Analysis of m6A-related lncRNAs for prognostic and immunotherapeutic response in hepatocellular carcinoma.

Background: RNA methylation modifications are important post-translational modifications that are regulated in an epigenetic manner. Recently, N6-methyladenosine (m6A) RNA modifications have emerged as potential epigenetic markers in tumor biology. Methods: Gene expression and clinicopathological data of LIHC were obtained from the cancer genome atlas (TCGA) database. The relationship between long non-coding RNAs (lncRNAs) and m6A-related genes was determined by gene expression analysis using Perl and R software. Co-expression network of m6A-lncRNA was constructed, and the relevant lncRNAs associated with prognosis were identified using univariate Cox regression analysis. These lncRNAs were then divided into two clusters (cluster 1 and cluster 2) to determine the differences in survival, pathoclinical parameters, and immune cell infiltration between the different lncRNA subtypes. The least absolute shrinkage and selection operator (LASSO) was carried out for regression analysis and prognostic model. The HCC patients were randomly divided into a train group and a test group. According to the median risk score of the model, HCC patients were divided into high-risk and low-risk groups. We built models using the train group and confirmed them through the test group. The m6A-lncRNAs derived from the models were analyzed for the tumor mutational burden (TMB), immune evasion and immune function using R software. AL355574.1 was identified as an important m6A-associated lncRNA and selected for further investigation. Finally, in vitro experiments were conducted to confirm the effect of AL355574.1 on the biological function of HCC and the possible biological mechanisms. Huh7 and HepG2 cells were transfected with AL355574.1 siRNA and cell proliferation ability was measured by CCK-8, EdU and colony formation assays. Wound healing and transwell assays were used to determine the cell migration capacity. The expression levels of MMP-2, MMP-9, E-cadherin, N-cadherin and Akt/mTOR phosphorylation were all determined by Western blotting. Results: The lncRNAs with significant prognostic value were classified into two subtypes by a consistent clustering analysis. We found that the clinical features, immune cell infiltration and tumor microenvironment (TME) were significantly different between the lncRNA subtypes. Our analysis revealed significant correlations between these different lncRNA subtypes and immune infiltrating and stromal cells. We created the final risk profile using LASSO regression, which notably included three lncRNAs (AL355574.1, AL158166.1, TMCC1-AS1). A prognostic signature consisting of the three lncRNAs was constructed, and the model showed excellent prognostic predictive ability. The overall survival (OS) of the low-risk cohort was significantly higher than that of the high-risk cohort in both the train and test group. Both risk score [hazard ratio (HR)=1.062; P<0.001] and stage (HR=1.647; P< 0.001) were considered independent indicators of HCC prognosis by univariate and multivariate Cox regression analysis. In Huh7 and HepG2 cells, AL355574.1 knockdown inhibited cell proliferation and migration, suppressed the protein expression levels of MMP-2, MMP-9, N-cadherin and Akt/mTOR phosphorylation, but promoted the protein expression levels of E-cadherin. Conclusions: This study established a predictive model for the OS of HCC patients, and these OS-related m6A-lncRNAs, especially AL355574.1 may play a potential role in the progression of HCC. In vitro experiments also showed that AL355574.1 could enhance the expression of MMPs and EMT through the Akt/mTOR signaling pathway, thereby affected the proliferation and migration of HCC. This provides a new perspective on the anticancer molecular mechanism of AL355574.1 in HCC.

m6A-Mediated Upregulation of lncRNA CHASERR Promotes the Progression of Glioma by Modulating the miR-6893-3p/TRIM14 Axis.

Long noncoding RNAs (lncRNAs) play crucial roles in tumor progression and are dysregulated in glioma. However, the functional roles of lncRNAs in glioma remain largely unknown. In this study, we utilized the TCGA (the Cancer Genome Atlas database) and GEPIA2 (Gene Expression Profiling Interactive Analysis 2) databases and observed the overexpression of lncRNA CHASERR in glioma tissues. We subsequently investigated this phenomenon in glioma cell lines. The effects of lncRNA CHASERR on glioma proliferation, migration, and invasion were analyzed using in vitro and in vivo experiments. Additionally, the regulatory mechanisms among PTEN/p-Akt/mTOR and Wnt/ß-catenin, lncRNA CHASERR, Micro-RNA-6893-3p(miR-6893-3p), and tripartite motif containing14 (TRIM14) were investigated via bioinformatics analyses, quantitative real-time PCR (qRT-PCR), western blot (WB), RNA immunoprecipitation (RIP), dual luciferase reporter assay, fluorescence in situ hybridization (FISH), and RNA sequencing assays. RIP and RT-qRCR were used to analyze the regulatory effect of N6-methyladenosine(m6A) on the aberrantly expressed lncRNA CHASERR. High lncRNA CHASERR expression was observed in glioma tissues and was associated with unfavorable prognosis in glioma patients. Further functional assays showed that lncRNA CHASERR regulates glioma growth and metastasis in vitro and in vivo. Mechanistically, lncRNA CHASERR sponged miR-6893-3p to upregulate TRIM14 expression, thereby facilitating glioma progression. Additionally, the activation of PTEN/p-Akt/mTOR and Wnt/ß-catenin pathways by lncRNA CHASERR, miR-6893-3p, and TRIM14 was found to regulate glioma progression. Moreover, the upregulation of lncRNA CHASERR was observed in response to N6-methyladenosine modification, which was facilitated by METTL3/YTHDF1-mediated RNA transcripts. This study elucidates the m6A/lncRNACHASERR/miR-6893-3p/TRIM14 pathway that contributes to glioma progression and underscores the potential of lncRNA CHASERR as a novel prognostic indicator and therapeutic target for glioma.

