A LASSO-based batch process modeling and end-product quality prediction method

Prediction system is one of the tools that can support business decision making. However, existing prediction systems often give high error rate and high computational complexity. In order to make an accurate prediction system while reducing computational complexity, we proposed works that combines multi-layered clustering model using k-means++ as a technique to model data, and feature selection LASSO to predict variables. K-means++ is chosen as clustering method because of its simplicity and its solution through poor initialization, while LASSO is chosen as feature selection because of its good accuracy and its linear nature that cause model complexity to be simpler than non-linear feature selection. First, k-means++ is applied in each layer, then centroids from each layer are transferred into a central processor. Next, a set of centroids is then proceeded using feature selection LASSO to predict variable. Simulation results show that the proposed prediction system has given a good prediction accuracy with MAPE 23.45% and has reduced computational complexity by 89.77%.

Variable selection in genome-wide association studies can be a daunting task and statistically challenging because there are more variables than subjects. We propose an approach that uses principal-component analysis (PCA) and least absolute shrinkage and selection operator (LASSO) to identify gene-gene interaction in genome-wide association studies. A PCA was used to first reduce the dimension of the single-nucleotide polymorphisms (SNPs) within each gene. The interaction of the gene PCA scores were placed into LASSO to determine whether any gene-gene signals exist. We have extended the PCA-LASSO approach using the bootstrap to estimate the standard errors and confidence intervals of the LASSO coefficient estimates. This method was compared to placing the raw SNP values into the LASSO and the logistic model with individual gene-gene interaction. We demonstrated these methods with the Genetic Analysis Workshop 16 rheumatoid arthritis genome-wide association study data and our results identified a few gene-gene signals. Based on our results, the PCA-LASSO method shows promise in identifying gene-gene interactions, and, at this time we suggest using it with other conventional approaches, such as generalized linear models, to narrow down genetic signals.

We consider the problem of predicting survival times of cancer patients from the gene expression profiles of their tumor samples via linear regression modeling of log-transformed failure times. The partial least squares (PLS) and least absolute shrinkage and selection operator (LASSO) methodologies are used for this purpose where we first modify the data to account for censoring. Three approaches of handling right censored data-reweighting, mean imputation, and multiple imputation-are considered. Their performances are examined in a detailed simulation study and compared with that of full data PLS and LASSO had there been no censoring. A major objective of this article is to investigate the performances of PLS and LASSO in the context of microarray data where the number of covariates is very large and there are extremely few samples. We demonstrate that LASSO outperforms PLS in terms of prediction error when the list of covariates includes a moderate to large percentage of useless or noise variables; otherwise, PLS may outperform LASSO. For a moderate sample size (100 with 10,000 covariates), LASSO performed better than a no covariate model (or noise-based prediction). The mean imputation method appears to best track the performance of the full data PLS or LASSO. The mean imputation scheme is used on an existing data set on lung cancer. This reanalysis using the mean imputed PLS and LASSO identifies a number of genes that were known to be related to cancer or tumor activities from previous studies.

Features and interaction between features of liver disease is of great significance for the classification of liver disease. Based on least absolute shrinkage and selection operator (LASSO) and interaction LASSO, the generalized interaction LASSO model is proposed in this paper for liver disease classification and compared with other methods. Firstly, the generalized interaction logistic classification model was constructed and the LASSO penalty constraints were added to the interactive model parameters. Then the model parameters were solved by an efficient alternating directions method of multipliers (ADMM) algorithm. The solutions of model parameters were sparse. Finally, the test samples were fed to the model and the classification results were obtained by the largest statistical probability. The experimental results of liver disorder dataset and India liver dataset obtained by the proposed methods showed that the coefficients of interaction features of the model were not zero, indicating that interaction features were contributive to classification. The accuracy of the generalized interaction LASSO method is better than that of the interaction LASSO method, and it is also better than that of traditional pattern recognition methods. The generalized interaction LASSO method can also be popularized to other disease classification areas.

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.

