Absolute Shrinkage Selection Operator Research Articles

Development and validation of a prognostic model for mitophagy-related genes in colon adenocarcinoma: A study based on TCGA and GEO databases.

Mitophagy is used by eukaryotic cells to eliminate damaged mitochondria. The deregulation of this process can lead to an accumulation of dysfunctional mitochondria and is implicated in carcinogenesis and tumorigenesis. Despite increasing evidence that mitophagy is involved in the development of colon cancer, the role of mitophagy-related genes (MRGs) in colon adenocarcinoma (COAD) prognosis and treatment remains largely unknown. Differential analysis was used to identify differentially expressed mitophagy-related genes associated with COAD and conduct key module screening. Cox regression and least absolute shrinkage selection operator, and other analyses were used to characterize prognosis-related genes and verify the feasibility of the model. The model was tested using GEO data and a nomogram was constructed for future clinical application. The level of immune cell infiltration and immunotherapy were compared between the two groups, and sensitivity to treatment with many commonly used chemotherapeutic agents was assessed in individuals with different risk factors. Finally, qualitative reverse transcription polymerase chain reaction and western blotting were performed to assess the expression of prognosis-related MRGs. A total of 461 differentially expressed genes were mined in COAD. Four prognostic genes, PPARGC1A, SLC6A1, EPHB2, and PPP1R17, were identified to construct a mitophagy-related gene signature. The feasibility of prognostic models was assessed using Kaplan-Meier analysis, time-dependent receiver operating characteristics, risk scores, Cox regression analysis, and principal component analysis. At 1, 3, and 5 years, the area under the receiver operating characteristic curves were 0.628, 0.678, and 0.755, respectively, for TCGA cohort, and 0.609, 0.634, and 0.640, respectively, for the GEO cohort. Drug sensitivity analysis found that camptothecin, paclitaxel, bleomycin, and doxorubicin were significantly different between low- and high-risk patients. The qPCR and western blotting results of clinical samples further confirmed the public database results. This study successfully constructed a mitophagy-related gene signature with significant predictive value for COAD, informing new possibilities for the treatment of this disease.

Establishment and validation of a nomogram for predicting perioperative complications of retroperitoneal laparoscopic adrenalectomy.

While laparoscopic adrenalectomy (LA) represents a gold standard for treating most adrenal lesions, no effective visual model for the prediction of perioperative complications of retroperitoneal laparoscopic adrenalectomy (RLA) exists. A retrospective study was conducted involving all consecutive patients underwent unilateral RLA for adrenal disease from January 2012 to December 2021. The entire cohort was randomly divided into 2 subsets (70% of the data for training, 30% for validation). Subsequently, a Least Absolute Shrinkage Selection Operator (LASSO) regression was performed to select the predictor variables, which were further consolidated via random forest (RF) and Boruta algorithm. Then the nomogram was established using the bivariate logistic regression analysis. Eventually, the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were employed to evaluate discrimination, calibration and clinical usefulness of the model, respectively. A total of 610 patients underwent unilateral RLA for adrenal diseases were enrolled. After machine learning analyses, a weighted nomogram was established with 7 factors associated with complications including operative time, lesion laterality, intraoperative blood loss, pheochromocytoma, body mass index (BMI) and 2 preoperative comorbidities [respiratory diseases, cardiovascular diseases (CVD)]. The model displayed a fine calibration curve for perioperative complications evaluation in both the training dataset (P=0.847) and validation dataset (P=0.248). ROC with area under the curve (AUC) revealed excellent discrimination in the training dataset (0.817, 95% CI: 0.758-0.875) and validation dataset (0.794, 95% CI: 0.686-0.901). DCA curves showed that using this nomogram provided a more net benefit where threshold probabilities lay in the range of 0.1 to 0.9. An effective nomogram that incorporating 7 predictors was established in this study to identify patients at high risk of perioperative complications for RLA. It would contribute to the improvement of perioperative strategy due to its accuracy and convenience.

Integration analysis based on fatty acid metabolism robustly predicts prognosis, dissecting immunity microenvironment and aiding immunotherapy for soft tissue sarcoma.

