Elimination Algorithm Research Articles

Sparse Deep Neural Network for Encoding and Decoding the Structural Connectome.

Brain state classification by applying deep learning techniques on neuroimaging data has become a recent topic of research. However, unlike domains where the data is low dimensional or there are large number of available training samples, neuroimaging data is high dimensional and has few training samples. To tackle these issues, we present a sparse feedforward deep neural architecture for encoding and decoding the structural connectome of the human brain. We use a sparsely connected element-wise multiplication as the first hidden layer and a fixed transform layer as the output layer. The number of trainable parameters and the training time is significantly reduced compared to feedforward networks. We demonstrate superior performance of this architecture in encoding the structural connectome implicated in Alzheimer's disease (AD) and Parkinson's disease (PD) from DTI brain scans. For decoding, we propose recursive feature elimination (RFE) algorithm based on DeepLIFT, layer-wise relevance propagation (LRP), and Integrated Gradients (IG) algorithms to remove irrelevant features and thereby identify key biomarkers associated with AD and PD. We show that the proposed architecture reduces 45.1% and 47.1% of the trainable parameters compared to a feedforward DNN with an increase in accuracy by 2.6 % and 3.1% for cognitively normal (CN) vs AD and CN vs PD classification, respectively. We also show that the proposed RFE method leads to a further increase in accuracy by 2.1% and 4% for CN vs AD and CN vs PD classification, while removing approximately 90% to 95% irrelevant features. Furthermore, we argue that the biomarkers (i.e., key brain regions and connections) identified are consistent with previous literature. We show that relevancy score-based methods can yield high discriminative power and are suitable for brain decoding. We also show that the proposed approach led to a reduction in the number of trainable network parameters, an increase in classification accuracy, and a detection of brain connections and regions that were consistent with earlier studies.

Recognition of partial discharge in GIS based on image feature fusion

<p>Partial discharge (PD) is a significant electrical fault in gas-insulated switchgear (GIS), with various types posing different risks to insulation. Accurate identification of PD types is essential for enhancing GIS management and ensuring the reliability of electrical grids. This study proposes a novel approach for PD identification in GIS integrating completed local binary pattern (CLBP) feature extraction, feature engineering, and an optimized support vector machine (SVM). PD faults were simulated in GIS and phase-resolved pulse sequence (PRPS) data for four different forms of PD were gathered. CLBP was used to extract image features, and then the support vector machine recursive feature elimination (SVM-RFE) algorithm was used to evaluate feature importance. Then, linear discriminant analysis (LDA) was used to fuse the selected features and reduce redundancy. The fused features were classified using a bald eagle search algorithm combined with differential evolution (IBES)-optimized SVM, achieving a recognition accuracy of 99.38%. The results indicate that the proposed method effectively distinguishes between different PD PRPS patterns in GIS.</p>

PPP1R14A is Associated with Immunotherapy Resistance in Head and Neck Squamous Cell Carcinoma Identified by Single-Cell and Bulk RNA-Sequencing

ObjectiveTo identify nivolumab resistance-related genes in patients with head and neck squamous cell carcinoma (HNSCC) using single-cell and bulk RNA-sequencing data. MethodsThe single-cell and bulk RNA-sequencing data downloaded from the Gene Expression Omnibus database were analyzed to screen out differentially expressed genes (DEGs) between nivolumab resistant and nivolumab sensitive patients using R software. The Least Absolute Shrinkage Selection Operator (LASSO) regression and Recursive Feature Elimination (RFE) algorithm were performed to identify key genes associated with nivolumab resistance. Functional enrichment of DEGs was analyzed with Gene Ontology and Kyoto Encyclopedia of Genes and Genomes analyses. The relationships of key genes with immune cell infiltration, differentation trajectory, dynamic gene expression profiles, and ligand-receptor interaction were explored. ResultsWe found 83 DEGs. They were mainly enriched in T-cell differentiation, PD-1 and PD-L1 checkpoint, and T-cell receptor pathways. Among six key genes identified using machine learning algorithms, only PPP1R14A gene was differentially expressed between the nivolumab resistant and nivolumab sensitive groups both before and after immunotherapy (P < 0.05). The high PPP1R14A gene expression group had lower immune score (P < 0.01), higher expression of immunosuppressive factors (such as PDCD1, CTLA4, and PDCD1LG2) (r > 0, P < 0.05), lower differentiation of infiltrated immune cells (P < 0.05), and a higher degree of interaction between HLA and CD4 (P < 0.05). ConclusionsPPP1R14A gene is closely associated with resistance to nivolumab in HNSCC patients. Therefore, PPP1R14A may be a target to ameliorate nivolumab resistance of HNSCC patients.

