Prognostic Value of mRNAsi/Corrected mRNAsi Calculated by the One-Class Logistic Regression Machine-Learning Algorithm in Glioblastoma Within Multiple Datasets.
Ontology highlight
ABSTRACT:
SUBMITTER: Zhang M
PROVIDER: S-EPMC8685528 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Variable or feature selection is one of the most important steps in model specification. Especially in the case of medical-decision making, the direct use of a medical database, without a previous analysis and preprocessing step, is often counterproductive. In this way, the variable selection represents the method of choosing the most relevant attributes from the database in order to build a robust learning models and, thus, to improve the performance of the models used in the decision process. In biomedical research, the purpose of variable selection is to select clinically important and statistically significant variables, while excluding unrelated or noise variables. A variety of methods exist for variable selection, but none of them is without limitations. For example, the stepwise approach, which is highly used, adds the best variable in each cycle generally producing an acceptable set of variables. Nevertheless, it is limited by the fact that it commonly trapped in local optima. The best subset approach can systematically search the entire covariate pattern space, but the solution pool can be extremely large with tens to hundreds of variables, which is the case in nowadays clinical data. Genetic algorithms (GA) are heuristic optimization approaches and can be used for variable selection in multivariable regression models. This tutorial paper aims to provide a step-by-step approach to the use of GA in variable selection. The R code provided in the text can be extended and adapted to other data analysis needs.
| S-EPMC5879502 | biostudies-literature
Project description:We develop a Bayesian variable selection method for logistic regression models that can simultaneously accommodate qualitative covariates and interaction terms under various heredity constraints. We use expectation-maximization variable selection (EMVS) with a deterministic annealing variant as the platform for our method, due to its proven flexibility and efficiency. We propose a variance adjustment of the priors for the coefficients of qualitative covariates, which controls false-positive rates, and a flexible parameterization for interaction terms, which accommodates user-specified heredity constraints. This method can handle all pairwise interaction terms as well as a subset of specific interactions. Using simulation, we show that this method selects associated covariates better than the grouped LASSO and the LASSO with heredity constraints in various exploratory research scenarios encountered in epidemiological studies. We apply our method to identify genetic and non-genetic risk factors associated with smoking experimentation in a cohort of Mexican-heritage adolescents.
| S-EPMC5935273 | biostudies-literature
Project description:BackgroundGlioma is the most common primary intracranial tumor with poor prognosis. The prediction of glioma prognosis has not been well investigated. XGBoost algorithm has been widely used in and data analysis. The predictive value of XGBoost algorithm in glioma remains unclear. This current study used the XGBoost algorithm to construct a predictive model for postoperative outcomes of glioma patients.MethodsPatients with glioma who underwent surgery from January 2006 to April 2017 were retrospectively included in this study. Clinical and follow-up data were collected. The XGBoost model and multivariate logistic regression analysis model were used to screen the factors related to postoperative outcomes, and the results of the two models were compared. The area under the receiver operating characteristic (ROC) curve (AUC), sensitivity, specificity, and Youden index were calculated to evaluate the predictive value of the XGBoost model.ResultsA total of 638 patients were included. In total, 336 (52.7%) cases died within 5 years after the operation. Multivariate logistic regression analysis showed that age, gender, World Health Organization (WHO) grade, extent of tumor resection, Karnofsy performance score (KPS), tumor diameter, and whether postoperative radiotherapy and chemotherapy were administered, were the most important risk factors for death within 5 years after surgery in glioma patients. The XGBoost model showed that the top 5 factors related to death of glioma patients within 5 years after surgery were WHO grade (30 points), extent of tumor resection (19 points), postoperative radiotherapy and chemotherapy (16 points), KPS (14 points), and age (11 points). The AUC of the XGBoost model for predicting the death of glioma patients within 5 years after surgery was 0.803 [95% confidence interval (CI): 0.718-0.832], and the sensitivity and specificity were 0.894 and 0.581, respectively. The Youden index was 0.475. The AUC of the multivariate logistic regression model was 0.738 (95% CI: 0.704-0.781), the sensitivity and specificity were 0.785 and 0.632, respectively, and the Youden index was 0.417.ConclusionsCompared with multivariate logistic regression model, XGBoost model has better performance in predicting the risk of death within 5 years after surgery in patients with glioma.