Background: Soft tissue sarcoma (STS) is a highly malignant tumor with a dismal prognosis. Presently, the dysregulation of fatty acid metabolism has received increasing attention in tumor research, but fewer reports are relevant to STS. Methods: Based on fatty acid metabolism-related genes (FRGs), a novel risk score for STS was developed utilizing univariate analysis and least absolute shrinkage selection operator (LASSO) Cox regression analyses in the STS cohort, which were further validated using the external validation cohort from other databases. Furthermore, independent prognostic analysis, C-index, ROC curves, and nomogram were carried out to investigate the predictive performance of fatty acid-related risk scores. We also analysed the differences in enrichment pathways, the immune microenvironment, gene mutations, and immunotherapy response between the two distinct fatty acid score groups. Moreover, the real-time quantitative polymerase chain reaction (RT-qPCR) was used to further verify the expression of FRGs in STS. Results: A total of 153 FRGs were retrieved in our study. Next, a novel fatty acid metabolism-related risk score (FAS) was constructed based on 18 FRGs. The predictive performance of FAS was also verified in external cohorts. In addition, the independent analysis, C-index, ROC curve, and nomograph also revealed that FAS could serve as an independent prognostic factor for the STS patients. Meanwhile, our results demonstrated that the STS cohort in two distinct FAS groups had different copy number variations, immune cell infiltration, and immunotherapy responses. Finally, the in vitro validation results demonstrated that several FRGs included in the FAS exhibited abnormal expression in STS. Conclusion: Altogether, our work comprehensively and systematically clarifies fatty acid metabolism's potential roles and clinical significance in STS. The novel individualized score based on fatty acid metabolism may be provided as a potential marker and treatment strategy in STS.

Histone acetylation-related IncRNA: Potential biomarkers for predicting prognosis and immune response in lung adenocarcinoma, and distinguishing hot and cold tumours.

Histone acetylation-related lncRNAs (HARlncRNAs) play significant roles in various cancers, but their impact on lung adenocarcinoma (LUAD) remains unclear. This study aimed to develop a new HARlncRNA-based prognostic model for LUAD and to explore its potential biological mechanisms. We identified 77 histone acetylation genes based on previous studies. HARlncRNAs related to prognosis were screened by co-expression, univariate and multivariate analyses, and least absolute shrinkage selection operator regression (LASSO). Afterward, a prognostic model was established based on the screened HARlncRNAs. We analysed the relationship between the model and immune cell infiltration characteristics, immune checkpoint molecule expression, drug sensitivity, and tumour mutational burden (TMB). Finally, the entire sample was divided into three clusters to further distinguish between hot and cold tumours. A seven-HARlncRNA-based prognostic model was established for LUAD. The area under the curve (AUC) of the risk score was the highest among all the analysed prognostic factors, indicating the accuracy and robustness of the model. The patients in the high-risk group were predicted to be more sensitive to chemotherapeutic, targeted, and immunotherapeutic drugs. It was worth noting that clusters could effectively identify hot and cold tumours. In our study, clusters 1 and 3 were considered hot tumours that were more sensitive to immunotherapy drugs. We developed a risk-scoring model based on seven prognostic HARlncRNAs that promises to be a new tool for evaluating the prognosis and efficacy of immunotherapy in patients with LUAD.

Relationships of ferroptosis-related genes with the pathogenesis in polycystic ovary syndrome.

Numerous studies have suggested that ferroptosis plays a significant role in the development of polycystic ovary syndrome (PCOS), but the mechanism remains unclear. In this study, we explored the role of ferroptosis-related genes in the pathogenesis of PCOS using a comprehensive bioinformatics method. First, we downloaded several Gene Expression Omnibus (GEO) datasets and combined them into a meta-GEO dataset. Differential expression analysis was performed to screen for significant ferroptosis-related genes between the normal and PCOS samples. The least absolute shrinkage selection operator regression and support vector machine-recursive feature elimination were used to select the best signs to construct a PCOS diagnostic model. Receiver operating characteristic curve analysis and decision curve analysis were applied to test the performance of the model. Finally, a ceRNA network-related ferroptosis gene was constructed. Five genes, namely, NOX1, ACVR1B, PHF21A, FTL, and GALNT14, were identified from 10 differentially expressed ferroptosis-related genes to construct a PCOS diagnostic model. Finally, a ceRNA network including 117 lncRNAs, 67 miRNAs, and five ferroptosis-related genes was constructed. Our study identified five ferroptosis-related genes that may be involved in the pathogenesis of PCOS, which may provide a novel perspective for the clinical diagnosis and treatment of PCOS.

An integrative analysis revealing cuproptosis-related lncRNAs signature as a novel prognostic biomarker in hepatocellular carcinoma.