Undernutrition among children under the age of five is a major public health concern, especially in developing countries. This study aimed to use machine learning (ML) algorithms to predict undernutrition and identify its associated factors. Secondary data analysis of the 2017 Multiple Indicator Cluster Survey (MICS) was performed using R and Python. The main outcomes of interest were undernutrition (stunting: height-for-age (HAZ) < -2 SD; wasting: weight-for-height (WHZ) < -2 SD; and underweight: weight-for-age (WAZ) < -2 SD). Seven ML algorithms were trained and tested: linear discriminant analysis (LDA), logistic model, support vector machine (SVM), random forest (RF), least absolute shrinkage and selection operator (LASSO), ridge regression, and extreme gradient boosting (XGBoost). The ML models were evaluated using the accuracy, confusion matrix, and area under the curve (AUC) receiver operating characteristics (ROC). In total, 8564 children were included in the final analysis. The average age of the children was 926 days, and the majority were females. The weighted prevalence rates of stunting, wasting, and underweight were 17%, 7%, and 12%, respectively. The accuracies of all the ML models for wasting were (LDA: 84%; Logistic: 95%; SVM: 92%; RF: 94%; LASSO: 96%; Ridge: 84%, XGBoost: 98%), stunting (LDA: 86%; Logistic: 86%; SVM: 98%; RF: 88%; LASSO: 86%; Ridge: 86%, XGBoost: 98%), and for underweight were (LDA: 90%; Logistic: 92%; SVM: 98%; RF: 89%; LASSO: 92%; Ridge: 88%, XGBoost: 98%). The AUC values of the wasting models were (LDA: 99%; Logistic: 100%; SVM: 72%; RF: 94%; LASSO: 99%; Ridge: 59%, XGBoost: 100%), for stunting were (LDA: 89%; Logistic: 90%; SVM: 100%; RF: 92%; LASSO: 90%; Ridge: 89%, XGBoost: 100%), and for underweight were (LDA: 95%; Logistic: 96%; SVM: 100%; RF: 94%; LASSO: 96%; Ridge: 82%, XGBoost: 82%). Age, weight, length/height, sex, region of residence and ethnicity were important predictors of wasting, stunting and underweight. The XGBoost model was the best model for predicting wasting, stunting, and underweight. The findings showed that different ML algorithms could be useful for predicting undernutrition and identifying important predictors for targeted interventions among children under five years in Ghana.

We present a framework for hyperspectral image (HSI) analysis validation, specifically abundance fraction estimation based on HSI measurements of water soluble dye mixtures printed on microarray chips. In our work we focus on the performance of two algorithms, the Least Absolute Shrinkage and Selection Operator (LASSO) and the Spatial LASSO (SPLASSO). The LASSO is a well known statistical method for simultaneously performing model estimation and variable selection. In the context of estimating abundance fractions in a HSI scene, the “sparse” representations provided by the LASSO are appropriate as not every pixel will be expected to contain every endmember. The SPLASSO is a novel approach we introduce here for HSI analysis which takes the framework of the LASSO algorithm a step further and incorporates the rich spatial information which is available in HSI to further improve the estimates of abundance. In our work here we introduce the dye mixture platform as a new benchmark data set for hyperspectral biomedical image processing and show our algorithm’s improvement over the standard LASSO.

Exosomal lipids for classifying early and late stage non-small cell lung cancer

BackgroundCOVID-19 pandemic has forced physicians to quickly determine the patient’s condition and choose treatment strategies. This study aimed to build and validate a simple tool that can quickly predict the deterioration and survival of COVID-19 patients.MethodsA total of 351 COVID-19 patients admitted to the Third People’s Hospital of Yichang between 9 January to 25 March 2020 were retrospectively analyzed. Patients were randomly grouped into training (n = 246) or a validation (n = 105) dataset. Risk factors associated with deterioration were identified using univariate logistic regression and least absolute shrinkage and selection operator (LASSO) regression. The factors were then incorporated into the nomogram. Kaplan-Meier analysis was used to compare the survival of patients between the low- and high-risk groups divided by the cut-off point.ResultsThe least absolute shrinkage and selection operator (LASSO) regression was used to construct the nomogram via four parameters (white blood cells, C-reactive protein, lymphocyte≥0.8 × 109/L, and lactate dehydrogenase ≥400 U/L). The nomogram showed good discriminative performance with the area under the receiver operating characteristic (AUROC) of 0.945 (95% confidence interval: 0.91–0.98), and good calibration (P = 0.539). Besides, the nomogram showed good discrimination performance and good calibration in the validation and total cohorts (AUROC = 0.979 and AUROC = 0.954, respectively). Decision curve analysis demonstrated that the model had clinical application value. Kaplan-Meier analysis illustrated that low-risk patients had a significantly higher 8-week survival rate than those in the high-risk group (100% vs 71.41% and P < 0.0001).ConclusionA simple-to-use nomogram with excellent performance in predicting deterioration risk and survival of COVID-19 patients was developed and validated. However, it is necessary to verify this nomogram using a large-scale multicenter study.

