An interpretable model predicts visual outcomes of no light perception eyes after open globe injury.

BACKGROUND: The visual outcome of open globe injury (OGI)-no light perception (NLP) eyes is unpredictable traditionally. This study aimed to develop a model to predict the visual outcomes of vitrectomy surgery in OGI-NLP eyes using a machine learning algorithm and to provide an interpretable system for the prediction results. METHODS: Clinical data of 459 OGI-NLP eyes were retrospectively collected from 19 medical centres across China to establish a training data set for developing a model, called 'VisionGo', which can predict the visual outcome of the patients involved and compare with the Ocular Trauma Score (OTS). Another 72 cases were retrospectively collected and used for human-machine comparison, and an additional 27 cases were prospectively collected for real-world validation of the model. The SHapley Additive exPlanations method was applied to analyse feature contribution to the model. An online platform was built for real-world application. RESULTS: The area under the receiver operating characteristic curve (AUC) of VisionGo was 0.75 and 0.90 in previtrectomy and intravitrectomy application scenarios, which was much higher than the OTS (AUC=0.49). VisionGo showed better performance than ophthalmologists in both previtrectomy and intravitrectomy application scenarios (AUC=0.73 vs 0.57 and 0.87 vs 0.64). In real-world validation, VisionGo achieved an AUC of 0.60 and 0.91 in previtrectomy and intravitrectomy application scenarios. Feature contribution analysis indicated that wound length-related indicators, vitreous status and retina-related indicators contributed highly to visual outcomes. CONCLUSIONS: VisionGo has achieved an accurate and reliable prediction in visual outcome after vitrectomy for OGI-NLP eyes.

Application Research of Artificial Intelligence Screening System for Diabetic Retinopathy.

According to the latest data from the Bureau of Disease Control and Prevention of the National Health and Family Planning Commission, China currently has 199.6 million diabetic patients and has become the world's largest country with diabetes. The prevalence rate is as high as 14.3%, which is much higher than the world average of 5.8%. The primary-level ophthalmic screening service is one of the important tasks to improve primary-level medical services, and the corresponding ophthalmic imaging diagnosis technology is an important support for primary-level medical and health services. Therefore, it is very necessary for us to study the application of artificial intelligence image recognition technology for diabetic retinopathy under the medical consortium mode and to study the precise initial diagnosis, precise referral, and precise follow-up of diabetic retina under the medical conjoined mode, so as to better promote the transformation of the ophthalmology primary service model. Based on this background, in this article, we have proposed and carried out the following solution: (1) diabetes data collation. Based on medical artificial intelligence technology, this paper collected 2,265 electronic medical records from an eye hospital in Ningbo and selected 2,000 qualified medical records for data integration and preprocessing. The contents of electronic medical records mainly include age, gender, and examination records. (2) Establish diabetic retinopathy diagnosis model based on neural network algorithm. This article first uses the classic algorithm of BP neural network for modeling, chooses the Levenberg-Marquardt method as the training function, and selects 10 hidden layer units through comparison experiments. After that, ophthalmologists assessed 80 sets of test results and determined the right diagnosis rate. Finally, this article compares and analyzes the accuracy of the two routes in 80 tests.

Development of a deep learning-based image eligibility verification system for detecting and filtering out ineligible fundus images: A multicentre study.