Background: Cuproptosis is a newly defined form of cell death, whether cuproptosis involved in hepatocellular carcinoma (HCC) remains elusive. Method: We obtained patients' RNA expression data and follow-up information from University of California Santa Cruz (UCSC) and The Cancer Genome Atlas (TCGA). We analyzed the mRNA level of Cuproptosis-related genes (CRGs) and performed univariate Cox analysis. Liver hepatocellular carcinoma (LIHC) was chosen for further investigation. Real-Time quantitative PCR (RT-qPCR), Western blotting (WB), Immunohistochemical (IHC), and Transwell assays were used to determine expression patterns and functions of CRGs in LIHC. Next, we identified CRGs-related lncRNAs (CRLs) and differentially expressed CRLs between HCC and normal cases. Univariate Cox analysis, least absolute shrinkage selection operator (LASSO) analysis and Cox regression analysis were used to construct the prognostic model. Univariate and multivariate Cox analysis was used to assess whether the risk model can act as an independent risk factor of overall survival duration. Different risk groups performed immune correlation analysis, tumor mutation burden (TMB), and Gene Set Enrichment Analysis (GSEA) analysis were performed in different risk groups. Finally, we assessed the performance of the predictive model in drug sensitivity. Results: CRGs expression levels have significant differences between tumor and normal tissues. High expression of Dihydrolipoamide S-Acetyltransferase (DLAT) correlated to metastasis of HCC cells and indicated poor prognosis for HCC patients. Our prognostic model consisted of four cuproptosis-related lncRNA (AC011476.3, AC026412.3, NRAV, MKLN1-AS). The prognostic model performed well in predicting survival rates. The results from Cox regression analysis suggested that risk score can serve as an independent prognostic element for survival durations. Survival analysis revealed that low risk patients have extended survival periods compared with those with high risk. The results of the immune analysis indicated that risk score has a positive correlation with B cell and CD4+ T cell Th2, while has a negative relationship with endothelial cell and hematopoietic cells. Besides, immune checkpoint genes have higher expression folds in the high-risk set than in the low-risk set. The high-risk group had higher rates of genetic mutation than the low-risk set while having a shorter survival time. GSEA revealed the signaling pathways enriched in the high-risk group were mostly immune-related, while metabolic-related pathways were enriched in the low-risk group. Drugs sensitivity analysis indicated that our model has the ability to predict the efficacy of clinical treatment. Conclusion: The Cuproptosis-related lncRNAs prognostic formula is a novel predictor of HCC patients' prognosis and drug sensitivity.

Predictive control of SCR denitrification system in thermal power plants based on GA‐BP and PSO

AbstractAiming at the characteristics of strong non‐linearity and large inertia in the reaction process of a selective catalytic reduction (SCR) denitrification system, a predictive control algorithm based on a back propagation neural network optimized by genetic algorithm (GA‐BP) and particle swarm optimization (PSO) is proposed. First, the prediction model of a SCR denitrification system is established by GA‐BP. Second, output feedback and bias correction are used to reduce the prediction error. Third, the optimal inlet ammonia concentration is obtained by PSO. At the same time, in order to solve the problems of high dimension, large noise, and strong coupling in the original data of the SCR system in the process of establishing the prediction model, the least absolute shrinkage selection operator (LASSO) algorithm and the local outlier factor (LOF) detection algorithm are used to screen important variables and samples in the original data set of the SCR system to remove redundant variables and outliers. Finally, the simulation results show that the prediction model has good prediction accuracy and that the proposed predictive control method can achieve accurate control of ammonia injection concentration. This method improves the denitrification efficiency and reduces the NOx emission concentration, which can provide good guidance for on‐site production.

Identification of fatty acid metabolism-based molecular subtypes and prognostic signature to predict immune landscape and guide clinical drug treatment in renal clear cell carcinoma

Three subtypes of samples were generated based on genes involved in fatty acid metabolism in The Cancer Genome Atlas (TCGA)-RCC patients using a non-negative matrix factorization (NMF) algorithm. 32 co-expressed modules were identified using WCGNA. We constructed a four-gene signature in our training set using least absolute shrinkage selection operator regression analysis and verified it in our testing and overall sets. A relevant study analysis in clinical trials was conducted, which showed the model had good stability and potential application value for predicting outcomes. We analyzed the immune microenvironment using MCPcounter, CIBERSORT, quanTIseq, TIMER and ESTIMATE algorithms, and the result indicated risk was positively related to T cells, B-lineage, and fibroblasts and negatively correlated with monocytic lineage, myeloid dendritic cells, neutrophils, and endothelial cells, and CPT1B was positively related to T cells, CD8 + T cells, Cytotoxic lymphocytes and NK cells, and negatively correlated with myeloid dendritic cells, fibroblasts, endothelial cells. Tumor mutation burden was positively related to risk score and the expression of CPT1B using the R packages corrplot, circlize. Through the R package pRRophetic, drug sensitivity tests showed that the low-risk score group would benefit more from sunitinib and less from pazopanib, sorafenib, temsirolimus, gemcitabine and doxorubicin than the high-risk score group. We performed the relevant basic assay validation for CPT1B, and the proliferation ability of RCC cells was inhibited after the knockdown of protein expression of CPT1B. In conclusion, we established a four-gene model that can predict outcomes of RCC with potential applications in diagnosis and treatment.