Integrating machine learning algorithms and multiple immunohistochemistry validation to unveil novel diagnostic markers based on costimulatory molecules for predicting immune microenvironment status in triple-negative breast cancer.

Costimulatory molecules are putative novel targets or potential additions to current available immunotherapy, but their expression patterns and clinical value in triple-negative breast cancer (TNBC) are to be clarified. The gene expression profiles datasets of TNBC patients were obtained from The Cancer Genome Atlas and the Gene Expression Omnibus databases. Diagnostic biomarkers for stratifying individualized tumor immune microenvironment (TIME) were identified using the Least Absolute Shrinkage and Selection Operator (LASSO) and Support Vector Machine-Recursive Feature Elimination (SVM-RFE) algorithms. Additionally, we explored their associations with response to immunotherapy via the multiplex immunohistochemistry (mIHC). A total of 60 costimulatory molecule genes (CMGs) were obtained, and we determined two different TIME subclasses ("hot" and "cold") through the K-means clustering method. The "hot" tumors presented a higher infiltration of activated immune cells, i.e., CD4 memory-activated T cells, resting NK cells, M1 macrophages, and CD8 T cells, thereby enriched in the B cell and T cell receptor signaling pathways. LASSO and SVM-RFE algorithms identified three CMGs (CD86, TNFRSF17 and TNFRSF1B) as diagnostic biomarkers. Following, a novel diagnostic nomogram was constructed for predicting individualized TIME status and was validated with good predictive accuracy in TCGA, GSE76250 and GSE58812 databases. Further mIHC conformed that TNBC patients with high CD86, TNFRSF17 and TNFRSF1B levels tended to respond to immunotherapy. This study supplemented evidence about the value of CMGs in TNBC. In addition, CD86, TNFRSF17 and TNFRSF1B were found as potential biomarkers, significantly promoting TNBC patient selection for immunotherapeutic guidance.

Perceptions Toward Established and Novel Dietary Therapies for Crohn's Disease Management Among Adult Patients: Results From a Questionnaire Survey.

Exclusive enteral nutrition (EEN) and partial enteral nutrition (PEN) remain the only established dietary therapies in Crohn's disease (CD) management. We conducted a questionnaire survey to evaluate the perceptions of adults with CD toward established and emerging food-based dietary therapies. A 26-question anonymous survey was mailed to 300 adults receiving biologic treatment. Two researchers independently conducted a thematic analysis of open-ended responses. Machine learning with the Random Forest-Recursive Feature Elimination algorithm identified predictors of willingness to try dietary therapies. One hundred and sixty patients (53% female) completed and returned the survey. Forty-two percent were following some form of exclusion diet, with low-spice and low-fiber diets being the most popular. Although only a quarter of patients believed that EEN/PEN could help with their CD, more than half believed that diet could help, with another 13% already using diet for CD management. While half of the patients were willing to try EEN, the majority were willing to try PEN instead (51% vs. 79%; P < .001). Forty-two percent of patients preferred food-based dietary plans prepared at home over EEN/PEN options. The most important predictors for willingness to try dietary therapies were age (25-65 years), recent symptoms, previous exposure to EEN/PEN, and current exclusion diet use. The top concerns about PEN were taste/palatability, satiety/hunger, and taste fatigue. Most adults preferred to follow a food-based dietary therapy over EEN/PEN. The majority would try PEN though which allows for more flexibility to incorporate in habitual diet and may be easier to comply with than the EEN.

Research on the method of eliminating differences between small-sample databases based on cloud computing