BACKGROUND: Recent advances in artificial intelligence (AI) have shown great promise in detecting some diseases based on medical images. Most studies developed AI diagnostic systems only using eligible images. However, in real-world settings, ineligible images (including poor-quality and poor-location images) that can compromise downstream analysis are inevitable, leading to uncertainty about the performance of these AI systems. This study aims to develop a deep learning-based image eligibility verification system (DLIEVS) for detecting and filtering out ineligible fundus images. METHODS: A total of 18,031 fundus images (9,188 subjects) collected from 4 clinical centres were used to develop and evaluate the DLIEVS for detecting eligible, poor-location, and poor-quality fundus images. Four deep learning algorithms (AlexNet, DenseNet121, Inception V3, and ResNet50) were leveraged to train models to obtain the best model for the DLIEVS. The performance of the DLIEVS was evaluated using the area under the receiver operating characteristic curve (AUC), sensitivity, and specificity, as compared with a reference standard determined by retina experts. RESULTS: In the internal test dataset, the best algorithm (DenseNet121) achieved AUCs of 1.000, 0.999, and 1.000 for the classification of eligible, poor-location, and poor-quality images, respectively. In the external test datasets, the AUCs of the best algorithm (DenseNet121) for detecting eligible, poor-location, and poor-quality images were ranged from 0.999-1.000, 0.997-1.000, and 0.997-0.999, respectively. CONCLUSIONS: Our DLIEVS can accurately discriminate poor-quality and poor-location images from eligible images. This system has the potential to serve as a pre-screening technique to filter out ineligible images obtained from real-world settings, ensuring only eligible images will be applied in the subsequent image-based AI diagnostic analyses.

Risk Factors for Band Keratopathy in Aphakic Eyes With Silicone Oil Tamponade for Open-Globe Injuries: A Multicenter Case-Control Study.

Band keratopathy (BK) is a common complication in aphakic eyes with silicone oil tamponade for open-globe injury (OGI), characterized by the grayish-white opacities in the cornea, resulting in a significantly decreased vision when extending to the visual axis. To identify the risk factors for BK in aphakic eyes following vitreoretinal surgical treatment with silicone oil tamponade for OGIs, we performed a multicenter case-control study. The incidence of BK was 28% (28/100 eyes). The multivariate binary logistic regression revealed the silicone oil retention time (SORT) ≥6 months and zone III injury were significant risk factors for BK. From the hierarchical interaction, SORT ≥6 months had a significant risk for BK in eyes with rupture, aniridia, and zone III injury, while zone III injury had a significant risk for BK in eyes with rupture, incomplete/complete iris, and SORT ≥6 months. By using restricted cubic splines with three knots at the 25th, 50th, and 75th centiles to model the association of SORT with BK, we also found a marked increase in the risk for BK at ≥10 months and a slow increase after 6 months, but almost stable within 4-6 months.

MiR-181a inhibits human trabecular meshwork cell apoptosis induced by H2O2 through the suppression of NF-κB and JNK pathways.

BACKGROUND: The trabecular meshwork (TM) plays a critical role in the outflow of aqueous humor. OBJECTIVES: In this study, we aimed to investigate the effect of miR-181a on H2O2-induced apoptosis in TM cells. MATERIAL AND METHODS: Human primary explant-derived TM cells were cultured in fibroblast medium and then treated with different concentrations of H2O2 for 2 h. We used a series of methods to carry out the research, such as MTT assay, quantitative reverse transcriptase-polymerase chain reaction (qRT-PCR), apoptosis assay, and western blot methodology. RESULTS: The apoptosis assay and qRT-PCR showed that H2O2-induced apoptosis and cell viability were suppressed in a dose-dependent manner in TM cells. After the TM cells were treated with H2O2, miR-181a expression was significantly lower. The overexpression of miR-181a enhanced TM cells' viability, while the knockdown of miR-181a inhibited viability of cells. The overexpression of miR-181a suppressed TM cell apoptosis, while the knockdown of miR-181a induced apoptosis. H2O2 activated the nuclear factor-κB (NF-κB) and c-Jun N-terminal kinase (JNK) pathways and induced cell apoptosis, while the overexpression of miR-181a suppressed both pathways and decreased the rate of apoptosis. CONCLUSIONS: In conclusion, this study indicated that miR-181a could improve the survival rate of TM cells after H2O2 treatment by blocking the NF-κB and JNK signaling pathways. These findings might provide novel therapeutic opportunities in the treatment of glaucoma.