GAPDH Is a Novel Ferroptosis-Related Marker and Correlates with Immune Microenvironment in Lung Adenocarcinoma

Lung adenocarcinoma (LUAD) is a prevalent form of lung cancer with high morbidity and fatality rates. Ferroptosis is a type of programmed cell death that is iron-dependent. Recent findings have suggested that ferroptosis inducers have promising prospects for the therapy of LUAD. However, ferroptosis-related gene expression in LUAD and its relationship with the tumor prognosis and tumor immune microenvironment remain unknown. We identified a total of 638 ferroptosis-related genes, built a LUAD ferroptosis-related risk model (FRRM) with the help of Least Absolute Shrinkage Selection Operator (LASSO) regression analysis based on The Cancer Genome Atlas (TCGA) database, split LUAD patients into high- and low-risk clusters, and verified the model utilizing the Gene Expression Omnibus (GEO) database. The results of the FRRM's principal component analysis (PCA) demonstrated its strong predictive power. Further, univariate and multivariate Cox and AUC curve analyses demonstrated that the model was independent of other clinical traits and served as an independent prognostic factor. The nomogram demonstrated strong predictive power for overall survival, according to calibration plots. We also explored variations in clinical characteristics, immune cell infiltration, immune-related function, and functional pathways between the high- and low-risk groups. Additionally, we used a protein-protein interaction (PPI) network of various genes in the two groups to search for potential target genes. GAPDH was then chosen for a follow-up investigation. An analysis was performed on the relationship between GAPDH and variations in survival prognosis, clinical traits, immune cell infiltration, immune checkpoints, and immunotherapy. In vitro tests further supported the probable functions of GAPDH as a ferroptosis marker in LUAD. In conclusion, a novel ferroptosis-related prognostic gene, GAPDH, was discovered, whose expression was connected to the tumor immune microenvironment. The combination of immunotherapy and the targeting of GAPDH to induce ferroptosis in LUAD may provide a novel therapeutical option.

Development and validation of a prognostic nomogram for Takotsubo syndrome patients in the intensive care units: a retrospective cohort study

Patients with Takotsubo syndrome (TTS) admitted to the intensive care unit (ICU) always confront a higher risk of in-hospital death than those hospitalized in the cardiology unit. The prognosis of the latter was analyzed by a large number of studies. However, there was no utility model to predict the risk of in-hospital death for patients with TTS in the ICU. This study aimed to establish a model predicting in-hospital death in patients with TTS admitted to ICU. We retrospectively included ICU patients with TTS from the MIMIC-IV database. The outcome of the nomogram was in-hospital death. Least Absolute Shrinkage Selection Operator (LASSO) analysis selected predictors preliminarily. The model was developed by multivariable logistic regression analysis. Calibration, decision curve analysis (DCA), and receiver operating characteristic (ROC) measured the performance of the nomogram on the accuracy, clinical utility, and discrimination, respectively. Eventually, 368 ICU patients with TTS were enrolled in this research. The in-hospital mortality was 13.04%. LASSO regression and multivariate logistic regression analysis verified risk factors significantly associated with in-hospital mortality. They were potassium, prothrombin time (PT), age, myocardial infarction, white cell count (WBC), hematocrit, anion gap, and sequential organ failure assessment (SOFA) score. This nomogram excellently discriminated against patients with a risk of in-hospital death. The area under curve (AUC) was 0.779 (95%CI: 0.732–0.826) in training set and 0.775 (95%CI: 0.711–0.839) in test set. The calibration plot and DCA showed good clinical benefits for this nomogram. We developed a nomogram that predicts the probability of in-hospital death for ICU patients with TTS. This nomogram was able to discriminate patients with a high risk of in-hospital death and performed clinical utility.

System Analysis Based on Pancreatic Cancer Progression Identifies BRINP2 as a Novel Prognostic Biomarker.

