Establishment and validation of a logistic regression model for prediction of septic shock severity in children
Ontology highlight
ABSTRACT: Background
Septic shock is the most severe complication of sepsis, and is a major cause of childhood mortality, constituting a heavy public health burden. Methods
We analyzed the gene expression profiles of septic shock and control samples from the Gene Expression Omnibus (GEO). Four differentially expressed genes (DEGs) from survivor and control groups, non-survivor and control groups, and survivor and non-survivor groups were selected. We used data about these genes to establish a logistic regression model for predicting the survival of septic shock patients. Results
Leave-one-out cross validation and receiver operating characteristic (ROC) analysis indicated that this model had good accuracy. Differential expression and Gene Set Enrichment Analysis (GSEA) between septic shock patients stratified by prediction score indicated that the systemic lupus erythematosus pathway was activated, while the limonene and pinene degradation pathways were inactivated in the high score group. Conclusions
Our study provides a novel approach for the prediction of the severity of pathology in septic shock patients, which are significant for personalized treatment as well as prognostic assessment. Supplementary Information
The online version contains supplementary material available at 10.1186/s41065-021-00206-9.
SUBMITTER: Han Y
PROVIDER: S-EPMC8588704 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Background: Septic shock heterogeneity has important implications for the conduct of clinical trials and individual patient management. We previously addressed this heterogeneity by indentifying 3 putative subclasses of children with septic shock based on a 100-gene expression signature corresponding to adaptive immunity and glucocorticoid receptor signaling. Herein we attempted to prospectively validate the existence of these gene expression-based subclasses in a validation cohort. Methods: Gene expression mosaics were generated from the 100 class-defining genes for 82 individual patients in the validation cohort. Patients were classified into 1 of 3 subclasses (“A”, “B”, or “C”) based on color and pattern similarity relative to reference mosaics generated from the original derivation cohort. Separate classifications were conducted by 21 individual clinicians and a computer-based algorithm. After subclassification the clinical database was mined for clinical phenotyping. Results: In the final consensus subclassification generated by clinicians, subclass A patients had a higher illness severity, as measured by illness severity scores and maximal organ failure, relative to subclasses B and C. The k coefficient across all possible inter-evaluator comparisons was 0.633. Similar observations were made based on the computer-generated subclassification. Patients in subclass A were also characterized by repression of a large number of genes having functional annotations related to zinc biology. Conclusions: We have validated the existence of subclasses of children with septic shock based on a biologically relevant, 100-gene expression signature. The subclasses can be indentified by clinicians without formal bioinformatics training, at a clinically relevant time point, and have clinically relevant phenotypic differences.
2011-01-13 | GSE26378 | GEO
Project description:Background: Septic shock heterogeneity has important implications for the conduct of clinical trials and individual patient management. We previously addressed this heterogeneity by indentifying 3 putative subclasses of children with septic shock based on a 100-gene expression signature corresponding to adaptive immunity and glucocorticoid receptor signaling. Herein we attempted to prospectively validate the existence of these gene expression-based subclasses in a validation cohort. Methods: Gene expression mosaics were generated from the 100 class-defining genes for 82 individual patients in the validation cohort. Patients were classified into 1 of 3 subclasses (“A”, “B”, or “C”) based on color and pattern similarity relative to reference mosaics generated from the original derivation cohort. Separate classifications were conducted by 21 individual clinicians and a computer-based algorithm. After subclassification the clinical database was mined for clinical phenotyping. Results: In the final consensus subclassification generated by clinicians, subclass A patients had a higher illness severity, as measured by illness severity scores and maximal organ failure, relative to subclasses B and C. The k coefficient across all possible inter-evaluator comparisons was 0.633. Similar observations were made based on the computer-generated subclassification. Patients in subclass A were also characterized by repression of a large number of genes having functional annotations related to zinc biology. Conclusions: We have validated the existence of subclasses of children with septic shock based on a biologically relevant, 100-gene expression signature. The subclasses can be indentified by clinicians without formal bioinformatics training, at a clinically relevant time point, and have clinically relevant phenotypic differences. Expression data from 82 children with septic shock and 21 normal controls were generated using whole blood-derived RNA samples representing the first 24 hours of admission to the pediatric intensive care unit. The controls were used for normalization. Subsequently, we used the expression data from 100 class defining genes to validate the existence of pediatric septic shock subclasses having phenotypic differences.
