Macroeconomic attention and stock market return predictability

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.

Multiple imputation (MI) is a commonly used technique for handling missing data in large-scale medical and public health studies. However, variable selection on multiply-imputed data remains an important and longstanding statistical problem. If a variable selection method is applied to each imputed dataset separately, it may select different variables for different imputed datasets, which makes it difficult to interpret the final model or draw scientific conclusions. In this paper, we propose a novel multiple imputation-least absolute shrinkage and selection operator (MI-LASSO) variable selection method as an extension of the least absolute shrinkage and selection operator (LASSO) method to multiply-imputed data. The MI-LASSO method treats the estimated regression coefficients of the same variable across all imputed datasets as a group and applies the group LASSO penalty to yield a consistent variable selection across multiple-imputed datasets. We use a simulation study to demonstrate the advantage of the MI-LASSO method compared with the alternatives. We also apply the MI-LASSO method to the University of Michigan Dioxin Exposure Study to identify important circumstances and exposure factors that are associated with human serum dioxin concentration in Midland, Michigan.

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.

For achieving high separation efficiency and a large throughput in the nuclear fuel reprocessing industry, it is crucial to have a profound understanding of the flooding characteristics in pulsed disc and doughnut extraction columns (PDDCs). For this purpose, the least absolute shrinkage and selection operator (LASSO) method was utilized to obtain predictive equations that provide high applicability and analytical convenience. The effects of three operating conditions (dispersed-phase velocity, continuous-phase velocity, and pulse intensity) on the hydrodynamic parameters (dispersed phase holdup, slip velocity, characteristic velocity, and flooding point) were studied in a Φ50 PDDC in the kerosene-water system. The LASSO method was applied to select highly correlated features of the hydrodynamic parameters and to propose second-order prediction equations. The effectiveness of LASSO was also compared to the published correlations and traditional linear regression. The second-order-regression of LASSO produced more intuitive prediction equations with the mean relative error within 15%. The impact of each operating variable on the hydrodynamic parameters was quantitatively analyzed by calculating the partial derivatives of these prediction equations. The dispersed-phase flow rate predominantly affects the holdup within the operating conditions. Pulse intensity emerges as the primary factor affecting slip velocity, characteristic velocity, and flooding throughput.

Preoperative prognostication of 30-day mortality in patients with carotid endarterectomy (CEA) can optimize surgical risk stratification and guide the decision-making process to improve survival. This study aims to develop and validate a set of predictive variables of 30-day mortality following CEA. The patient cohort was identified from the American College of Surgeons National Surgical Quality Improvement Program (2005-2016). We performed logistic regression (enter, stepwise, and forward) and least absolute shrinkage and selection operator (LASSO) method for the selection of variables, which resulted in 28-candidate models. The final model was selected based upon clinical knowledge and numerical results. Statistical analysis included 65,807 patients with 30-day mortality in 0.7% (n = 466) patients. The median age of our cohort was 71.0years (range, 16-89years). The model with 9 predictive factors which included age, body mass index, functional health status, American Society of Anesthesiologist grade, chronic obstructive pulmonary disorder, preoperative serum albumin, preoperative hematocrit, preoperative serum creatinine, and preoperative platelet count-performed best on discrimination, calibration, Brier score, and decision analysis to develop a machine learning algorithm. Logistic regression showed higher AUCs than LASSO across these different models. The predictive probability derived from the best model was converted into an open-accessible scoring system. Machine learning algorithms show promising results for predicting 30-day mortality following CEA. These algorithms can be useful aids for counseling patients, assessing preoperative medical risks, and predicting survival after surgery.

The aim of this study was to develop and validate a method of disease classification for bipolar disorder (BD) by functional activity and connectivity using radiomics analysis. Ninety patients with unmedicated BD II as well as 117 healthy controls underwent resting-state functional magnetic resonance imaging (rs-fMRI). A total of 4 types of 7018 features were extracted after preprocessing, including mean regional homogeneity (mReHo), mean amplitude of low-frequency fluctuation (mALFF), resting-state functional connectivity (RSFC), and voxel-mirrored homotopic connectivity (VMHC). Then, predictive features were selected by Mann-Whitney U test and removing variables with a high correlation. Least absolute shrinkage and selection operator (LASSO) method was further used to select features. At last, support vector machine (SVM) model was used to estimate the state of each subject based on the selected features after LASSO. Sixty-five features including 54 RSFCs, 7 mALFFs, 1 mReHo, and 3 VMHCs were selected. The accuracy and area under curve (AUC) of the SVM model built based on the 65 features is 87.3% and 0.919 in the training dataset, respectively, and the accuracy and AUC of this model validated in the validation dataset is 80.5% and 0.838, respectively. These findings demonstrate a valid radiomics approach by rs-fMRI can identify BD individuals from healthy controls with a high classification accuracy, providing the potential adjunctive approach to clinical diagnostic systems.

Genomic selection holds a great promise to accelerate plant breeding via early selection before phenotypes are measured, and it offers major advantages over marker-assisted selection for highly polygenic traits. In addition to genomic data, metabolome and transcriptome are increasingly receiving attention as new data sources for phenotype prediction. We used data available from maize as a model to compare the predictive abilities of three different omic data sources using eight representative methods for six traits. We found that the best linear unbiased prediction overall performs better than other methods across different traits and different omic data, and genomic prediction performs better than transcriptomic and metabolomic predictions. For the same maize data, we also conducted genome-wide association study, transcriptome-wide association studies and metabolome-wide association studies for the six agronomic traits using both the genome-wide efficient mixed model association (GEMMA) method and a modified least absolute shrinkage and selection operator (LASSO) method. The new LASSO method has the ability to perform statistical tests. Simulation studies show that the modified LASSO performs better than GEMMA in terms of high power and low Type 1 error.