Pancreatic adenocarcinoma (PAAD) is a malignant tumor of the digestive system, which develops rapidly and has no obvious early symptoms. This study aims to discover the biomarkers associated with PAAD development. We obtained RNA expression of PAAD patient samples and corresponding clinical data from The cancer genome atlas (TCGA), and screened out BMP/RA-inducible neural-specific protein 2 (BRINP2) gene which is highly associated with PAAD severity. Then, gene ontology (GO) enrichment, Kyoto encyclopedia of genes and genomes (KEGG) pathway analysis and single-sample gene set enrichment analysis (ssGSEA) analysis were performed to explore the biological functions of BRINP2. Subsequently, long non-coding RNA (lncRNAs) associated with BRINP2 were screened out via correlation analysis, and Cox regression analysis and least absolute shrinkage selection operator (LASSO) regression analysis were used to construct the risk prediction model. We further validated the expression level of BRINP2 and its associated lncRNAs in BRINP2-associated lncRNAs prognostic model in vitro. We proposed that BRINP2 might be correlated to the tumor immune microenvironment and could also be used as a biomarker for PAAD progression. GO enrichment analysis and KEGG pathway analysis showed that the prognostic model was highly correlated to immune microenvironment-related pathways. Additionally, we established a BRINP2-associated lncRNAs prognostic model consisting of three lncRNAs. We validated the expression trends of BRINP2 and its associated lncRNAs in BRINP2-associated lncRNAs prognostic model in PAAD cells with various severity of metastatic potential using the quantitative real-time PCR (qRT-PCR). Meanwhile, pRRophetic R package was employed to predict potential therapeutic drugs for BRINP2-associated lncRNAs prognostic model of PAAD. The results suggest that BRINP2 can be used as a novel prognostic biomarker for PAAD.

Development and Evaluation of a Novel Cuproptosis-Related lncRNA Signature for Gastric Cancer Prognosis.

According to a growing body of research, long noncoding RNAs (lncRNAs) participate in the progress of gastric cancer (GC). Cuproptosis is a distinct kind of programmed cell death, separating it from several other forms of programmed cell death that may be caused by genetic programming. Consequently, it is crucial to examine cuproptosis-related lncRNAs (CRLs) prognostic importance for the prognosis and treatment response in GC. The Cancer Genome Atlas (TCGA) database was used to retrieve RNA-seq data, pertinent clinical information, and somatic mutation data. A list of cuproptosis-related genes (CRGs) was obtained from prior work. We can distinguish prognostic CRLs using coexpression and univariate Cox analysis. Then, using CRLs, we developed a risk prediction model using multivariate Cox regression analysis and the least absolute shrinkage selection operator (LASSO) technique. To evaluate the diagnostic accuracy of this model, a Kaplan-Meier (K-M) survival analysis and a receiver operating characteristic (ROC) analysis were used. Moreover, the relationships between the risk model and immunological function, somatic mutation, and drug sensitivity were also investigated. Using the multivariate Cox analysis technique, we developed a signature based on cuproptosis-related four lncRNAs. We then classified patients into high-risk and low-risk groups based on the likelihood of unfavorable outcomes. The model was subjected to further testing, including K-M survival analysis, ROC analysis, and multivariate Cox regression analysis, all of which proved the model's exceptional robustness and predictive capacity. In addition, a nomogram that has a strong capacity for prediction ability was built. This nomogram included age, gender, clinical grade, pathologic stage, T stage, and risk score. Furthermore, we discovered substantial disparities in immune function and the number of mutations carried by tumors between the high-risk and low-risk groups. Moreover, this research also found that the IC50 values for 27 chemotherapeutic drugs varied widely across patients within high- and low-risk groups. The proposed 4-CRLs signature is a promising biomarker to predict clinical outcomes in GC.

Identification of feature genes and key biological pathways in immune-mediated necrotizing myopathy: High-throughput sequencing and bioinformatics analysis