Abstract As computer technology continues to advance, more and more people are using databases, leading to variations in data backup and transfer between databases. This paper proposes a small sample inter-database discrepancy data elimination method based on cloud computing architecture as a way to solve the problem of data synchronization discrepancy between different databases. The semantic features of the data in the database are represented in the form of a directed graph, and the semantic Gaussian marginalized data fusion system is constructed by combining the rectangular window function of Gaussian marginalization to realize the fusion filtering processing of discrepant data. Then, the particle swarm discriminant tree algorithm is used to extract the features of the difference data between the small sample databases, and the KL transform is used to compress the difference data to improve its confidence level. The rough weighted average single dependency method is introduced to detect and identify the difference data between small sample databases and combined with the artificial intelligence algorithm to construct the principal component feature set of the difference data in the small sample databases, thus realizing the elimination of the difference data between small sample databases. When the proportion of difference data is increased from 0.05% to 1.00%, the leakage alarm rate and false alarm rate of this paper’s method for the difference data between small sample databases are 0.113% and 0.099%, respectively. When eliminating the inter-database discrepancy data, its time consumption is between 0.06μs and 0.3μs, and the average value of the removal rate of discrepancy data can reach 95.54%. Small sample databases that utilize cloud computing technology can utilize a variety of differential data elimination algorithms to ensure high-quality migration and synchronized backup of inter-database data.

Security risk prediction technology for power monitoring system under the integration of OT and IT

As an essential force for economic advancement and social stability, the security of the power system has always been a concern. Therefore, the security risks of power monitoring systems are a research focus. This study proposes a prediction method that integrates IT and OT for the security risk prediction of power monitoring systems. A basic indicator system for security risks for analyzing risk data is constructed, the support vector machine regression feature elimination method for predicting security risks in IT Technology is used. The experiment showed that the accuracy of the support vector machine regression feature elimination method was 92.35%, which was 6.06% higher than the error back propagation algorithm, 3.19% higher than the support vector machine algorithm, and 0.77% higher than the regression feature elimination algorithm. The maximum testing accuracy of the support vector machine regression feature elimination method was 0.96, which was 0.1 higher than the support vector machine algorithm, 0.04 higher than the regression feature elimination algorithm, and 0.17 higher than the back propagation algorithm. Therefore, the support vector machine regression feature elimination method can accurately predict power monitoring systems and has higher accuracy compared with other algorithms.

A Hybrid convolution neural network for the classification of tree species using hyperspectral imagery.

In recent years, the advancement of hyperspectral remote sensing technology has greatly enhanced the detailed mapping of tree species. Nevertheless, delving deep into the significance of hyperspectral remote sensing data features for tree species recognition remains a challenging endeavor. The method of Hybrid-CS was proposed to addresses this challenge by synergizing the strengths of both deep learning and traditional learning techniques. Initially, we extract comprehensive correlation structures and spectral features. Subsequently, a hybrid approach, combining correlation-based feature selection with an optimized recursive feature elimination algorithm, identifies the most valuable feature set. We leverage the Support Vector Machine algorithm to evaluate feature importance and perform classification. Through rigorous experimentation, we evaluate the robustness of hyperspectral image-derived features and compare our method with other state-of-the-art classification methods. The results demonstrate: (1) Superior classification accuracy compared to traditional machine learning methods (e.g., SVM, RF) and advanced deep learning approaches on the tree species dataset. (2) Enhanced classification accuracy achieved by incorporating SVM and CNN information, particularly with the integration of attention mechanisms into the network architecture. Additionally, the classification performance of a two-branch network surpasses that of a single-branch network. (3) Consistent high accuracy across different proportions of training samples, indicating the stability and robustness of the method. This study underscores the potential of hyperspectral images and our proposed methodology for achieving precise tree species classification, thus holding significant promise for applications in forest resource management and monitoring.

Estimation of Biochemical Pigment Content in Poplar Leaves Using Proximal Multispectral Imaging and Regression Modeling Combined with Feature Selection.

Monitoring the biochemical pigment contents in individual plants is crucial for assessing their health statuses and physiological states. Fast, low-cost measurements of plants' biochemical traits have become feasible due to advances in multispectral imaging sensors in recent years. This study evaluated the field application of proximal multispectral imaging combined with feature selection and regressive analysis to estimate the biochemical pigment contents of poplar leaves. The combination of 6 spectral bands and 26 vegetation indices (VIs) derived from the multispectral bands was taken as the group of initial variables for regression modeling. Three variable selection algorithms, including the forward selection algorithm with correlation analysis (CORR), recursive feature elimination algorithm (RFE), and sequential forward selection algorithm (SFS), were explored as candidate methods for screening combinations of input variables from the 32 spectral-derived initial variables. Partial least square regression (PLSR) and nonlinear support vector machine regression (SVR) were both applied to estimate total chlorophyll content (Chla+b) and carotenoid content (Car) at the leaf scale. The results show that the nonlinear SVR prediction model based on optimal variable combinations, selected by SFS using multiple scatter correction (MSC) preprocessing data, achieved the best estimation accuracy and stable prediction performance for the leaf pigment content. The Chla+b and Car models developed using the optimal model had R2 and RMSE predictive statistics of 0.849 and 0.825 and 5.116 and 0.869, respectively. This study demonstrates the advantages of using a nonlinear SVR model combined with SFS variable selection to obtain a more reliable estimation model for leaf biochemical pigment content.