A radiomics feature-based nomogram to predict telomerase reverse transcriptase promoter mutation status and the prognosis of lower-grade gliomas

To compare machine learning (ML) to traditional models to predict radiographic progression in patients with early axial spondyloarthritis (axSpA). We carried out a prospective French multicentric DESIR cohort study with 5 years of follow-up that included patients with chronic back pain for <3 years, suggestive of axSpA. Radiographic progression was defined as progression at the spine (increase of at least 1 point of mSASSS scores/2 years) or at the sacroiliac joint (worsening of at least one grade of the mNY score between 2 visits). Statistical analyses were based on patients without any missing data regarding the outcome and variables of interest (295 patients).Traditional modelling: we performed a multivariate logistic regression model (M1); then variable selection with stepwise selection based on Akaike Information Criterion (stepAIC) method (M2), and Least Absolute Shrinkage and Selection Operator (LASSO) method (M3).ML modelling: using "SuperLearner" package on R, we modelled radiographic progression with stepAIC, LASSO, random forest, Discrete Bayesian Additive Regression Trees Samplers (DBARTS), Generalized Additive Models (GAM), multivariate adaptive polynomial spline regression (polymars), Recursive Partitioning And Regression Trees (RPART) and Super Learner. Accuracy of these models was compared based on their 10-fold cross-validated AUC (cv-AUC). 10-fold cv-AUC for traditional models were 0.79 and 0.78 for M2 and M3, respectively. The three best models in the ML algorithms were the GAM, the DBARTS and the Super Learner models, with 10-fold cv-AUC of: 0.77, 0.76 and 0.74, respectively. Two traditional models predicted radiographic progression as good as the eight ML models tested in this population.

Lung cancer is one of the most common contributors to cancer-related deaths worldwide. This study aimed to develop a new blood index on the basis of the patient's systemic inflammation and nutritional status, which can be used to predict the prognosis of patients with non-small cell lung cancer (NSCLC). Pre-treatment blood markers were analyzed in 556 NSCLC patients from 2010 to 2019. A least absolute shrinkage and selection operator (LASSO) method was used to select indicators to establish a new integrated biomarker (PNAGR). Kaplan-Meier survival curves were used to assess the prognostic impact of platelet-to-lymphocyte ratio (PLR), albumin (ALB), and the PNAGR. The prognostic value was verified using univariate and multivariate Cox analyses. We used four biomarkers including PLR, ALB, 1/albumin-to-globulin ratio (1/AGR), and neutrophil/albumin-to-globulin ratio (N/AGR) were used to screen for the PNAGR using LASSO. Patients with high PNAGR demonstrated lower overall survival (OS) compared to those with low PNAGR. In both univariate and multivariate analyses, PNAGR was revealed as an independent prognostic factor for OS. The predictive power of PNAGR [area under the curve (AUC): 0.753] was higher than that of the metrics alone. PNAGR is a novel and effective clinical prognostic tool with good clinical predictive value for NSCLC patients.

Background Lean individuals with non-alcohol fatty liver disease (NAFLD) often have normal body size but abnormal visceral fat. Therefore, an alternative to body mass index should be considered for prediction of lean-NAFLD. This study aimed to use representative visceral fat links with other laboratory parameters using the least absolute shrinkage and selection operator (LASSO) method to construct a predictive model for lean-NAFLD. Methods This retrospective cross-sectional analysis enrolled 2325 subjects with BMI < 24 kg/m2 from medical records of 51,271 examinees who underwent a routine health check-up. They were randomly divided into training and validation cohorts at a ratio of 1:1. The LASSO-derived prediction model used LASSO regression to select 23 clinical and laboratory factors. The discrimination and calibration abilities were evaluated using the Hosmer–Lemeshow test and calibration curves. The performance of the LASSO model was compared with the fatty liver index (FLI) model. Results The LASSO-derived model included four variables—visceral fat, triglyceride levels, HDL-C-C levels, and waist hip ratio—and demonstrated superior performance in predicting lean-NAFLD with high discriminatory ability (AUC, 0.8416; 95% CI: 0.811–0.872) that was comparable with the FLI model. Using a cut-off of 0.1484, moderate sensitivity (75.69%) and specificity (79.86%), as well as high negative predictive value (95.9%), were achieved in the LASSO model. In addition, with normal WC subgroup analysis, the LASSO model exhibits a trend of higher accuracy compared to FLI (cut-off 15.45). Conclusions We developed a LASSO-derived predictive model with the potential for use as an alternative tool for predicting lean-NAFLD in clinical settings.

Recent research has documented the dramatic increase in idiosyncratic risk and the under-diversification of portfolios.We provide a unique marketing perspective to the financial risk management literature by suggesting that idiosyncratic volatility can be reduced by enhancing marketing, operational and R&D capabilities.We investigate the relationship between idiosyncratic risk, firm capabilities and financial control variables using the least absolute selection and shrinkage operator (LASSO) -a penalty-based variable selection and shrinkage technique developed in the context of 'machine learning' and 'big data' that has not been much used in the empirical marketing literature.Our results differ from those reported in the literature.Using the more stringent criterion imposed by the LASSO, we find that whereas R&D, marketing and operational capabilities have no statistically significant individual effects, the interactive effects between marketing capability and R&D intensity have a significant effect on reducing idiosyncratic risk.

Alfalfa (Medicago sativa L.) crop vigor and yield characterization using high-resolution aerial multispectral and thermal infrared imaging technique

Novel risk factors for venous thromboembolism following outpatient or inpatient transurethral resection of bladder tumors: Multivariable stepwise and LASSO regression modeling from us insurance claim database.

Analyzing Risk Factors for Morbidity and Mortality after Lung Resection for Lung Cancer Using the NSQIP Database