Systematic analysis of the role of LDHs subtype in pan-cancer demonstrates the importance of LDHD in the prognosis of hepatocellular carcinoma patients.

BACKGROUND: Lactate dehydrogenase (LDHs) is an enzyme involved in anaerobic glycolysis, including LDHA, LDHB, LDHC and LDHD. Given the regulatory role in the biological progression of certain tumors, we analyzed the role of LDHs in pan-cancers. METHODS: Cox regression, Kaplan-Meier curves, Receiver Operating Characteristic (ROC) curves, and correlation of clinical indicators in tumor patients were used to assess the prognostic significance of LDHs in pan-cancer. The TCGA, HPA, TIMER, UALCAN, TISIDB, and Cellminer databases were used to investigate the correlation between the expression of LDHs and immune subtypes, immune checkpoint genes, methylation levels, tumor mutational load, microsatellite instability, tumor-infiltrating immune cells and drug sensitivity. The cBioPortal database was also used to identify genomic abnormalities of LDHs in pan-cancer. A comprehensive assessment of the biological functions of LDHs was performed using GSEA. In vitro, HepG2 and Huh7 cells were transfected with LDHD siRNA and GFP-LDHD, the proliferation capacity of cells was examined using CCK-8, EdU, and colony formation assays; the migration and invasion of cells was detected by wound healing and transwell assays; western blotting was used to detect the levels of MMP-2, MMP-9, E-cadherin, N-cadherin and Akt phosphorylation. RESULTS: LDHs were differentially expressed in a variety of human tumor tissues. LDHs subtypes can act as pro-oncogenes or anti-oncogenes in different types of cancer and have an impact on the prognosis of patients with tumors by influencing their clinicopathological characteristics. LDHs were differentially expressed in tumor immune subtypes and molecular subtypes. In addition, LDHs expression correlated with immune checkpoint genes, tumor mutational load, and microsatellite instability. LDHD was identified to play an important role in the prognosis of HCC patients, according to a comprehensive analysis of LDHs in pan-cancer. In HepG2 and Huh7 cells, knockdown of LDHD promoted cell proliferation, migration, and invasion, promoted the protein expression levels of MMP-2, MMP-9, N-cadherin, and Akt phosphorylation, but inhibited the protein expression level of E-cadherin. In addition, LDHD overexpression showed the opposite changes. CONCLUSION: LDHs subtypes can be used as potential prognostic markers for certain cancers. Prognostic and immunotherapeutic analysis indicated that LDHD plays an important role in the prognosis of HCC patients. In vitro experiments revealed that LDHD can affect HCC proliferation, migration, and invasion by regulating MMPs expression and EMT via Akt signaling pathway, which provides a new perspective on the anti-cancer molecular mechanism of LDHD in HCC.

Bioinformatics analysis identifies coagulation factor II receptor as a potential biomarker in stomach adenocarcinoma.