Enhancing optical character recognition: Efficient techniques for document layout analysis and text line detection

AbstractIn recent years, automatic document and text analysis has gained significant importance, driven by advancements in optical character recognition (OCR) technology and the need for efficient processing of large volumes of printed or handwritten documents. This article specifically focuses on document layout analysis (DLA) and text line detection (TLD), both of which are crucial components of OCR systems. Our objective is to develop an effective method for extracting both textual and non‐textual regions, addressing challenges unique to the Persian (and Persian‐like) language(s). In the DLA stage, we employ deep learning models and a voting system to accurately determine the regions of interest. Additionally, we introduce methods such as optimum font size concepts, angle correction, and a line curvature elimination algorithm in the TLD process to enhance OCR accuracy. Comparative evaluations against state‐of‐the‐art methods demonstrate the superiority of our approach, showcasing a 2.8% improvement in the accuracy of Tesseract‐OCR 5.1.0 (a well‐established commercial OCR system) on the official Iranian newspapers dataset. These findings underscore the importance of addressing DLA and TLD challenges to advance OCR technology for Persian language documents and provide a solid foundation for future research in this domain.

DOE: a dynamic object elimination scheme based on geometric and semantic constraints

In this paper, we propose a dynamic object elimination algorithm that combines semantic and geometric constraints to address the problem of visual SLAM being easily affected by dynamic feature points in dynamic environments. This issue leads to the degradation of localisation accuracy and robustness. Firstly, we employ a lightweight YOLO-Tiny network to enhance both detection accuracy and system speed. Secondly, we integrate the YOLO-Tiny network into the ORB-SLAM3 system to extract semantic information from the images and initiate the elimination of dynamic feature points. Subsequently, we augment this approach by incorporating geometric constraints between neighbouring frames to further eliminate dynamic feature points. Then, the former is supplemented by combining the geometric constraints between neighbouring frames to further eliminate dynamic feature points. Experiments on the TUM dataset demonstrate that the algorithm in this paper can improve the Relative Pose Error (RPE) by up to 95.12% and the Absolute Trajectory Error (ATE) by up to 99.01% in high dynamic sequences compared to ORB-SLAM3. The effectiveness of dynamic feature point elimination is evident, leading to significantly improved localisation accuracy.

Symbolic analysis and parameter synthesis for networks of parametric timed automata with global variables using Maude and SMT solving

This paper presents a rewriting logic “interpreter” for networks of parametric timed automata with global variables (NPTAVs) in Real-Time Maude style. Since explicit-state analysis is not sound and complete for such dense-time systems, we explain how our real-time rewrite theory can be systematically transformed into a rewrite theory that is amenable to symbolic analysis using the integration of Maude with SMT solving. We show that symbolic reachability analysis using Maude-with-SMT of the resulting rewrite theory is sound and complete for the NPTAV reachability problem. We extend and optimize standard Maude-with-SMT reachability analysis with folding and merging of symbolic states, so that the analysis terminates when the symbolic state space of the NPTAV is finite. These procedures rely on a subsumption relation that requires eliminating existentially quantified SMT variables. We have therefore implemented the Fourier-Motzkin quantifier elimination algorithm, thereby making our rewrite theory executable with any SMT solver connected to Maude. We show how we can provide most reachability and parameter synthesis analysis methods provided by Imitator, a state-of-the-art tool for NPTAVs. We compare the performance of our analysis methods with those of Imitator on a wide range of benchmarks, with the expected outcome. The practical contributions are two-fold: providing new analysis methods for NPTAVs—e.g., allowing more general state properties and supporting reachability analysis combined with user-defined execution strategies—not supported by Imitator, and developing symbolic analysis methods for both real-time rewrite theories and rewrite theories in general.

Identification and Analysis of Immune Microenvironment-Related Genes for Keloid Risk Prediction and Their Effects on Keloid Proliferation and Migration.

