Machine learning regression algorithms to predict short-term efficacy after anti-VEGF treatment in diabetic macular edema based on real-world data.

The objective of this retrospective study was to predict short-term efficacy of anti-vascular endothelial growth factor (VEGF) treatment in diabetic macular edema (DME) using machine learning regression models. Real-world data from 279 DME patients who received anti-VEGF treatment at Ineye Hospital of Chengdu University of TCM between April 2017 and November 2022 were analyzed. Eight machine learning regression models were established to predict four clinical efficacy indicators. The accuracy of the models was evaluated using mean absolute error (MAE), mean square error (MSE) and coefficient of determination score (R2). Multilayer perceptron had the highest R2 and lowest MAE among all models. Regression tree and lasso regression had similar R2, with lasso having lower MAE and MSE. Ridge regression, linear regression, support vector machines and polynomial regression had lower R2 and higher MAE. Support vector machine had the lowest MSE, while polynomial regression had the highest MSE. Stochastic gradient descent had the lowest R2 and high MAE and MSE. The results indicate that machine learning regression algorithms are valuable and effective in predicting short-term efficacy in DME patients through anti-VEGF treatment, and the lasso regression is the most effective ML algorithm for developing predictive regression models.

Noninvasive Evaluation of GIP Effects on ß-Cell Mass Under High-Fat Diet.

Pancreatic ß-cell mass (BCM) has an importance in the pathophysiology of diabetes mellitus. Recently, glucagon-like peptide-1 receptor (GLP-1R)-targeted imaging has emerged as a promising tool for BCM evaluation. While glucose-dependent insulinotropic polypeptide/gastric inhibitory polypeptide (GIP) is known to be involved in high-fat diet (HFD)-induced obesity, the effect of GIP on BCM is still controversial. In this study, we investigated indium 111 (111In)-labeled exendin-4 derivative ([Lys12(111In-BnDTPA-Ahx)]exendin-4) single-photon emission computed tomography/computed tomography (SPECT/CT) as a tool for evaluation of longitudinal BCM changes in HFD-induced obese mice, at the same time we also investigated the effects of GIP on BCM in response to HFD using GIP-knockout (GIP-/-) mice. 111In-exendin-4 SPECT/CT was able to distinguish control-fat diet (CFD)-fed mice from HFD-fed mice and the pancreatic uptake values replicated the BCM measured by conventional histological methods. Furthermore, BCM expansions in HFD-fed mice were demonstrated by time-course changes of the pancreatic uptake values. Additionally, 111In-exendin-4 SPECT/CT demonstrated the distinct changes in BCM between HFD-fed GIP-/- (GIP-/-+HFD) and wild-type (WT+HFD) mice; the pancreatic uptake values of GIP-/-+HFD mice became significantly lower than those of WT+HFD mice. The different changes in the pancreatic uptake values between the two groups preceded those in fat accumulation and insulin resistance. Taken together with the finding of increased ß-cell apoptosis in GIP-/-+HFD mice compared with WT+HFD mice, these data indicated that GIP has preferable effects on BCM under HFD. Therefore, 111In-exendin-4 SPECT/CT can be useful for evaluating increasing BCM and the role of GIP in BCM changes under HFD conditions.

The effectiveness of AGV, Ex-PRESS, or trabeculectomy in the treatment of primary and secondary glaucoma: a systematic review and network meta-analysis.

BACKGROUND: In this study, we compared the efficacy of Ahmed, Ex-PRESS, and trabeculectomy to provide a reference for determining surgical schemes for glaucoma patients undergoing external drainage surgery in clinical practice. METHODS: We performed a literature search for studies on the treatment of primary and secondary glaucoma with three types of external drainage surgery (Ahmed, Ex-PRESS, and trabeculectomy). As at April 24, 2021, seven electronic databases were searched for randomized controlled trials comparing any two of Ahmed, Ex-PRESS, and trabeculectomy in the treatment of glaucoma. The Cochrane tool was also adopted to evaluate the risk of bias in these trials. The relative risk (RR) with 95% confidence interval (CI), and weighted mean difference (WMD) were determined and compared indirectly using R software. RESULTS: A total of 14 randomized controlled trials were included in this study, involving 866 eyes of 808 patients. As for the intraocular pressure (IOP) after 3 months, trabeculectomy did not contribute to better improvement than Ahmed (WMD =0.014; 95% CI: -0.14-0.18) and Ex-PRESS (WMD =0.014; 95% CI: -0.072-0.097). However, there was a significant difference in the IOP 1 year between trabeculectomy and Ex-PRESS (WMD =0.097; 95% CI: 0.0080-0.18), with the latter achieving a favorable improvement effect. Meanwhile, the complete success (CS) of trabeculectomy was significantly lower than that of Ex-PRESS (RR =0.73; 95% CI: 0.57-0.93). In addition, Ex-PRESS was superior to Ahmed (WMD =-0.48; 95% CI: -0.89 to -0.084) in terms of a decreased number of post-operative medications. DISCUSSION: For glaucoma patients who are required to receive external drainage surgery, Ex-PRESS could achieve a significant effect on the IOP 1 year and CS, as well as a marked decrease in the number of post-operative medications used, compared with the other two types of surgery. In terms of the efficacy at least 1 year after surgery, Ex-PRESS should be one of the preferred methods for external drainage.