Coagulation factor 2 thrombin receptor (F2R), a member of the G protein-coupled receptor family, plays an important role in regulating blood clotting through protein hydrolytic cleavage mediated receptor activation. However, the underlying biological mechanisms by which F2R affects the development of gastric adenocarcinoma are not fully understood. This study aimed to systematically analyze the role of F2R in gastric adenocarcinoma. Stomach adenocarcinoma (STAD)-related gene microarray data and corresponding clinicopathological information were downloaded from the Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases. Differential expression genes (DEGs) associated with F2R were analyzed using Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), gene set enrichment analysis (GSEA), and protein-protein interaction (PPI) networks. F2R mRNA expression data were utilized to estimate stromal cell and immune cell scores in gastric cancer tissue samples, including stromal score, immune score, and ESTIMATE score, derived from single-sample enrichment studies. Analysis of TCGA and GEO databases revealed significantly higher F2R expression in STAD tissues compared to normal tissues. Patients with high F2R expression had shorter survival times than those with low F2R expression. F2R expression was significantly correlated with tumor (T) stage, node (N) stage, histological grade and pathological stage. Enrichment analysis of F2R-related genes showed that GO terms were mainly related to circulation-mediated human immune response, immunoglobulin, cell recognition and phagocytosis. KEGG analysis indicated associations to extracellular matrix (ECM) receptor interactions, neuroactive ligand-receptor interactions, the phosphoinositide-3-kinase-protein kinase B/Akt (PI3K-AKT) signaling pathway, the Wnt signaling pathway and the transforming growth factor-beta (TGF-ß) signaling pathway. GSEA revealed connections to DNA replication, the Janus kinase/signal transducers and activators of transcription (JAK-STAT) signaling pathway, the mitogen-activated protein kinase (MAPK) signaling pathway and oxidative phosphorylation. Drug sensitivity analysis demonstrated positive correlations between F2R and several drugs, including BEZ235, CGP-60474, Dasatinib, HG-6-64-1, Aazopanib, Rapamycin, Sunitinib and TGX221, while negative correlation with CP724714, FH535, GSK1904529A, JNK-9L, LY317615, pyrimidine, rTRAIL and Vinorelbine. Knocking down F2R in GC cell lines resulted in slowed proliferation, migration, and invasion. All statistical analyses were performed using R software (version 4.2.1) and GraphPad Prism 9.0. p < 0.05 was considered statistically significant. In conclusion, this study underscores the significance of F2R as a potential biomarker in gastric adenocarcinoma, shedding light on its molecular mechanisms in tumorigenesis. F2R holds promise for aiding in the diagnosis, prognosis, and targeted therapy of STAD.

Construction of an Early Alert System for Intradialytic Hypotension before Initiating Hemodialysis Based on Machine Learning.

Introduction: Intradialytic hypotension (IDH) is prevalent and associated with high hospitalization and mortality rates. The purpose of this study was to explore the risk factors for IDH and use artificial intelligence to establish an early alert system before hemodialysis sessions to identify patients at high risk of IDH. Materials and Methods: We obtained data on 314,534 hemodialysis sessions conducted at Sichuan Provincial People's Hospital from the renal disease treatment information system. IDH was defined as a systolic blood pressure drop ≥20 mm Hg, a mean arterial pressure drop ≥10 mm Hg during dialysis, or the occurrence of clinical hypotensive events requiring nursing intervention. After pre-processing, the data were randomly divided into training (80%) and testing (20%) sets. Four interpolation methods, three feature selection methods, and 18 machine learning algorithms were used to construct predictive models. The area under the receiver operating characteristic curve (AUC) was the main indicator for evaluating the performance of the models, while Shapley Additive ExPlanation was used to explain the contribution of each variable to the best predictive model. Results: A total of 3,906 patients and 314,534 dialysis sessions were included, of which 142,237 cases showed IDH (incidence rate, 45.2%). Nineteen parameters were identified through artificial intelligence feature screening. They included age, pre-dialysis weight, dry weight, pre-dialysis blood pressure, heart rate, prescribed ultrafiltration, blood cell counts (neutrophil, lymphocyte, monocyte, eosinophil, lymphocyte, and platelet counts), hematocrit, serum calcium, creatinine, urea, glucose, and uric acid. Random forest, gradient boosting, and logistic regression were the three best models, and the AUCs were 0.812 (95% confidence interval [CI], 0.811-0.813), 0.748 (95% CI, 0.747-0.749), and 0.743 (95% CI, 0.742-0.744), respectively. Conclusion: Our dialysis software-based artificial intelligence alert system can be used to predict IDH occurrence, enabling the initiation of relevant interventions.

Predicting three-month fasting blood glucose and glycated hemoglobin changes in patients with type 2 diabetes mellitus based on multiple machine learning algorithms.

Fasting blood glucose (FBG) and glycosylated hemoglobin (HbA1c) are key indicators reflecting blood glucose control in type 2 diabetes mellitus (T2DM) patients. The purpose of this study is to establish a predictive model for blood glucose changes in T2DM patients after 3 months of treatment, achieving personalized treatment.A retrospective study was conducted on type 2 diabetes mellitus real-world medical data from 4 cities in Sichuan Province, China from January 2015 to December 2020. After data preprocessing, data inputting, data sampling, and feature screening, 16 kinds of machine learning methods were used to construct prediction models, and 5 prediction models with the best prediction performance were screened respectively. A total of 100,000 cases were included to establish the FBG model, and 2,169 cases were established to establish the HbA1c model. The best prediction model both of FBG and HbA1c finally obtained are realized by ensemble learning and modified random forest inputting, the AUC values are 0.819 and 0.970, respectively. The most important indicators of the FBG and HbA1c prediction model were FBG and HbA1c. Medication compliance, follow-up outcome, dietary habits, BMI, and waist circumference also had a greater impact on FBG levels. The prediction accuracy of the models of the two blood glucose control indicators is high and has certain clinical applicability.HbA1c and FBG are mutually important predictors, and there is a close relationship between them.