BackgroundImmune-mediated necrotizing myopathy (IMNM), a subgroup of idiopathic inflammatory myopathies (IIMs), is characterized by severe proximal muscle weakness and prominent necrotic fibers but no infiltration of inflammatory cells. IMNM pathogenesis is unclear. This study investigated key biomarkers and potential pathways for IMNM using high-throughput sequencing and bioinformatics technology. MethodsRNA sequencing was conducted in 18 IMNM patients and 10 controls. A combination of weighted gene coexpression network analysis (WGCNA) and differentially expressed gene (DEG) analysis was conducted to identify IMNM-related DEGs. Feature genes were screened out by employing the proteinprotein interaction (PPI) network, support vector machine-recursive feature elimination (SVM-RFE), and least absolute shrinkage selection operator (LASSO). Quantitative real-time polymerase chain reaction (qRTPCR) was performed to verify their differential expression, and the receiver operating characteristic curve (ROC) was used to evaluate their diagnostic efficiency. Functional enrichment analysis was applied to reveal the hidden functions of feature genes. Furthermore, 28 immune cell abundance patterns in IMNM samples were measured. ResultsWe identified 193 IMNM-related DEGs that were aberrantly upregulated in the IMNM population and were closely associated with immune-inflammatory responses, regulation of skeletal and cardiac muscle contraction, and lipoprotein metabolism. With the help of the PPI network and the LASSO and SVM-RFE algorithms, three feature genes, LTK, MYBPH, and MYL4, were identified and further confirmed by qRTPCR. ROC curves among IMNM, dermatomyositis (DM), inclusion body myositis (IBM), and polymyositis (PM) samples validated the LTK and MYL4 genes as IMNM-specific feature markers. In addition, all three genes had a notable association with the autophagylysosome pathway and immune-inflammatory responses. Ultimately, IMNM displayed a marked immune-cell infiltrative microenvironment. The most significant correlation was found between CD4 T cells, CD8 T cells, macrophages, natural killer (NK) cells, and dendritic cells (DCs). ConclusionsLTK, MYBPH, and MYL4 were identified as potential key molecules for IMNM and are believed to play a role in the autophagylysosome pathway and muscle inflammation.

A radiomic model to classify response to neoadjuvant chemotherapy in breast cancer

BackgroundMedical image analysis has evolved to facilitate the development of methods for high-throughput extraction of quantitative features that can potentially contribute to the diagnostic and treatment paradigm of cancer. There is a need for further improvement in the accuracy of predictive markers of response to neo-adjuvant chemotherapy (NAC). The aim of this study was to develop a radiomic classifier to enhance current approaches to predicting the response to NAC breast cancer.MethodsData on patients treated for breast cancer with NAC prior to surgery who had a pre-NAC dynamic contrast enhanced breast MRI were included. Response to NAC was assessed using the Miller–Payne system on the excised tumor. Tumor segmentation was carried out manually under the supervision of a consultant breast radiologist. Features were selected using least absolute shrinkage selection operator regression. A support vector machine learning model was used to classify response to NAC.Results74 patients were included. Patients were classified as having a poor response to NAC (reduction in cellularity < 90%, n = 44) and an excellent response (> 90% reduction in cellularity, n = 30). 4 radiomics features (discretized kurtosis, NGDLM contrast, GLZLM_SZE and GLZLM_ZP) were identified as pertinent predictors of response to NAC. A SVM model using these features stratified patients into poor and excellent response groups producing an AUC of 0.75. Addition of estrogen receptor status improved the accuracy of the model with an AUC of 0.811.ConclusionThis study identified a radiomic classifier incorporating 4 radiomics features to augment subtype based classification of response to NAC in breast cancer.

Machine learning model identifies aggressive acute pancreatitis within 48 h of admission: a large retrospective study

BackgroundAcute pancreatitis (AP) with critical illness is linked to increased morbidity and mortality. Current risk scores to identify high-risk AP patients have certain limitations.ObjectiveTo develop and validate a machine learning tool within 48 h after admission for predicting which patients with AP will develop critical illness based on ubiquitously available clinical, laboratory, and radiologic variables.Methods5460 AP patients were enrolled. Clinical, laboratory, and imaging variables were collected within 48 h after hospital admission. Least Absolute Shrinkage Selection Operator with bootstrap method was employed to select the most informative variables. Five different machine learning models were constructed to predictive likelihood of critical illness, and the optimal model (APCU) was selected. External cohort was used to validate APCU. APCU and other risk scores were compared using multivariate analysis. Models were evaluated by area under the curve (AUC). The decision curve analysis was employed to evaluate the standardized net benefit.ResultsXgboost was constructed and selected as APCU, involving age, comorbid disease, mental status, pulmonary infiltrates, procalcitonin (PCT), neutrophil percentage (Neu%), ALT/AST, ratio of albumin and globulin, cholinesterase, Urea, Glu, AST and serum total cholesterol. The APCU performed excellently in discriminating AP risk in internal cohort (AUC = 0.95) and external cohort (AUC = 0.873). The APCU was significant for biliogenic AP (OR = 4.25 [2.08–8.72], P < 0.001), alcoholic AP (OR = 3.60 [1.67–7.72], P = 0.001), hyperlipidemic AP (OR = 2.63 [1.28–5.37], P = 0.008) and tumor AP (OR = 4.57 [2.14–9.72], P < 0.001). APCU yielded the highest clinical net benefit, comparatively.ConclusionMachine learning tool based on ubiquitously available clinical variables accurately predicts the development of AP, optimizing the management of AP.