| S-EPMC9469144 | biostudies-literature
Project description:BackgroundFor finite samples with binary outcomes penalized logistic regression such as ridge logistic regression has the potential of achieving smaller mean squared errors (MSE) of coefficients and predictions than maximum likelihood estimation. There is evidence, however, that ridge logistic regression can result in highly variable calibration slopes in small or sparse data situations.MethodsIn this paper, we elaborate this issue further by performing a comprehensive simulation study, investigating the performance of ridge logistic regression in terms of coefficients and predictions and comparing it to Firth's correction that has been shown to perform well in low-dimensional settings. In addition to tuned ridge regression where the penalty strength is estimated from the data by minimizing some measure of the out-of-sample prediction error or information criterion, we also considered ridge regression with pre-specified degree of shrinkage. We included 'oracle' models in the simulation study in which the complexity parameter was chosen based on the true event probabilities (prediction oracle) or regression coefficients (explanation oracle) to demonstrate the capability of ridge regression if truth was known.ResultsPerformance of ridge regression strongly depends on the choice of complexity parameter. As shown in our simulation and illustrated by a data example, values optimized in small or sparse datasets are negatively correlated with optimal values and suffer from substantial variability which translates into large MSE of coefficients and large variability of calibration slopes. In contrast, in our simulations pre-specifying the degree of shrinkage prior to fitting led to accurate coefficients and predictions even in non-ideal settings such as encountered in the context of rare outcomes or sparse predictors.ConclusionsApplying tuned ridge regression in small or sparse datasets is problematic as it results in unstable coefficients and predictions. In contrast, determining the degree of shrinkage according to some meaningful prior assumptions about true effects has the potential to reduce bias and stabilize the estimates.
| S-EPMC8482588 | biostudies-literature
Project description:Background Urothelial Carcinoma of the bladder (BLCA) is the most prevalent cancer of the urinary system. In cancer patients, HRG fusion is linked to a poor prognosis. The prediction of HRG expression by imaging omics in BLCA has not yet been fully investigated. Methods HRG expression in BLCA and healthy adjoining tissues was primarily identified utilizing data sourced from The Cancer Genome Atlas (TCGA). Using Kaplan–Meier survival curves and Landmark analysis, the relationship between HRG expression, clinicopathological parameters, and overall survival (OS) was investigated. Additionally, gene set variation analysis (GSVA) was conducted and CIBERSORTx was used to investigate the relationship between HRG expression and immune cell infiltration. The Cancer Imaging Archive (TCIA) provided CT images that were used for prognostic analysis, radiomic feature extraction, and construction of the model, respectively. The HRG expression levels were predicted using the constructed and evaluated LR and SMV models. Results HRG expression was shown to be substantially lower in BLCA tumors as opposed to that observed in normal tissues (p < 0.05). HRG expression had a close positive relationship with Eosinophils and a close negative relationship with B cells naive. The findings of the Landmark analysis illustrated that higher HRG was associated with improved patient survival at an early stage (P=0.048). The predictive performance of the two models, based on logistic regression analysis and support vector machine, was outstanding in the training and validation sets, yielding AUCs of 0.722 and 0.708, respectively, in the SVM model, and 0.727 and 0.662, respectively, in the LR.The models have good predictive efficiency. Conclusion HRG expression levels can have a significant impact on BLCA patients’ prognoses. The radiomic characteristics can successfully predict the pre-surgical HRG expression levels, based on CT- Image omics.
| S-EPMC9884970 | biostudies-literature
Project description:ObjectiveMethods to correct class imbalance (imbalance between the frequency of outcome events and nonevents) are receiving increasing interest for developing prediction models. We examined the effect of imbalance correction on the performance of logistic regression models.Material and methodsPrediction models were developed using standard and penalized (ridge) logistic regression under 4 methods to address class imbalance: no correction, random undersampling, random oversampling, and SMOTE. Model performance was evaluated in terms of discrimination, calibration, and classification. Using Monte Carlo simulations, we studied the impact of training set size, number of predictors, and the outcome event fraction. A case study on prediction modeling for ovarian cancer diagnosis is presented.ResultsThe use of random undersampling, random oversampling, or SMOTE yielded poorly calibrated models: the probability to belong to the minority class was strongly overestimated. These methods did not result in higher areas under the ROC curve when compared with models developed without correction for class imbalance. Although imbalance correction improved the balance between sensitivity and specificity, similar results were obtained by shifting the probability threshold instead.DiscussionImbalance correction led to models with strong miscalibration without better ability to distinguish between patients with and without the outcome event. The inaccurate probability estimates reduce the clinical utility of the model, because decisions about treatment are ill-informed.ConclusionOutcome imbalance is not a problem in itself, imbalance correction may even worsen model performance.
