Uveal melanoma distant metastasis prediction system: A retrospective observational study based on machine learning.

Uveal melanoma (UM) patients face a significant risk of distant metastasis, closely tied to a poor prognosis. Despite this, there is a dearth of research utilizing big data to predict UM distant metastasis. This study leveraged machine learning methods on the Surveillance, Epidemiology, and End Results (SEER) database to forecast the risk probability of distant metastasis. Therefore, the information on UM patients from the SEER database (2000-2020) was split into a 7:3 ratio training set and an internal test set based on distant metastasis presence. Univariate and multivariate logistic regression analyses assessed distant metastasis risk factors. Six machine learning methods constructed a predictive model post-feature variable selection. The model evaluation identified the multilayer perceptron (MLP) as optimal. Shapley additive explanations (SHAP) interpreted the chosen model. A web-based calculator personalized risk probabilities for UM patients. The results show that nine feature variables contributed to the machine learning model. The MLP model demonstrated superior predictive accuracy (Precision = 0.788; ROC AUC = 0.876; PR AUC = 0.788). Grade recode, age, primary site, time from diagnosis to treatment initiation, and total number of malignant tumors were identified as distant metastasis risk factors. Diagnostic method, laterality, rural-urban continuum code, and radiation recode emerged as protective factors. The developed web calculator utilizes the MLP model for personalized risk assessments. In conclusion, the MLP machine learning model emerges as the optimal tool for predicting distant metastasis in UM patients. This model facilitates personalized risk assessments, empowering early and tailored treatment strategies.

Berberine ameliorate inflammation and apoptosis via modulating PI3K/AKT/NFκB and MAPK pathway on dry eye.

BACKGROUND: Dry eye disease (DED) is a multifactorial disease in ocular surface, and inflammation plays an etiological role. Berberine (BBR) has shown efficacy in treating inflammatory diseases. Yet, there was no adequate information related to the therapeutic effects of BBR for DED. PURPOSE: To detect the effects and explore the potential mechanisms of BBR on DED. STUDY DESIGN: In vitro, in vivo study and network pharmacology analysis were involved. METHOD: The human corneal epithelium cells viability was evaluated with different concentrations of BBR. Dry eye murine model was established by exposing to the desiccating stress, and Ciclosporin (CSA), BBR eye drops or vehicle were topical administration for 7 days. The phenol red cotton tests, Oregon-green-dextran staining and Periodic acid-Schiff staining were performed and evaluated the dry eye after treatment. Inflammation and apoptosis levels of ocular surface were quantified. The potential targets related to berberine and dry eye were collected from databases. The Protein-Protein interaction network analysis and GO & KEGG enrichment analysis were realized by STRING database, Metascape platform and Cytoscape software to find core targets and signaling pathways. The SchrÖdinger software was used to molecular docking and PyMOL software to visualization. Finally, the levels of PI3K/AKT/NFκB and MAPK pathways were detected. RESULT: The data revealed BBR could rescue impaired HCE under hyperosmotic conditions. In addition, BBR eye drops could ameliorate dry eye. And BBR eye drops suppressed the inflammatory factors and CD4+T cells infiltration in conjunctiva. Besides, BBR eye drops protected ocular surface by avoiding the severe apoptosis and decreasing the level of MMP-3 and MMP-9. 148 common targets intersection between BBR and dry eye were found via network pharmacology analysis. Core proteins and core pathways were identified through PPI and GO&KEGG enrichment analysis. Molecular docking displayed excellent binding between BBR and those core targets. Finally, in vivo study verified that BBR eye drops had a therapeutic effect in dry eye by inhibiting PI3K/AKT/NFκB and MAPK pathways. CONCLUSION: The research provided convincing evidence that BBR could be a candidate drug for dry eye.

AES-CSFS: an automatic evaluation system for corneal sodium fluorescein staining based on deep learning.

Background: Corneal fluorescein sodium staining is a valuable diagnostic method for various ocular surface diseases. However, the examination results are highly dependent on the subjective experience of ophthalmologists. Objectives: To develop an artificial intelligence system based on deep learning to provide an accurate quantitative assessment of sodium fluorescein staining score and the size of cornea epithelial patchy defect. Design: A prospective study. Methods: We proposed an artificial intelligence system for automatically evaluating corneal staining scores and accurately measuring patchy corneal epithelial defects based on corneal fluorescein sodium staining images. The design incorporates two segmentation models and a classification model to forecast and assess the stained images. Meanwhile, we compare the evaluation findings from the system with ophthalmologists with varying expertise. Results: For the segmentation task of cornea boundary and cornea epithelial patchy defect area, our proposed method can achieve the performance of dice similarity coefficient (DSC) is 0.98/0.97 and Hausdorff distance (HD) is 3.60/8.39, respectively, when compared with the manually labeled gold standard. This method significantly outperforms the four leading algorithms (Unet, Unet++, Swin-Unet, and TransUnet). For the classification task, our algorithm achieves the best performance in accuracy, recall, and F1-score, which are 91.2%, 78.6%, and 79.2%, respectively. The performance of our developed system exceeds seven different approaches (Inception, ShuffleNet, Xception, EfficientNet_B7, DenseNet, ResNet, and VIT) in classification tasks. In addition, three ophthalmologists were selected to rate corneal staining images. The results showed that the performance of our artificial intelligence system significantly outperformed the junior doctors. Conclusion: The system offers a promising automated assessment method for corneal fluorescein staining, decreasing incorrect evaluations caused by ophthalmologists' subjective variance and limited knowledge.

Fenofibrate suppresses corneal neovascularization by regulating lipid metabolism through PPARα signaling pathway.

Purpose: The purpose of this study was to explore the potential underlying mechanism of anti-vascular effects of peroxisome proliferator-activated receptor α (PPARα) agonist fenofibrate against corneal neovascularization (CNV) through the changes of lipid metabolism during CNV. Methods: A suture-induced CNV model was established and the clinical indications were evaluated from day 1 to day 7. Treatments of vehicle and fenofibrate were performed for 5 days after suture and the CNV areas were compared among the groups. The eyeballs were collected for histological analysis, malondialdehyde (MDA) measurement, terminal deoxynucleotidyl transferase 2'-deoxyuridine 5'-triphosphate nick end labeling (TUNEL) staining, western blot, quantitative real-time PCR (qRT-PCR) assays and immunohistochemical (IHC) staining to elucidate pathological changes and the underlying mechanism. Results: Lipi-Green staining and MDA measurement showed that lipid deposition and peroxidation were increased in the CNV cornea while the expression of long-chain acyl-coenzyme A synthetase 1 (ACSL1), carnitine palmitoyltransterase 1A(CPT1A) and medium-chain acyl-coenzyme A dehydrogenase (ACADM), which are key enzymes of fatty acid ß-oxidation (FAO) and targeted genes of peroxisome proliferator-activated receptor alpha (PPARα) pathway, were decreased in CNV cornea. Fenofibrate suppressed lipid accumulation and peroxidation damage in the CNV cornea. Fenofibrate upregulated the expression levels of PPARα, ACSL1, CPT1A, and ACADM compared with vehicle group. IHC staining indicated that fenofibrate also decreased the expression of VEGFa, VEGFc, TNFα, IL1ß and CD68. Conclusion: Disorder of lipid metabolism may be involved in the formation of suture-induced CNV and fenofibrate played anti-neovascularization and anti-inflammatory roles on cornea by regulating the key enzymes of lipid metabolism and ameliorating lipid peroxidation damage of cornea through PPARα signaling pathway.