Keloid is a kind of proliferative scar with continuous growth, no restriction and easy recurrence, which cannot be cured and bring serious physical injury and psychological burden to patients. The main reason is that the pathological mechanism is not clear. Therefore, this project is expected to reveal the immune microenvironment-related genes and their functions in keloid progression, and provide effective targets for the treatment of keloid. Firstly, 8 kinds of immune infiltrating cells and 19 potential characteristic genes were identified by immune infiltration analysis, ssGSEA, LASSO regression (glmnet algorithm and lars algorithm) and WGCNA, indicating that keloid was closely related to the changes of immune microenvironment. Then, 4 pathological biomarkers of keloid (MAPK1, PTPRC, STAT3 and IL1R1) were identified by differentially analysis, univariate analysis, LASSO regression (lars algorithm), support vector machine recursive feature elimination (SVM-REF) algorithm, multivariate logical regression analysis and six machine learning algorithms. Based on the 4 feature genes, the risk prediction model and nomogram were constructed. Calibration curve and ROC analysis (AUC = 0.930) showed that the model had reliable clinical value. Subsequently, consistent cluster analysis was used to find that there were 2 immune microenvironment subsets in keloid patients, of which subgroup II was immune subgroup. Multiple independent datasets and RT-qPCR showed that the expression trend of the 4 genes was consistent with the analysis. Cell gain-loss experiment confirmed that 4 genes regulated the proliferation and migration of keloid cells. The above data shows that MAPK1, PTPRC, STAT3 and IL1R1 may be personalized therapeutic targets for keloid patients.

Feature Selection in House Price Prediction

This study aims to construct a model to choose effective features and use them to predict the market price of an exact house, which can help people with house pricing and property evaluating. This paper preliminarily constructs several machine learning models like Linear Regression, SVM, KNN and compares their accuracy on this problem to choose the best-fit one for improving. After using parameter tuning to optimize this model, this study tries to use and recursive feature elimination and genetic algorithm to select features to improve simple SVM model. After feature selection, this study re-evaluated the accuracy of the model and compared which features had a greater impact on the predictions. After comparison, this study found that in this particular case, features have closer connections with living condition, traffic condition and sale condition will have a huge impact on the house price.

Spatial Heterogeneity of Combined Factors Affecting Vegetation Greenness Change in the Yangtze River Economic Belt from 2000 to 2020

Vegetation greenness change is the result of the combination of natural and anthropogenic factors. Understanding how these factors individually and collectively affect vegetation dynamics and whether their spatial heterogeneity has any effect on vegetation greenness change is the crucial investigation area. Previous studies revealed the distinct characteristics of spatial and temporal heterogeneity in the impact factors influencing vegetation greenness change across various regions, often assuming a linear contribution mechanism between vegetation greenness change and these drivers. However, such a simplistic assumption fails to adequately capture the real-world dynamics of vegetation greenness change. Thus, this study firstly used geographical detector (Geodetector) to quantitatively measure the contribution of each factor to vegetation greenness change considering spatial heterogeneity in the Yangtze River Economic Belt (YREB) during the growing season from 2000 to 2020, then selecting significant factors from numerous drivers with the recursive feature elimination algorithm combined with a random forest model (RFE-RF), which is able to reduce redundant features in the data and prevent overfitting. Finally, four stable impact factors and the spatial heterogeneity of some factors contributing to vegetation greenness change were identified. The results show that approximately 83% of the regional vegetation has shown an overall increasing trend, while areas undergoing rapid development predominantly experienced a decline in greenness. Single factor screened by Geodetector with the explanatory power greater than 10% for vegetation greenness change included temperature (Tem), population density (PD), the land-use/land-cover (LULC), DEM, wind speed, and slope. The RFE-RF method identified precipitation (Pre) and CO2 emissions as additional influential factors for vegetation greenness change, in addition to the first four factors mentioned previously. These findings suggest that the four stable factors consistently influence vegetation greenness change. Combined with the principles of the algorithms and the above results, it was found that the spatial heterogeneity of wind speed and slope has an effect on vegetation greenness change, whereas the spatial heterogeneity of Pre and CO2 emissions has minimal effect.