| S-EPMC9382395 | biostudies-literature
Project description:BACKGROUND:Electronic health record (EHR) systems generate large datasets that can significantly enrich the development of medical predictive models. Several attempts have been made to investigate the effect of glycated hemoglobin (HbA1c) elevation on the prediction of diabetes onset. However, there is still a need for validation of these models using EHR data collected from different populations. OBJECTIVE:The aim of this study is to perform a replication study to validate, evaluate, and identify the strengths and weaknesses of replicating a predictive model that employed multiple logistic regression with EHR data to forecast the levels of HbA1c. The original study used data from a population in the United States and this differentiated replication used a population in Saudi Arabia. METHODS:A total of 3 models were developed and compared with the model created in the original study. The models were trained and tested using a larger dataset from Saudi Arabia with 36,378 records. The 10-fold cross-validation approach was used for measuring the performance of the models. RESULTS:Applying the method employed in the original study achieved an accuracy of 74% to 75% when using the dataset collected from Saudi Arabia, compared with 77% obtained from using the population from the United States. The results also show a different ranking of importance for the predictors between the original study and the replication. The order of importance for the predictors with our population, from the most to the least importance, is age, random blood sugar, estimated glomerular filtration rate, total cholesterol, non-high-density lipoprotein, and body mass index. CONCLUSIONS:This replication study shows that direct use of the models (calculators) created using multiple logistic regression to predict the level of HbA1c may not be appropriate for all populations. This study reveals that the weighting of the predictors needs to be calibrated to the population used. However, the study does confirm that replicating the original study using a different population can help with predicting the levels of HbA1c by using the predictors that are routinely collected and stored in hospital EHR systems.
| S-EPMC7367516 | biostudies-literature
Project description:Two different approaches to analysis of data from diagnostic biomarker studies are commonly employed. Logistic regression is used to fit models for probability of disease given marker values while ROC curves and risk distributions are used to evaluate classification performance. In this paper we present a method that simultaneously accomplishes both tasks. The key step is to standardize markers relative to the non-diseased population before including them in the logistic regression model. Among the advantages of this method are: (i) ensuring that results from regression and performance assessments are consistent with each other; (ii) allowing covariate adjustment and covariate effects on ROC curves to be handled in a familiar way, and (iii) providing a mechanism to incorporate important assumptions about structure in the ROC curve into the fitted risk model. We develop the method in detail for the problem of combining biomarker datasets derived from multiple studies, populations or biomarker measurement platforms, when ROC curves are similar across data sources. The methods are applicable to both cohort and case-control sampling designs. The dataset motivating this application concerns Prostate Cancer Antigen 3 (PCA3) for diagnosis of prostate cancer in patients with or without previous negative biopsy where the ROC curves for PCA3 are found to be the same in the two populations. Estimated constrained maximum likelihood and empirical likelihood estimators are derived. The estimators are compared in simulation studies and the methods are illustrated with the PCA3 dataset.
| S-EPMC3817965 | biostudies-literature
Project description:Gulf War Illness (GWI) is a debilitating condition characterized by dysfunction of cognition, pain, fatigue, sleep, and diverse somatic symptoms with no known underlying pathology. As such, uncovering objective biomarkers such as differential regions of activity within a Functional Magnetic Resonance Imaging (fMRI) scan is important to enhance validity of the criteria for diagnosis. Symptoms are exacerbated by mild activity, and exertional exhaustion is a key complaint amongst sufferers. We modeled this exertional exhaustion by having GWI (n = 80) and sedentary control (n = 31) subjects perform submaximal exercise stress tests on two consecutive days. Cognitive differences were assessed by comparing fMRI scans performed during 2-Back working memory tasks before and after the exercise. Machine learning algorithms were used to identify differences in brain activation patterns between the two groups on Day 1 (before exercise) and Day 2 (after exercise). The numbers of voxels with t > 3.17 (corresponding to p < 0.001 uncorrected) were determined for brain regions defined by the Automated Anatomical Labeling (AAL) atlas. Data were divided 70:30 into training and test sets. Recursive feature selection identified twenty-nine regions of interest (ROIs) that significantly distinguished GWI from control on Day 1 and 28 ROIs on Day 2. Ten regions were present in both models between the two days, including right anterior insula, orbital frontal cortex, thalamus, bilateral temporal poles, and left supramarginal gyrus and cerebellar Crus 1. The models had 70% accuracy before exercise on Day 1 and 85% accuracy after exercise on Day 2, indicating the logistic regression model significantly differentiated subjects with GWI from the sedentary control group. Exercise caused changes in these patterns that may indicate the cognitive differences caused by exertional exhaustion. A second set of predictive models was able to classify previously identified GWI exercise subgroups START, STOPP, and POTS for both Days 1 and Days 2 with 67% and 69% accuracy respectively. This study was the first of its kind to differentiate GWI and the three sub-phenotypes START, STOPP, and POTS from a sedentary control using a logistic regression estimation method.
| S-EPMC7287630 | biostudies-literature
Project description:Logistic regression analysis is a statistical technique to evaluate the relationship between various predictor variables (either categorical or continuous) and an outcome which is binary (dichotomous). In this article, we discuss logistic regression analysis and the limitations of this technique.
| S-EPMC5543767 | biostudies-other