Predicting 7-day unplanned readmission in elderly patients with coronary heart disease using machine learning.

Background: Short-term unplanned readmission is always neglected, especially for elderly patients with coronary heart disease (CHD). However, tools to predict unplanned readmission are lacking. This study aimed to establish the most effective predictive model for the unplanned 7-day readmission in elderly CHD patients using machine learning (ML) algorithms. Methods: The detailed clinical data of elderly CHD patients were collected retrospectively. Five ML algorithms, including extreme gradient boosting (XGB), random forest, multilayer perceptron, categorical boosting, and logistic regression, were used to establish predictive models. We used the area under the receiver operating characteristic curve (AUC), accuracy, precision, recall, the F1 value, the Brier score, the area under the precision-recall curve (AUPRC), and the calibration curve to evaluate the performance of ML models. The SHapley Additive exPlanations (SHAP) value was used to interpret the best model. Results: The final study included 834 elderly CHD patients, whose average age was 73.5 ± 8.4 years, among whom 426 (51.08%) were men and 139 had 7-day unplanned readmissions. The XGB model had the best performance, exhibiting the highest AUC (0.9729), accuracy (0.9173), F1 value (0.9134), and AUPRC (0.9766). The Brier score of the XGB model was 0.08. The calibration curve of the XGB model showed good performance. The SHAP method showed that fracture, hypertension, length of stay, aspirin, and D-dimer were the most important indicators for the risk of 7-day unplanned readmissions. The top 10 variables were used to build a compact XGB, which also showed good predictive performance. Conclusions: In this study, five ML algorithms were used to predict 7-day unplanned readmissions in elderly patients with CHD. The XGB model had the best predictive performance and potential clinical application perspective.

CLEC5A regulates the proliferation and migration of colon cancer via the AKT/mTOR signaling pathway.

Background: The purpose of this study is to understand the CLEC5A mechanism in colon cancer's proliferation and migration. Methods: The CLEC5A expression levels in colon cancer tissues were analyzed using bioinformatics method based on Oncomine and The Cancer Genome Atlas (TCGA) databases, which were further tested by immunohistochemistry (IHC) and quantitative real-time polymerase chain reaction (qRT-PCR). The CLEC5A expression levels in 4 types of colon cancer cell lines (HCT116, SW620, HT29, and SW480) were also examined by qRT-PCR. We constructed CLEC5A knockdown cell lines and used colony formation, Cell Counting Kit-8 (CCK-8), 5-Ethynyl-2'-deoxyuridine (EdU), wound healing, and transwell assays for investigating the CLEC5A function in colon cancer's proliferation and migration. A CLEC5A silencing nude mice model was established to measure the scale, weight, and growth rate of tumor xenograft. In CLEC5A knockdown cell lines and xenograft tissues, the levels of cell cycle and epithelial-mesenchymal transition (EMT)-related proteins were detected using Western blot (WB), and the phosphorylation levels of AKT/mTOR pathway key proteins were also detected by WB. On the basis of gene expression data retrieved from TCGA database, a relevance between CLEC5A and AKT/mTOR pathway in colon cancer was examined by gene set enrichment analysis (GSEA), and correlation analysis of CLEC5A and COL1A1 was employed to confirm their interaction. Results: Bioinformatics analysis, IHC staining, and qRT-PCR assay results all showed the significant high levels of CLEC5A expression in colon cancer tissues and cells, and positive links between CLEC5A levels and lymph node metastasis, vascular metastasis, and tumor-node-metastasis (TNM) stages of colon cancer patients. The suppressive effects of CLEC5A knockdown on colon cancer's proliferation and migration were verified in cell function and nude mice tumorigenesis assays. WB analysis further indicated that CLEC5A knockdown could inhibit cell cycle, and EMT processes, as well as AKT/mTOR pathway phosphorylation in colon cancer. On the basis of TCGA data, CLEC5A's activation effect on AKT/mTOR pathway had been confirmed by GSEA analysis, and the interaction between CLEC5A and COL1A1 was also revealed through correlation analysis in colon cancer. Conclusions: CLEC5A may promote the development and migration of colon cancer by triggering the AKT/mTOR signaling pathway. Furthermore, COL1A1 could serve as the target gene of CLEC5A.

Development and economic assessment of machine learning models to predict glycosylated hemoglobin in type 2 diabetes.