Ensemble Machine Learning for Monkeypox Transmission Time Series Forecasting

Public health is now in danger because of the current monkeypox outbreak, which has spread rapidly to more than 40 countries outside of Africa. The growing monkeypox epidemic has been classified as a “public health emergency of international concern” (PHEIC) by the World Health Organization (WHO). Infection outcomes, risk factors, clinical presentation, and transmission are all poorly understood. Computer- and machine-learning-assisted prediction and forecasting will be useful for controlling its spread. The objective of this research is to use the historical data of all reported human monkey pox cases to predict the transmission rate of the disease. This paper proposed stacking ensemble learning and machine learning techniques to forecast the rate of transmission of monkeypox. In this work, adaptive boosting regression (Adaboost), gradient boosting regression (GBOOST), random forest regression (RFR), ordinary least square regression (OLS), least absolute shrinkage selection operator regression (LASSO), and ridge regression (RIDGE) were applied for time series forecasting of monkeypox transmission. Performance metrics considered in this study are root mean square (RMSE), mean absolute error (MAE), and mean square error (MSE), which were used to evaluate the performance of the machine learning and the proposed Stacking Ensemble Learning (SEL) technique. Additionally, the monkey pox dataset was used as test data for this investigation. Experimental results revealed that SEL outperformed other machine learning approaches considered in this work with an RMSE of 33.1075; a MSE of 1096.1068; and a MAE of 22.4214. This is an indication that SEL is a better predictor than all the other models used in this study. It is hoped that this research will help government officials understand the threat of monkey pox and take the necessary mitigation actions.

Machine learning models representing catalytic activity for direct catalytic CO2 hydrogenation to methanol

Direct catalytic hydrogenation of CO2 to methanol is one of the most attractive ways to meet increasing fuel demand and reduce anthropogenic CO2 emission. An efficient catalyst is required for this highly complex structure-based reaction that simultaneously activates the CO2 molecule along with increased selectivity at feasible operating conditions. Application of machine learning models in catalysis research enables researchers to estimate and develop insights on the catalyst performances.This work focuses on development of machine learning (ML) models that include Multi Linear Regression, Least Absolute Shrinkage Selection Operator, Ridge Regression, Support Vector Regression, Gaussian Process Regression (GPR), Random Forest Regression, Gradient Boost Random Forest Regression (GBRT) and Artificial Neural Network (ANN) using published experimental data (698 datapoints) generated in a fixed bed reactor during the years 2010–2020. CO2 conversion and methanol selectivity were considered as catalytic activity performance indicators. Compared to other ML models, GBRT and ANN model predictions outperformed with R2 ∼ 0.95 and R2 ∼ 0.94 for CO2 conversion and with R2 ∼ 0.95 and R2 ∼ 0.95 for methanol selectivity respectively. Further, the input contributions using ANN models reveal that catalyst composition and calcination temperature are the significant inputs for CO2 conversion and methanol selectivity.

Construction and validation of an angiogenesis-related scoring model to predict prognosis, tumor immune microenvironment and therapeutic response in hepatocellular carcinoma.

Hepatocellular carcinoma (HCC) is one of the most common malignant tumors in the world with high morbidity and mortality. Identifying an effective marker for predicting the prognosis and therapeutic response is extremely meaningful. Angiogenesis-related genes (ARGs) play important roles in the tumor progression and immune-suppressive microenvironment formation. The differential expressed ARGs associated with the prognosis of HCC were identified in the TCGA dataset. Univariate Cox and least absolute shrinkage selection operator (LASSO) regression were applied to construct a ARGs Scoring model. The prognostic value of the ARGs Scoring model was assessed by Cox regression, Kaplan-Meier (KM) and ROC curve analyses. Then the model was further validated in an external dataset, ICGC dataset. The patients were split into two groups based on the ARGs Score and the clinical features were compared. TIMER, CIBERSORT and xCell algorithms were utilized to analyze the correlation between the ARGs Score and tumor immune microenvironment (TIME). Furthermore, we analyzed the efficacy of the model in predicting the therapeutic response for immunotherapy, targeted therapy and TACE treatment in different cohorts. A total of 97 differential expressed ARGs were identified relating to the prognosis of HCC patients from the TCGA dataset. Then the ARGs Scoring model based on a 9-gene signature was constructed using the Cox and LASSO regression analyses. Higher ARGs Score had a poor clinical outcome and was considered to be an independent prognostic predictor for HCC in the multivariate Cox analysis. The ARGs Score was related to the enrichment of various immune cells, such as CD4+ T cells, Treg, macrophage, neutrophil and dendritic cells, exhibiting a more immunosuppressive phenotype. Higher ARGs Score was correlated with higher expression of immune checkpoint genes and poor response to immunotherapy. Furthermore, higher ARGs Score indicated poor therapeutic response in the sorafenib and TACE treatment cohorts, individually. The ARGs Scoring model exhibited robust predictive value for the prognosis and TIME for HCC patients. Higher ARGs Score indicated poor therapeutic response of the immunotherapy, sorafenib and TACE treatment. The ARGs Scoring model could be used as a biomarker to help physicians to develop more individualized treatment for HCC patients.