2011-01-13 | E-GEOD-26378 | biostudies-arrayexpress
Project description:Study designRetrospective analysis of prospectively collected data.ObjectivesRecently, logistic regression models were developed to predict independence in bowel function 1 year after spinal cord injury (SCI) on a multicenter European SCI (EMSCI) dataset. Here, we evaluated the external validity of these models against a prospectively accrued North American SCI dataset.SettingTwenty-five SCI centers in the United States and Canada.MethodsTwo logistic regression models developed by the EMSCI group were applied to data for 277 patients derived from three prospective multicenter SCI studies based in North America. External validation was evaluated for both models by assessing their discrimination, calibration, and clinical utility. Discrimination and calibration were assessed using ROC curves and calibration curves, respectively, while clinical utility was assessed using decision curve analysis.ResultsThe simplified logistic regression model, which used baseline total motor score as the predictor, demonstrated the best performance, with an area under the ROC curve of 0.869 (95% confidence interval: 0.826-0.911), a sensitivity of 75.5%, and a specificity of 88.5%. Moreover, the model was well calibrated across the full range of observed probabilities and displayed superior clinical benefit on the decision curve.ConclusionsA logistic regression model using baseline total motor score as a predictor of independent bowel function 1 year after SCI was successfully validated against an external dataset. These findings provide evidence supporting the use of this model to enhance the care for individuals with SCI.
| S-EPMC7870806 | biostudies-literature
Project description:ObjectivesSepsis and septic shock are leading causes of in-hospital mortality. Timely treatment is crucial in improving patient outcome, yet treatment delays remain common. Early prediction of those patients with sepsis who will progress to its most severe form, septic shock, can increase the actionable window for interventions. We aim to extend a time-evolving risk score, previously developed in adult patients, to predict pediatric sepsis patients who are likely to develop septic shock before its onset, and to determine whether or not these risk scores stratify into groups with distinct temporal evolution once this prediction is made.DesignRetrospective cohort study.SettingAcademic medical center from July 1, 2016, to December 11, 2020.PatientsSix-thousand one-hundred sixty-one patients under 18 admitted to the Johns Hopkins Hospital PICU.InterventionsNone.Measurements and main resultsWe trained risk models to predict impending transition into septic shock and compute time-evolving risk scores representative of a patient's probability of developing septic shock. We obtain early prediction performance of 0.90 area under the receiver operating curve, 43% overall positive predictive value, patient-specific positive predictive value as high as 62%, and an 8.9-hour median early warning time using Sepsis-3 labels based on age-adjusted Sequential Organ Failure Assessment score. Using spectral clustering, we stratified pediatric sepsis patients into two clusters differing in septic shock prevalence, mortality, and proportion of patients adequately fluid resuscitated.ConclusionsWe demonstrate the applicability of our methodology for early prediction and stratification for risk of septic shock in pediatric sepsis patients. Through analyses of risk score evolution over time, we corroborate our past finding of an abrupt transition preceding onset of septic shock in children and are able to stratify pediatric sepsis patients using their risk score trajectories into low and high-risk categories.
| S-EPMC8208392 | biostudies-literature
Project description:α-Fetoprotein is commonly used in the diagnosis of hepatocellular carcinoma. However, the diagnostic significance of α-fetoprotein has been questioned because a number of patients with hepatocellular carcinoma are α-fetoprotein negative. It is therefore necessary to develop novel noninvasive techniques for the early diagnosis of hepatocellular carcinoma, particularly when α-fetoprotein level is low or negative. The current study aimed to evaluate the diagnostic efficiency of hematological parameters to determine which can act as surrogate markers in α-fetoprotein-negative hepatocellular carcinoma. Therefore, a retrospective study was conducted on a training set recruited from Zhongnan Hospital of Wuhan University-including 171 α-fetoprotein-negative patients with hepatocellular carcinoma and 102 healthy individuals. The results show that mean values of mean platelet volume, red blood cell distribution width, mean platelet volume-PC ratio, neutrophils-lymphocytes ratio, and platelet count-lymphocytes ratio were significantly higher in patients with hepatocellular carcinoma in comparison to the healthy individuals. Most of these parameters showed moderate area under the curve in α-fetoprotein-negative patients with hepatocellular carcinoma, but their sensitivities or specificities were not satisfactory enough. So, we built a logistic regression model combining multiple hematological parameters. This model presented better diagnostic efficiency with area under the curve of 0.922, sensitivity of 83.0%, and specificity of 93.1%. In addition, the 4 validation sets from different hospitals were used to validate the model. They all showed good area under the curve with satisfactory sensitivities or specificities. These data indicate that the logistic regression model combining multiple hematological parameters has better diagnostic efficiency, and they might be helpful for the early diagnosis for α-fetoprotein-negative hepatocellular carcinoma.