EphA2 as a new target for breast cancer and its potential clinical application.

PURPOSE: The aim of this research was to study the expression of EphA2 to assess its suitability as a new breast cancer target. METHODS: Immunohistochemistry (IHC) was used to detect EphA2 protein expression in pathology tissue samples from 250 cases of breast cancer, and the expression of EphA2 mRNA was detected by in situ hybridization (ISH). Breast cancer cells were isolated and cultured. The expression of EphA2 in the cells was detected by the indirect immunofluorescence assay (IFA), and the expression of EphA2 in breast cancer was analysed. RESULTS: EphA2 protein and mRNA were mainly expressed in tumor cells and vascular endothelial cells. EphA2 protein was expressed in 187 cases, with a positive rate of 74.80%, whereas EphA2 mRNA was expressed in 209 cases, with a positive rate of 83.60%. EphA2 protein and mRNA expression were correlated with lymph node metastasis, clinical stage, and breast cancer histologic grade (P<0.05). In addition, the positive expression rates of EphA2 protein and EphA2 mRNA were correlated (P<0.05). EphA2 was barely expressed in normal breast cells but highly expressed in breast cancer cells. CONCLUSION: EphA2 is highly expressed in breast cancer tissues and has the potential to be a new breast cancer target, providing a preliminary basis for the development of new targeted drugs for breast cancer and the construction of fluorescent-targeted tracers for fluorescence-guided mastoscopic breast-conserving surgery.

Screening and identification of key biomarkers for retinoblastoma: Evidence from bioinformatics analysis.

BACKGROUND: Retinoblastoma (RB) is one of the most common malignant tumors in pediatrics; to clarify the cause of RB, a lot of manpower and material resources have been invested but have not been well explained. METHODS: To identify the candidate genes in the occurrence and development of the disease, we downloaded the microarray datasets GSE97508, GSE92987, and GSE24673 from the gene expression database (GEO). The differentially expressed gene (DEG) was identified and functional enrichment analysis was performed. The protein-protein interaction network was constructed and analyzed by String and Cytoscape. RESULTS: A total of 74 DEGs were identified, including 40 up-regulated genes and 34 down-regulated genes. The rich functions and pathways of DEG include regulating mitosis, cell cycle, DNA transcription process, promoting protein phosphorylation, regulating energy metabolism in vivo, promoting the binding of some macromolecular complexes, and regulating the cell cycle. Twenty-four HUB genes were identified. Biological process analysis showed that these genes were mainly enriched in regulating energy metabolism in vivo, promoting the binding of some small molecules and regulating the cell cycle. Survival analysis showed that DGPDC1, NDC80, SHCBP, TOP2A, and DLGAP5 may be involved in the occurrence, invasion, or recurrence of RB. CONCLUSION: In conclusion, screening DEGs and HUB genes in RB can help us to better understand the mechanism of the occurrence and development of RB at the molecular level, and provide candidate targets for the diagnosis and treatment of RB.

Simultaneous Recordings of Cortical Local Field Potentials and Electrocorticograms in Response to Nociceptive Laser Stimuli from Freely Moving Rats.

Electrocortical responses, elicited by laser heat pulses that selectively activate nociceptive free nerve endings, are widely used in many animal and human studies to investigate the cortical processing of nociceptive information. These laser-evoked brain potentials (LEPs) consist of several transient responses that are time-locked to the onset of laser stimuli. However, the functional properties of the LEP responses are still largely unknown, due to the lack of a sampling technique that can simultaneously record neural activities at the surface of the cortex (i.e., electrocorticogram [ECoG] and scalp electroencephalogram [scalp EEG]) and inside the brain (i.e., local field potential [LFP]). To address this issue, we present here an animal protocol using freely moving rats. This protocol is composed of three main procedures: (1) animal preparation and surgical procedures, (2) a simultaneous recording of ECoG and LFP in response to nociceptive laser stimuli, and (3) data analysis and feature extraction. Specifically, with the help of a 3D-printed protective shell, both ECoG and LFP electrodes implanted on the rat's skull were securely held together. During data collection, laser pulses were delivered on the rat's forepaws through gaps in the bottom of the chamber when the animal was in spontaneous stillness. Ongoing white noise was played to avoid the activation of the auditory system by the laser-generated ultrasounds. As a consequence, only nociceptive responses were selectively recorded. Using the standard analytical procedures (e.g., band-pass filtering, epoch extraction, and baseline correction) to extract stimulus-related brain responses, we obtained results showing that LEPs with a high signal-to-noise ratio were simultaneously recorded from ECoG and LFP electrodes. This methodology makes the simultaneous recording of ECoG and LFP activities possible, which provides a bridge of electrocortical signals at the mesoscopic and macroscopic levels, thereby facilitating the investigation of nociceptive information processing in the brain.