorporate multicenter, multimodal, and multiethnic datasets will enhance model robustness and clinical applicability.Furthermore, generative AI may contribute to remote ophthalmic care and personalized precision therapy by enhancing low-quality image, reconstructing missing data, and simulating dynamic disease courses.This article reviews the current applications, core technologies, and challenges of generative AI in glaucoma diagnosis and management, and discusses its future directions and translational potential in clinical ophthalmology.

Objective:To evaluate the short-term and long-term outcomes of patients with locally advanced low rectal cancer who achieved clinical complete response (cCR) or near-clinical complete response (near-cCR) after neoadjuvant chemoradiotherapy (nCRT) and then underwent local excision.Methods:This was a descriptive case series study. Clinical data of patients with low rectal cancer who received neoadjuvant therapy, achieved cCR or near-cCR, underwent local excision, and had complete postoperative follow-up data were retrospectively analyzed. The study period was from May, 2015 to October, 2024, and the patients were treated at Fujian Medical University Union Hospital. Indications for local excision in this study were as follows: pathologically confirmed rectal adenocarcinoma, with the lower edge of the tumor ≤ 6 cm from the anal verge; maximum diameter of the lesion ≤ 2 cm after nCRT; no regional lymph node metastasis detected by transrectal endoscopic ultrasound (ERUS), pelvic magnetic resonance imaging (MRI), or positron emission tomography-computed tomography (PET-CT) after nCRT; MRI showing fibrosis of the primary lesion with a small amount of high signal on diffusion-weighted imaging (DWI), consistent with ymrT0-1 stage; serum carcinoembryonic antigen level within the normal range (< 5 μg/L) after nCRT; complicated with severe underlying diseases such as cardiovascular and cerebrovascular diseases and assessed as unable to tolerate radical surgery through comprehensive evaluation; and signed informed consent for local excision. The contraindications were: colonoscopic pathology indicating poorly differentiated adenocarcinoma or signet ring cell carcinoma; suspected lateral lymph node metastasis before neoadjuvant therapy; patients with residual lesions exceeding 3 cm in range after treatment. A total of 153 patients were included in this study, including 84 males and 69 females. The median age was 62 years, and the median distance from the tumor to the anal verge after neoadjuvant therapy was 4.0 cm. The short-term efficacy indicators of this study included postoperative complications of local excision and postoperative pathological results, and the long-term efficacy indicators included oncological prognosis (3-year cumulative local recurrence rate, 3-year cumulative distant metastasis rate, 3-year progression-free survival, and 3-year overall survival) and anal function at 1 year after surgery evaluated using the Low Anterior Resection Syndrome (LARS) scale where the total score is 42 points such that 0-20 points indicate no LARS, 21-29 points indicate mild LARS, and 30-42 points indicate severe LARS.Results:Postoperative pathology showed 122 cases (79.7%) of ypT0 stage, 10 cases (6.5%) of ypT1 stage, 18 cases (11.8%) of ypT2 stage, and 3 cases (2.0%) of ypT3 stage. The incidence of surgery-related complications was 42.5% (65/153), and the main complications included perianal pain (39.9%, 61/153), intestinal wall incision dehiscence (21.6%, 33/153), and intestinal wall incision infection (18.3%, 28/153). The proportion of patients who received hypofractionated radiotherapy before surgery and developed intestinal wall incision dehiscence was 65.2% (15/23), which was higher than that in the conventional long-course (13.6%, 16/118) and short-course radiotherapy groups (16.7%,2/12) (χ 2=30.55, P<0.001); of the 20 patients who received additional immunotherapy before surgery, 13 developed intestinal wall incision dehiscence was 65.0%, which was higher than that in the group without additional immunotherapy [15.0%(20/133),χ 2=25.66, P<0.001]. The median follow-up time of the entire group was 35.4 months. During the follow-up period, there were 9 cases of postoperative local recurrence, with a 3-year cumulative local recurrence rate of 7.9% and 5 cases of distant metastasis, with a 3-year cumulative distant metastasis rate of 5.0%. The 3-year progression-free survival rate was 89.0%, and the 3-year overall survival rate was 95.9%. At 1 year after surgery, 10 cases (10.5%, 10/95) had severe anal dysfunction, and the median LARS score of the entire group was 5.0 (range: 0-41.0) points. Conclusions:For patients with locally advanced low rectal cancer who achieve cCR or near-cCR after neoadjuvant therapy, local excision results in favorable oncological prognosis and anal function preservation effects; however, the incidence of complications is relatively high.