Model of Storm Surge Maximum Water Level Increase in a Coastal Area Using Ensemble Machine Learning and Explicable Algorithm

AbstractThis study proposes a novel, new ensemble model (NEM) designed to simulate the maximum water level increases caused by storm surges in a frequently cyclone‐affected coastal water of Hong Kong, China. The model relies on storm and water level data spanning 1978–2022. The NEM amalgamates three machine learning algorithms: Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and XGBoost (XGB), employing a stacking technique for integration. Six parameters, determined using the Random Forest and Recursive Feature Elimination algorithms (RF‐RFE), are used as input features for the NEM. These parameters are the nearest wind speed, gale distance, nearest air pressure, minimum distance, maximum pressure drop within 24 hr, and large wind radius. Model assessment results suggest that the NEM exhibits superior performance over RF, GBDT, and XGB, delivering high stability and precision. It reaches a coefficient of determination (R2) up to 0.95 and a mean absolute error (MAE) that fluctuates between 0.08 and 0.20 m for the test data set. An interpretability analysis conducted using the SHapley Additive exPlanations (SHAP) method shows that gale distance and nearest wind speed are the most significant features for predicting peak water level increases during storm surges. The results of this study could provide practical implications for predictive models concerning storm surges. These findings present essential tools for the mitigation of coastal disasters and the improvement of marine disaster warning systems.

Prediction of biomarkers associated with membranous nephropathy: Bioinformatic analysis and experimental validation

Membranous nephropathy (MN), the most prevalent form of nephrotic syndrome in non-diabetic adults globally, is currently the second most prevalent and fastest-increasing primary glomerular disease in China. Numerous renal disorders are developed partly due to ferroptosis. However, its relationship to the pathogenesis of MN has rarely been investigated in previous studies; actually, ferroptosis is closely linked to the immune microenvironment and inflammatory response, which might affect the entire process of MN development. In this study, we aimed to identify ferroptosis-related genes that are potentially related to immune cell infiltration, which can further contribute to MN pathogenesis.The microarray datasets were downloaded from the Gene Expression Omnibus (GEO) database. Ferroptosis-related differentially expressed genes (FDEGs) were identified, which were further used for functional enrichment analysis. The common genes identified using the Least Absolute Shrinkage and Selection Operator (LASSO) logistic regression algorithm and the support vector machine recursive feature elimination (SVM-RFE) algorithm were used to identify the characteristic genes related to ferroptosis. The feasibility of the 7 genes as a distinguishing factor was assessed using the receiver operating characteristic (ROC) curve, with the area under the curve (AUC) score serving as the evaluation metric. Gene set enrichment analysis (GSEA) and correlation analysis of these genes were further performed. The correlation between the expression of these genes and immune cell infiltration inferred by single sample gene set enrichment analysis (ssGSEA) algorithm was explored. As a result, 7 genes, including NR1D1, YTHDC2, EGR1, ZFP36, RRM2, RELA and PDK4, which were most relevant to immune cell infiltration, were identified to be potential diagnostic genes in MN patients. Next, the signature genes were validated with other GEO datasets. In the subsequent steps, we conducted quantitative real-time fluorescence PCR (qRT-PCR) analysis and immunohistochemistry (IHC) method on the cationic bovine serum albumin (C-BSA) induced membranous nephropathy (MN) rat model and the passive Heymann nephritis (pHN) rat model to examine characteristic genes. Finally, we analysed the mRNA expression patterns of hub genes in MN patients and normal controls using the Nephroseq V5 online platform. In concise terms, our study successfully identified biomarkers specific to MN patients and delved into the potential interplay between these markers and immune cell infiltration. This knowledge bears significance for the diagnosis and prospective treatment strategies for individuals affected by MN.

Development and validation of a machine learning model to predict the use of renal replacement therapy in 14,374 patients with COVID-19