Esophageal squamous cell carcinoma (ESCC) is the most common pathological type of esophageal malignancy in most regions of the world. The study aimed to identify risk factors and develop a predictive model for ESCC following surgical resection. A total of 533 ESCC patients who underwent surgical resection from Suining Central Hospital were enrolled in the study. Cox proportional hazards regression and Least Absolute Shrinkage and Selection Operator (LASSO) regression were performed to identify significant prognostic factors. A prognostic model was constructed, and the receiver operating characteristic (ROC) curve, concordance index (C-index), and decision cure analysis (DCA) were used to evaluate the discrimination and calibration of the prognostic model. Subsequently, we built a nomogram for overall survival (OS) incorporating the prognostic factors, and a calibration plot was employed to assess the consistency between the predicted survival and the observed survival. Based on the model risk score, we split the patients into two subgroups, low-risk and high-risk, and we analyzed the survival time of these two groups using Kaplan-Meier (K-M) survival plots. Five independent prognosis factors were identified as independent risk factors for OS in ESCC patients who underwent surgical resection. The C-index, ROC curve, and DCA showed that the prognostic model had good predictive accuracy and discriminatory power in the training cohort and validation cohort than other clinical features. A nomogram consisting of prognosis factors showed some superior net benefit. K-M survival plots showed significant differences in OS between the low-risk and high-risk groups. Similar results were observed in the subgroup analysis based on age, grade, and stage. Univariate and multivariate Cox regression analyses revealed that both risk score and risk group are independent prognostic factors in the patient cohort. This study put forward a novel prognostic model based on clinical features; biopsy data and blood biomarkers may represent a promising tool for estimating OS in ESCC patients.

Many tree algorithms have been developed for regression problems. Although they are regarded as good algorithms, most of them suffer from loss of prediction accuracy when there are many irrelevant variables and the number of predictors exceeds the number of observations. We propose the multistep regression tree with adaptive variable selection to handle this problem. The variable selection step and the fitting step comprise the multistep method. The multistep generalized unbiased interaction detection and estimation (GUIDE) with adaptive forward selection (fg) algorithm, as a variable selection tool, performs better than some of the well-known variable selection algorithms such as efficacy adaptive regression tube hunting (EARTH), FSR (false selection rate), LSCV (least squares cross-validation), and LASSO (least absolute shrinkage and selection operator) for the regression problem. The results based on simulation study show that fg outperforms other algorithms in terms of selection result and computation time. It generally selects the important variables correctly with relatively few irrelevant variables, which gives good prediction accuracy with less computation time.