Background: Glycosylated hemoglobin (HbA1c) is recommended for diagnosing and monitoring type 2 diabetes. However, the monitoring frequency in real-world applications has not yet reached the recommended frequency in the guidelines. Developing machine learning models to screen patients with poor glycemic control in patients with T2D could optimize management and decrease medical service costs. Methods: This study was carried out on patients with T2D who were examined for HbA1c at the Sichuan Provincial People's Hospital from April 2018 to December 2019. Characteristics were extracted from interviews and electronic medical records. The data (excluded FBG or included FBG) were randomly divided into a training dataset and a test dataset with a radio of 8:2 after data pre-processing. Four imputing methods, four screening methods, and six machine learning algorithms were used to optimize data and develop models. Models were compared on the basis of predictive performance metrics, especially on the model benefit (MB, a confusion matrix combined with economic burden associated with therapeutic inertia). The contributions of features were interpreted using SHapley Additive exPlanation (SHAP). Finally, we validated the sample size on the best model. Results: The study included 980 patients with T2D, of whom 513 (52.3%) were defined as positive (need to perform the HbA1c test). The results indicated that the model trained in the data (included FBG) presented better forecast performance than the models that excluded the FBG value. The best model used modified random forest as the imputation method, ElasticNet as the feature screening method, and the LightGBM algorithms and had the best performance. The MB, AUC, and AUPRC of the best model, among a total of 192 trained models, were 43475.750 (¥), 0.972, 0.944, and 0.974, respectively. The FBG values, previous HbA1c values, having a rational and reasonable diet, health status scores, type of manufacturers of metformin, interval of measurement, EQ-5D scores, occupational status, and age were the most significant contributors to the prediction model. Conclusion: We found that MB could be an indicator to evaluate the model prediction performance. The proposed model performed well in identifying patients with T2D who need to undergo the HbA1c test and could help improve individualized T2D management.

m6A-mediated upregulation of LINC01003 regulates cell migration by targeting the CAV1/FAK signaling pathway in glioma.

BACKGROUND: Long non-coding RNAs (lncRNAs) play important roles in the progression of glioma. Here, we examined the potential functions of a lncRNA, LINC01003, in glioma and characterized the underlying molecular mechanisms. METHODS: The GEIPA2 and Chinese Glioma Genome Atlas (CCGA) databases were employed to analyze gene expression and the overall survival curve in patients with glioma. The functions of LINC01003 in glioma growth and migration were assessed by loss-of-function experiments in vitro and in vivo. RNA sequencing was used to determine the signaling pathways effected by LINC01003. Bioinformatics analysis and RNA immunoprecipitation (RIP) assays were used to explore the mechanism underlying the N6-methyladenine (m6A) modification-dependent upregulation of LINC01003 in glioma. RESULTS: LINC01003 expression was upregulated in glioma cell lines and tissues. Higher LINC01003 expression predicted shorter overall survival time in glioma patients. Functionally, LINC01003 knockdown inhibited the cell cycle and cell proliferation and migration in glioma cells. Mechanistically, RNA sequencing revealed that LINC01003 mediated the focal adhesion signaling pathway. Furthermore, LINC01003 upregulation is induced by m6A modification regulated by METTL3. CONCLUSION: This study characterized LINC01003 as a lncRNA that contributes to tumorigenesis in glioma and demonstrated that the LINC01003-CAV1-FAK axis serves as a potential therapeutic target for glioma.

Development and assessment of novel machine learning models to predict the probability of postoperative nausea and vomiting for patient-controlled analgesia.

Postoperative nausea and vomiting (PONV) can lead to various postoperative complications. The risk assessment model of PONV is helpful in guiding treatment and reducing the incidence of PONV, whereas the published models of PONV do not have a high accuracy rate. This study aimed to collect data from patients in Sichuan Provincial People's Hospital to develop models for predicting PONV based on machine learning algorithms, and to evaluate the predictive performance of the models using the area under the receiver characteristic curve (AUC), accuracy, precision, recall rate, F1 value and area under the precision-recall curve (AUPRC). The AUC (0.947) of our best machine learning model was significantly higher than that of the past models. The best of these models was used for external validation on patients from Chengdu First People's Hospital, and the AUC was 0.821. The contributions of variables were also interpreted using SHapley Additive ExPlanation (SHAP). A history of motion sickness and/or PONV, sex, weight, history of surgery, infusion volume, intraoperative urine volume, age, BMI, height, and PCA_3.0 were the top ten most important variables for the model. The machine learning models of PONV provided a good preoperative prediction of PONV for intravenous patient-controlled analgesia.

A personalized prediction model for urinary tract infections in type 2 diabetes mellitus using machine learning.