PurposeTo develop a model to predict the use of renal replacement therapy (RRT) in COVID-19 patients. Materials and methodsRetrospective analysis of multicenter cohort of intensive care unit (ICU) admissions of Brazil involving COVID-19 critically adult patients, requiring ventilatory support, admitted to 126 Brazilian ICUs, from February 2020 to December 2021 (development) and January to May 2022 (validation). No interventions were performed. ResultsEight machine learning models' classifications were evaluated. Models were developed using an 80/20 testing/train split ratio and cross-validation. Thirteen candidate predictors were selected using the Recursive Feature Elimination (RFE) algorithm. Discrimination and calibration were assessed. Temporal validation was performed using data from 2022. Of 14,374 COVID-19 patients with initial respiratory support, 1924 (13%) required RRT. RRT patients were older (65 [53-75] vs. 55 [42-68]), had more comorbidities (Charlson's Comorbidity Index 1.0 [0.00-2.00] vs 0.0 [0.00-1.00]), had higher severity (SAPS-3 median: 61 [51-74] vs 48 [41-58]), and had higher in-hospital mortality (71% vs 22%) compared to non-RRT. Risk factors for RRT, such as Creatinine, Glasgow Coma Scale, Urea, Invasive Mechanical Ventilation, Age, Chronic Kidney Disease, Platelets count, Vasopressors, Noninvasive Ventilation, Hypertension, Diabetes, modified frailty index (mFI) and Gender, were identified. The best discrimination and calibration were found in the Random Forest (AUC [95%CI]: 0.78 [0.75-0.81] and Brier's Score: 0.09 [95%CI: 0.08–0.10]). The final model (Random Forest) showed comparable performance in the temporal validation (AUC [95%CI]: 0.79 [0.75–0.84] and Brier's Score, 0.08 [95%CI: 0.08-0.1]). ConclusionsAn early ML model using easily available clinical and laboratory data accurately predicted the use of RRT in critically ill patients with COVID-19. Our study demonstrates that using ML techniques is feasible to provide early prediction of use of RRT in COVID-19 patients.

A Multi-Sensor Stochastic Energy-Based Vibro-Localization Technique with Byzantine Sensor Elimination.

This paper presents an occupant localization technique that determines the location of individuals in indoor environments by analyzing the structural vibrations of the floor caused by their footsteps. Structural vibration waves are difficult to measure as they are influenced by various factors, including the complex nature of wave propagation in heterogeneous and dispersive media (such as the floor) as well as the inherent noise characteristics of sensors observing the vibration wavefronts. The proposed vibration-based occupant localization technique minimizes the errors that occur during the signal acquisition time. In this process, the likelihood function of each sensor-representing where the occupant likely resides in the environment-is fused to obtain a consensual localization result in a collective manner. In this work, it becomes evident that the above sources of uncertainties can render certain sensors deceptive, commonly referred to as "Byzantines." Because the ratio of Byzantines among the set sensors defines the success of the collective localization results, this paper introduces a Byzantine sensor elimination (BSE) algorithm to prevent the unreliable information of Byzantine sensors from affecting the location estimations. This algorithm identifies and eliminates sensors that generate erroneous estimates, preventing the influence of these sensors on the overall consensus. To validate and benchmark the proposed technique, a set of previously conducted controlled experiments was employed. The empirical results demonstrate the proposed technique's significant improvement (3~0%) over the baseline approach in terms of both accuracy and precision.

Identification of key genes and their correlation with immune infiltration in osteoarthritis using integrative bioinformatics approaches and machine-learning strategies.

Osteoarthritis (OA) is a common degenerative joint disease and is closely associated with chronic, low-grade inflammation. Regulating ferroptosis by targeting ferroptosis-related genes may be a fast and effective way to delay the degeneration of OA. However, the molecular mechanisms and gene targets related to ferroptosis in OA are still unclear. Data of OA samples from 3 gene expression omnibus (GEO) datasets were combined to identify differentially expressed genes (DEGs). Ferroptosis-related genes (FRGs) retrieved by the Ferroptosis database were intersected with DEGs, and the intersected hub genes were used for functional enrichment analysis. The feature genes were obtained from the least absolute shrinkage and selection operator (LASSO) algorithm, support vector machine recursive feature elimination (SVM-RFE) algorithm, and random forest (RF) algorithm. Single sample gene set enrichment analysis (ssGSEA) was used to compare immune infiltration between OA patients and normal controls, and the correlation between feature genes and immune cells was analyzed. The expression levels of feature genes were confirmed by RT-PCR. In addition, to explore the applicability of these genes, we extended the bioinformatics analysis of these feature genes to cancer. Finally, 4 feature genes, GABARAPL1, TNFAIP3, ARNTL, and JUN, were confirmed in OA. Theirs expression level were validated by RT-PCR. ROC curves of the 4 genes exhibit excellent diagnostic efficiency for OA, suggesting that the 4 genes were associated with the pathogenesis of OA. Another GEO dataset validated this result. Further analysis revealed that the 4 feature genes were all closely related to the immune infiltration cells in OA. Additionally, results of prognosis analysis indicated that JUN might be a promising therapeutic target for cancer. GABARAPL1, TNFAIP3, ARNTL, and JUN may be predicted biomarkers for OA. The feature genes and association between feature genes and immune infiltration may provide potential biomarkers for OA prediction along with the better assessment of the disease.