| S-EPMC6535757 | biostudies-literature
Project description:Acute kidney injury (AKI) after liver transplantation has been reported to be associated with increased mortality. Recently, machine learning approaches were reported to have better predictive ability than the classic statistical analysis. We compared the performance of machine learning approaches with that of logistic regression analysis to predict AKI after liver transplantation. We reviewed 1211 patients and preoperative and intraoperative anesthesia and surgery-related variables were obtained. The primary outcome was postoperative AKI defined by acute kidney injury network criteria. The following machine learning techniques were used: decision tree, random forest, gradient boosting machine, support vector machine, naïve Bayes, multilayer perceptron, and deep belief networks. These techniques were compared with logistic regression analysis regarding the area under the receiver-operating characteristic curve (AUROC). AKI developed in 365 patients (30.1%). The performance in terms of AUROC was best in gradient boosting machine among all analyses to predict AKI of all stages (0.90, 95% confidence interval [CI] 0.86?0.93) or stage 2 or 3 AKI. The AUROC of logistic regression analysis was 0.61 (95% CI 0.56?0.66). Decision tree and random forest techniques showed moderate performance (AUROC 0.86 and 0.85, respectively). The AUROC of support the vector machine, naïve Bayes, neural network, and deep belief network was smaller than that of the other models. In our comparison of seven machine learning approaches with logistic regression analysis, the gradient boosting machine showed the best performance with the highest AUROC. An internet-based risk estimator was developed based on our model of gradient boosting. However, prospective studies are required to validate our results.
| S-EPMC6262324 | biostudies-other
Project description:Detecting the temporally and spatially varying correlations is important to understand the biological and disease systems. Here we proposed a geographically weighted temporally correlated logistic regression (GWTCLR) model to identify such dynamic correlation of predictors on binomial outcome data, by incorporating spatial and temporal information for joint inference. The local likelihood method is adopted to estimate the spatial relationship, while the smoothing method is employed to estimate the temporal variation. We present the construction and implementation of GWTCLR and the study of the asymptotic properties of the proposed estimator. Simulation studies were conducted to evaluate the robustness of the proposed model. GWTCLR was applied on real epidemiologic data to study the climatic determinants of human seasonal influenza epidemics. Our method obtained results largely consistent with previous studies but also revealed certain spatial and temporal varying patterns that were unobservable by previous models and methods.
| S-EPMC5780421 | biostudies-literature
Project description:BackgroundLysine acetylation is a crucial type of protein post-translational modification, which is involved in many important cellular processes and serious diseases. However, identification of protein acetylated sites through traditional experiment methods is time-consuming and laborious. Those methods are not suitable to identify a large number of acetylated sites quickly. Therefore, computational methods are still very valuable to accelerate lysine acetylated site finding.ResultIn this study, many biological characteristics of acetylated sites have been investigated, such as the amino acid sequence around the acetylated sites, the physicochemical property of the amino acids and the transition probability of adjacent amino acids. A logistic regression method was then utilized to integrate these information for generating a novel lysine acetylation prediction system named LAceP. When compared with existing methods, LAceP overwhelms most of state-of-the-art methods. Especially, LAceP has a more balanced prediction capability for positive and negative datasets.ConclusionLAceP can integrate different biological features to predict lysine acetylation with high accuracy. An online web server is freely available at http://www.scbit.org/iPTM/.
| S-EPMC3930742 | biostudies-literature
Project description:Rationale: We previously generated genome-wide expression data in children with septic shock, based on whole blood-derive RNA, having the potential to lead the field into novel areas of investigation. Objective: Herein we seek to validate our data through a bioinformatic approach centered on a validation patient cohort. Methods: Microarray- and bioinformatics-centered analyses involving our previous data as a training data set (n = 42) and a new, validation cohort (n = 30) as the test data set. Measurements and Main Results: Class prediction modeling using the training data set and the previously reported genome-wide expression signature of pediatric septic shock correctly identified 93 to 100% of septic shock patients in the test data set, depending on the class prediction algorithm and the gene selection method. Subjecting the test data set to an identical filtering strategy as that used for the training data set, demonstrated 72% concordance between the two gene lists. Subjecting the test data set to a purely statistical filtering strategy, with highly stringent correction for multiple comparisons, demonstrated less than 50% concordance with the previous gene filtering strategy. However, functional analysis of this statistics-based gene list demonstrated similar functional annotations and signaling pathways as that seen in the learning data set. In particular, we validated that pediatric septic shock is characterized by large scale repression of genes related to zinc homeostasis and lymphocyte function. Conclusions: These data demonstrate that the previously reported genome-wide expression signature of pediatric septic shock is applicable to a validation cohort of patients. Keywords: Inflammation; sepsis; innate immunity; T cells; MHC antigen; zinc
2007-12-01 | GSE9692 | GEO
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