Risk prediction model of polypharmacy for community-dwelling elderly patients: An assessment tool for early detection.

Background: Polypharmacy has become a major and growing public health issue, with significant implications for health outcomes and expenditure on healthcare resources. In this study, a risk prediction model of polypharmacy represented by a nomogram for community-dwelling elderly patients based on the Chinese population was constructed. Methods: A cross-sectional study was conducted in Shanghai, China. The variables data affecting polypharmacy were fetched from the information system database of health government departments in Shanghai. The Least Absolute Shrinkage Selection Operator (LASSO) regression analysis was used to select the predictor variables, and multivariate logistic regression was used to establish the prediction model. A visual tool of the nomogram was established for predicting the risk of polypharmacy in the elderly population. In addition, the receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA) were used to estimate the performance of the model. Results: A total of 80,012 elderly patients were included in this study. Eight variables, containing age, residential area, preferred medical institutions, number of visits to tertiary hospitals, number of visits to secondary hospitals, number of visits to community health centers, number of diagnoses, and main types of disease, were included in the risk prediction model of nomogram. The area under the curve (AUC) of the nomogram was 0.782 in both sets, demonstrating that the model has a good discriminant ability. The calibration chart shows that the prediction model fits well with the validation set. DCA results displayed that the threshold probabilities of the two sets in the prediction model reached up to 90%, implying that the model had a preferable application value. Conclusion: This study explored the risk factors for polypharmacy among the elderly in Shanghai, China, and applied the nomogram to establish a predictive model via eight variables, which provided an effective tool for early screening and timely prevention of polypharmacy. Family physicians or pharmacists could scientifically use the tool to closely observe community-dwelling elderly patients, decreasing the adverse health effects caused by medication for the elderly.

A nomogram to predict hyperkalemia in patients with hemodialysis: a retrospective cohort study

BackgroundHyperkalemia increases the risk of mortality and cardiovascular-related hospitalizations in patients with hemodialysis. Predictors of hyperkalemia are yet to be identified. We aimed at developing a nomogram able to predict hyperkalemia in patients with hemodialysis.MethodsWe retrospectively screened patients with end-stage renal disease (ESRD) who had regularly received hemodialysis between Jan 1, 2017, and Aug 31, 2021, at Lishui municipal central hospital in China. The outcome for the nomogram was hyperkalemia, defined as serum potassium [K+] ≥ 5.5 mmol/L. Data were collected from hemodialysis management system. Least Absolute Shrinkage Selection Operator (LASSO) analysis selected predictors preliminarily. A prediction model was constructed by multivariate logistic regression and presented as a nomogram. The performance of nomogram was measured by the receiver operating characteristic (ROC) curve, calibration diagram, and decision curve analysis (DCA). This model was validated internally by calculating the performance on a validation cohort.ResultsA total of 401 patients were enrolled in this study. 159 (39.65%) patients were hyperkalemia. All participants were divided into development (n = 256) and validation (n = 145) cohorts randomly. Predictors in this nomogram were the number of hemodialysis session, blood urea nitrogen (BUN), serum sodium, serum calcium, serum phosphorus, and diabetes. The ROC curve of the training set was 0.82 (95%CI 0.77, 0.88). Similar ROC curve was achieved at validation set 0.81 (0.74, 0.88). The calibration curve demonstrated that the prediction outcome was correlated with the observed outcome.ConclusionThis nomogram helps clinicians in predicting the risk of PEW and managing serum potassium in the patients with hemodialysis.