Patients with type 2 diabetes mellitus (T2DM) are at higher risk for urinary tract infections (UTIs), which greatly impacts their quality of life. Developing a risk prediction model to identify high-risk patients for UTIs in those with T2DM and assisting clinical decision-making can help reduce the incidence of UTIs in T2DM patients. To construct the predictive model, potential relevant variables were first selected from the reference literature, and then data was extracted from the Hospital Information System (HIS) of the Sichuan Academy of Medical Sciences and Sichuan Provincial People's Hospital for analysis. The data set was split into a training set and a test set in an 8:2 ratio. To handle the data and establish risk warning models, four imputation methods, four balancing methods, three feature screening methods, and eighteen machine learning algorithms were employed. A 10-fold cross-validation technique was applied to internally validate the training set, while the bootstrap method was used for external validation in the test set. The area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA) were used to evaluate the performance of the models. The contributions of features were interpreted using the SHapley Additive ExPlanation (SHAP) approach. And a web-based prediction platform for UTIs in T2DM was constructed by Flask framework. Finally, 106 variables were identified for analysis from a total of 119 literature sources, and 1340 patients were included in the study. After comprehensive data preprocessing, a total of 48 datasets were generated, and 864 risk warning models were constructed based on various balancing methods, feature selection techniques, and a range of machine learning algorithms. The receiver operating characteristic (ROC) curves were used to assess the performances of these models, and the best model achieved an impressive AUC of 0.9789 upon external validation. Notably, the most critical factors contributing to UTIs in T2DM patients were found to be UTIs-related inflammatory markers, medication use, mainly SGLT2 inhibitors, severity of comorbidities, blood routine indicators, as well as other factors such as length of hospital stay and estimated glomerular filtration rate (eGFR). Furthermore, the SHAP method was utilized to interpret the contribution of each feature to the model. And based on the optimal predictive model a user-friendly prediction platform for UTIs in T2DM was built to assist clinicians in making clinical decisions. The machine learning model-based prediction system developed in this study exhibited favorable predictive ability and promising clinical utility. The web-based prediction platform, combined with the professional judgment of clinicians, can assist to make better clinical decisions.

Development and assessment of novel machine learning models to predict medication non-adherence risks in type 2 diabetics.

Background: Medication adherence is the main determinant of effective management of type 2 diabetes, yet there is no gold standard method available to screen patients with high-risk non-adherence. Developing machine learning models to predict high-risk non-adherence in patients with T2D could optimize management. Methods: This cross-sectional study was carried out on patients with T2D at the Sichuan Provincial People's Hospital from April 2018 to December 2019 who were examined for HbA1c on the day of the survey. Demographic and clinical characteristics were extracted from the questionnaire and electronic medical records. The sample was randomly divided into a training dataset and a test dataset with a radio of 8:2 after data preprocessing. Four imputing methods, five sampling methods, three screening methods, and 18 machine learning algorithms were used to groom data and develop and validate models. Bootstrapping was performed to generate the validation set for external validation and univariate analysis. Models were compared on the basis of predictive performance metrics. Finally, we validated the sample size on the best model. Results: This study included 980 patients with T2D, of whom 184 (18.8%) were defined as medication non-adherence. The results indicated that the model used modified random forest as the imputation method, random under sampler as the sampling method, Boruta as the feature screening method and the ensemble algorithms and had the best performance. The area under the receiver operating characteristic curve (AUC), F1 score, and area under the precision-recall curve (AUPRC) of the best model, among a total of 1,080 trained models, were 0.8369, 0.7912, and 0.9574, respectively. Age, present fasting blood glucose (FBG) values, present HbA1c values, present random blood glucose (RBG) values, and body mass index (BMI) were the most significant contributors associated with risks of medication adherence. Conclusion: We found that machine learning methods could be used to predict the risk of non-adherence in patients with T2D. The proposed model was well performed to identify patients with T2D with non-adherence and could help improve individualized T2D management.

Artificial intelligence for the prediction of acute kidney injury during the perioperative period: systematic review and Meta-analysis of diagnostic test accuracy.

BACKGROUND: Acute kidney injury (AKI) is independently associated with morbidity and mortality in a wide range of surgical settings. Nowadays, with the increasing use of electronic health records (EHR), advances in patient information retrieval, and cost reduction in clinical informatics, artificial intelligence is increasingly being used to improve early recognition and management for perioperative AKI. However, there is no quantitative synthesis of the performance of these methods. We conducted this systematic review and meta-analysis to estimate the sensitivity and specificity of artificial intelligence for the prediction of acute kidney injury during the perioperative period. METHODS: Pubmed, Embase, and Cochrane Library were searched to 2nd October 2021. Studies presenting diagnostic performance of artificial intelligence in the early detection of perioperative acute kidney injury were included. True positives, false positives, true negatives and false negatives were pooled to collate specificity and sensitivity with 95% CIs and results were portrayed in forest plots. The risk of bias of eligible studies was assessed using the PROBAST tool. RESULTS: Nineteen studies involving 304,076 patients were included. Quantitative random-effects meta-analysis using the Rutter and Gatsonis hierarchical summary receiver operating characteristics (HSROC) model revealed pooled sensitivity, specificity, and diagnostic odds ratio of 0.77 (95% CI: 0.73 to 0.81),0.75 (95% CI: 0.71 to 0.80), and 10.7 (95% CI 8.5 to 13.5), respectively. Threshold effect was found to be the only source of heterogeneity, and there was no evidence of publication bias. CONCLUSIONS: Our review demonstrates the promising performance of artificial intelligence for early prediction of perioperative AKI. The limitations of lacking external validation performance and being conducted only at a single center should be overcome. TRIAL REGISTRATION: This study was not registered with PROSPERO.