In Hubei, China, where the coronavirus disease (COVID-19) epidemic first emerged, the government has enforced strict quarantine and lockdown measures. Longitudinal studies suggest that the impact of adverse events on psychological adjustment is highly heterogenous. To better understand protective and risk factors that predict longitudinal psychopathology and resilience following strict COVID-19 lockdowns, this study used unsupervised machine learning to identify half-year longitudinal trajectories (April, June, August, and October, 2020) of three mental health outcomes (depression, anxiety, and posttraumatic stress disorder [PTSD]) among a sample of Hubei residents (N = 326), assessed a broad range of person- and context-level predictors, and applied least absolute shrinkage and selection operator (LASSO) logistic regression, a supervised machine learning approach, to select best predictors for trajectory memberships of resilience and chronic psychopathology. Across outcomes, most individuals remained resilient. Models with both person- and context-level predictors showed excellent predictive accuracy, except for models predicting chronic anxiety. The person-level models showed either good or excellent predictive accuracy. The context-level models showed good predictive accuracy for depression trajectories but were only fair in predicting trajectories of anxiety and PTSD. Overall, the most critical person-level predictors were worry, optimism, fear of COVID, and coping flexibility, whereas important context-level predictors included features of stressful life events, community satisfaction, and family support. This study identified clinical patterns of response to COVID-19 lockdowns and used a combination of risk and protective factors to accurately differentiate these patterns. These findings have implications for clinical risk identifications and interventions in the context of potential trauma. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Objectives This research aims to explore the relationship between glutathione peroxidase (GPX) expression variations in papillary renal cell carcinoma (pRCC) and patient survival, while also developing and evaluating a customized survival prediction model based on GPX. Methods The transcriptomic dataset, including clinical parameters and GPX expression levels, is sourced from The Cancer Genome Atlas (TCGA) database, comprising 290 individuals diagnosed with pRCC. We utilized a univariate Cox regression model to select differentially expressed genes. Subsequently, we calculated risk scores through the least absolute shrinkage and selection operator (LASSO) regression. Based on the median risk score, patients were categorized into high and low-risk groups, establishing a prognostic risk model. Following this, the relationship between the risk model and the survival of pRCC patients was revealed through Kaplan–Meier survival curve analysis. The sensitivity and specificity of the predictive model were evaluated using receiver operating characteristic (ROC) curve analysis. Furthermore, chemotherapy drug sensitivity analysis was conducted on patients in the high and low-risk groups. Results A risk-scoring model was built by selecting GPX7 and GPX8. Compared to the low-risk group, individuals in the high-risk category showed significantly reduced overall survival rates (p=0.018). Additionally, validation results demonstrated the model’s good predictive accuracy. Conclusions The risk-scoring model constructed based on GPX family genes provides an innovative biomarker for forecasting the prognosis of pRCC and serves as a reference for individualized therapy in pRCC.

The successful use of machine learning (ML) for medical diagnostic purposes has prompted myriad applications in cancer image analysis. Particularly for hepatocellular carcinoma (HCC) grading, there has been a surge of interest in ML-based selection of the discriminative features from high-dimensional magnetic resonance imaging (MRI) radiomics data. As one of the most commonly used ML-based selection methods, the least absolute shrinkage and selection operator (LASSO) has high discriminative power of the essential feature based on linear representation between input features and output labels. However, most LASSO methods directly explore the original training data rather than effectively exploiting the most informative features of radiomics data for HCC grading. To overcome this limitation, this study marks the first attempt to propose a feature selection method based on LASSO with dictionary learning, where a dictionary is learned from the training features, using the Fisher ratio to maximize the discriminative information in the feature. This study proposes a LASSO method with dictionary learning to ensure the accuracy and discrimination of feature selection. Specifically, based on the Fisher ratio score, each radiomic feature is classified into two groups: the high-information and the low-information group. Then, a dictionary is learned through an optimal mapping matrix to enhance the high-information part and suppress the low discriminative information for the task of HCC grading. Finally, we select the most discrimination features according to the LASSO coefficients based on the learned dictionary. The experimental results based on two classifiers (KNN and SVM) showed that the proposed method yielded accuracy gains, compared favorably with another 5 state-of-the-practice feature selection methods.

PurposeThis paper develops a robust hospital readmission prediction framework by combining the feature selection algorithm and machine learning (ML) classifiers. The improved feature selection is proposed by considering the uncertainty in patient's attributes that leads to the output variable.Design/methodology/approachFirst, data preprocessing is conducted which includes how raw data is managed. Second, the impactful features are selected through feature selection process. It started with calculating the relational grade of each patient towards readmission using grey relational analysis (GRA) and the grade is used as the target values for feature selection. Then, the influenced features are selected using the Least Absolute Shrinkage and Selection Operator (LASSO) method. This proposed method is termed as Grey-LASSO feature selection. The final task is the readmission prediction using ML classifiers.FindingsThe proposed method offered good performances with a minimum feature subset up to 54–65% discarded features. Multi-Layer Perceptron with Grey-LASSO gave the best performance.Research limitations/implicationsThe performance of Grey-LASSO is justified in two readmission datasets. Further research is required to examine the generalisability to other datasets.Originality/valueIn designing the feature selection algorithm, the selection on influenced input variables was based on the integration of GRA and LASSO. Specifically, GRA is a part of the grey system theory, which was employed to analyse the relation between systems under uncertain conditions. The LASSO approach was adopted due to its ability for sparse data representation.