A novel LUAD prognosis prediction model based on immune checkpoint-related lncRNAs.

Lung adenocarcinoma (LUAD) is a malignant disease with an extremely poor prognosis, and there is currently a lack of clinical methods for early diagnosis and precise treatment and management. With the deepening of tumor research, more and more attention has been paid to the role of immune checkpoints (ICP) and long non-coding RNAs (lncRNAs) regulation in tumor development. Therefore, this study downloaded LUAD patient data from the TCGA database, and finally screened 14 key ICP-related lncRNAs based on ICP-related genes using univariate/multivariate COX regression analysis and LASSO regression analysis to construct a risk prediction model and corresponding nomogram. After multi-dimensional testing of the model, the model showed good prognostic prediction ability. In addition, to further elucidate how ICP plays a role in LUAD, we jointly analyzed the immune microenvironmental changes in LAUD patients and performed a functional enrichment analysis. Furthermore, to enhance the clinical significance of this study, we performed a sensitivity analysis of common antitumor drugs. All the above works aim to point to new directions for the treatment of LUAD.

Activation of LXRs Reduces Oxysterol Lipotoxicity in RPE Cells by Promoting Mitochondrial Function.

Effective treatments for age-related macular degeneration (AMD), the most prevalent neurodegenerative form of blindness in older adults, are lacking. Genome-wide association studies have identified lipid metabolism and inflammation as AMD-associated pathogenic changes. Liver X receptors (LXRs) play a critical role in intracellular homeostases, such as lipid metabolism, glucose homeostasis, inflammation, and mitochondrial function. However, its specific role in AMD and its underlying molecular mechanisms remain unknown. In this study, we investigated the effects of lipotoxicity in human retinal pigmental epithelial (ARPE-19) cells and evaluated how LXRs reduce 7-ketocholesterol (7KCh) lipotoxicity in RPE cells using models, both in vivo and in vitro. A decrease in oxidative lipid accumulation was observed in mouse retinas following the activation of the LXRs; this result was also confirmed in cell experiments. At the same time, LXRs activation reduced RPE cell apoptosis induced by oxysterols. We found that oxysterols decreased the mitochondrial membrane potential in ARPE-19 cells, while LXR agonists counteracted these effects. In cultured ARPE-19 cells, activating LXRs reduced p62, mTOR, and LC3I/II levels, and the knockdown of LXRs elevated the expression of these proteins, indicating that activating LXRs could boost mitophagy. The findings of this study suggest LXR-active pharmaceuticals as a potential therapeutic target for dry AMD.

Develop an ADR prediction system of Chinese herbal injections containing Panax notoginseng saponin: a nested case-control study using machine learning.

OBJECTIVE: This study aimed to develop an adverse drug reactions (ADR) antecedent prediction system using machine learning algorithms to provide the reference for security usage of Chinese herbal injections containing Panax notoginseng saponin in clinical practice. DESIGN: A nested case-control study. SETTING: National Center for ADR Monitoring and the Electronic Medical Record (EMR) system. PARTICIPANTS: All patients were from five medical institutions in Sichuan Province from January 2010 to December 2018. MAIN OUTCOMES/MEASURES: Data of patients with ADR who used Chinese herbal injections containing Panax notoginseng saponin were collected from the National Center for ADR Monitoring. A nested case-control study was used to randomly match patients without ADR from the EMR system by the ratio of 1:4. Eighteen machine learning algorithms were applied for the development of ADR prediction models. Area under curve (AUC), accuracy, precision, recall rate and F1 value were used to evaluate the predictive performance of the model. An ADR prediction system was established by the best model selected from the 1080 models. RESULTS: A total of 530 patients from five medical institutions were included, and 1080 ADR prediction models were developed. Among these models, the AUC of the best capable one was 0.9141 and the accuracy was 0.8947. According to the best model, a prediction system, which can provide early identification of patients at risk for the ADR of Panax notoginseng saponin, has been established. CONCLUSION: The prediction system developed based on the machine learning model in this study had good predictive performance and potential clinical application.

YTHDC1-mediated VPS25 regulates cell cycle by targeting JAK-STAT signaling in human glioma cells.

BACKGROUND: Glioma is a common type of malignant brain tumor with a high mortality and relapse rate. The endosomal sorting complex required for transport (ESCRT) has been reported to be involved in tumorigenesis. However, the molecular mechanisms have not been clarified. METHODS: Bioinformatics was used to screen the ESCRT subunits highly expressed in glioma tissues from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) databases. The function of the ESCRT subunits in glioma cells was examined in vitro. Transcriptome sequencing analyzed the target genes and signaling pathways affected by the ESCRT subunit. Finally, the relationship between m6A (N6-methyladenosine) modification and high expression of the ESCRT subunit was studied. RESULTS: VPS25 was upregulated in glioma tissues, which was correlated with poor prognosis in glioma patients. Furthermore, VPS25 knockdown inhibited the proliferation, blocked the cell cycle, and promoted apoptosis in glioma cells. Meanwhile, VPS25 induced a G0/G1 phase arrest of the cell cycle in glioma cells by directly mediating p21, CDK2, and cyclin E expression, and JAK-signal transducer and activator of transcription (STAT) activation. Finally, YTHDC1 inhibited glioma proliferation by reducing the expression of VPS25. CONCLUSION: These results suggest that VPS25 is a promising prognostic indicator and a potential therapeutic target for glioma.

RGD-modified multifunctional nanoparticles encapsulating salvianolic acid A for targeted treatment of choroidal neovascularization.

BACKGROUND: The development of alternative anti-angiogenesis therapy for choroidal neovascularization (CNV) remains a great challenge. Nanoparticle systems have emerged as a new form of drug delivery in ocular diseases. Here, we report the construction and characterization of arginine-glycine-aspartic acid (RGD)-conjugated polyethyleneimine (PEI) as a vehicle to load antioxidant salvianolic acid A (SAA) for targeted anti-angiogenesis therapy of CNV. In this study, PEI was consecutively modified with polyethylene glycol (PEG) conjugated RGD segments, 3-(4'-hydroxyphenyl) propionic acid-Osu (HPAO), and fluorescein isothiocyanate (FI), followed by acetylation of the remaining PEI surface amines to generate the multifunctional PEI vehicle PEI.NHAc-FI-HPAO-(PEG-RGD) (for short, RGD-PEI). The formed RGD-PEI was utilized as an effective vehicle platform to load SAA. RESULTS: We showed that RGD-PEI/SAA complexes displayed desirable water dispersibility, low cytotoxicity, and sustainable release of SAA under different pH conditions. It could be specifically taken up by retinal pigment epithelium (RPE) cells which highly expressed ɑvß5 integrin receptors in vitro and selectively accumulated in CNV lesions in vivo. Moreover, the complexes displayed specific therapeutic efficacy in a mouse model of laser induced CNV, and the slow elimination of the complexes in the vitreous cavity was verified by SPECT imaging after 131I radiolabeling. The histological examinations further confirmed the biocompatibility of RGD-PEI/SAA. CONCLUSIONS: The results suggest that the designed RGD-PEI/SAA complexes may be a potential alternative anti-angiogenesis therapy for posterior ocular neovascular diseases.

Machine Learning Approaches to Predict Risks of Diabetic Complications and Poor Glycemic Control in Nonadherent Type 2 Diabetes.

Purpose: The objective of this study was to evaluate the efficacy of machine learning algorithms in predicting risks of complications and poor glycemic control in nonadherent type 2 diabetes (T2D). Materials and Methods: This study was a real-world study of the complications and blood glucose prognosis of nonadherent T2D patients. Data of inpatients in Sichuan Provincial People's Hospital from January 2010 to December 2015 were collected. The T2D patients who had neither been monitored for glycosylated hemoglobin A nor had changed their hyperglycemia treatment regimens within the last 12 months were the object of this study. Seven types of machine learning algorithms were used to develop 18 prediction models. The predictive performance was mainly assessed using the area under the curve of the testing set. Results: Of 800 T2D patients, 165 (20.6%) met the inclusion criteria, of which 129 (78.2%) had poor glycemic control (defined as glycosylated hemoglobin A ≥7%). The highest area under the curves of the testing set for diabetic nephropathy, diabetic peripheral neuropathy, diabetic angiopathy, diabetic eye disease, and glycosylated hemoglobin A were 0.902 ± 0.040, 0.859 ± 0.050, 0.889 ± 0.059, 0.832 ± 0.086, and 0.825 ± 0.092, respectively. Conclusion: Both univariate analysis and machine learning methods reached the same conclusion. The duration of T2D and the duration of unadjusted hypoglycemic treatment were the key risk factors of diabetic complications, and the number of hypoglycemic drugs was the key risk factor of glycemic control of nonadherent T2D. This was the first study to use machine learning algorithms to explore the potential adverse outcomes of nonadherent T2D. The performances of the final prediction models we developed were acceptable; our prediction performances outperformed most other previous studies in most evaluation measures. Those models have potential clinical applicability in improving T2D care.