scholarly journals CXCL10 levels at hospital admission predict COVID-19 outcome: hierarchical assessment of 53 putative inflammatory biomarkers in an observational study

2021 ◽  
Vol 27 (1) ◽  
Author(s):  
Nicola I. Lorè ◽  
Rebecca De Lorenzo ◽  
Paola M. V. Rancoita ◽  
Federica Cugnata ◽  
Alessandra Agresti ◽  
...  
Keyword(s):  
Hospital Admission ◽  
Classification Tree ◽  
Regression Tree ◽  
Predictive Biomarker ◽  
Classification And Regression Tree ◽  
Data Driven ◽  
Reference Hospital ◽  
Data Driven Approach ◽  
Hierarchical Assessment ◽  
Potential Biomarkers

Abstract Background Host inflammation contributes to determine whether SARS-CoV-2 infection causes mild or life-threatening disease. Tools are needed for early risk assessment. Methods We studied in 111 COVID-19 patients prospectively followed at a single reference Hospital fifty-three potential biomarkers including alarmins, cytokines, adipocytokines and growth factors, humoral innate immune and neuroendocrine molecules and regulators of iron metabolism. Biomarkers at hospital admission together with age, degree of hypoxia, neutrophil to lymphocyte ratio (NLR), lactate dehydrogenase (LDH), C-reactive protein (CRP) and creatinine were analysed within a data-driven approach to classify patients with respect to survival and ICU outcomes. Classification and regression tree (CART) models were used to identify prognostic biomarkers. Results Among the fifty-three potential biomarkers, the classification tree analysis selected CXCL10 at hospital admission, in combination with NLR and time from onset, as the best predictor of ICU transfer (AUC [95% CI] = 0.8374 [0.6233–0.8435]), while it was selected alone to predict death (AUC [95% CI] = 0.7334 [0.7547–0.9201]). CXCL10 concentration abated in COVID-19 survivors after healing and discharge from the hospital. Conclusions CXCL10 results from a data-driven analysis, that accounts for presence of confounding factors, as the most robust predictive biomarker of patient outcome in COVID-19. Graphic abstract

scholarly journals A Novel Comprehensive Clinical Stratification Model to Refine Prognosis of Glioblastoma Patients Undergoing Surgical Resection

Cancers ◽  
2020 ◽  
Vol 12 (2) ◽  
pp. 386 ◽  
Author(s):  
Tamara Ius ◽  
Fabrizio Pignotti ◽  
Giuseppe Maria Della Pepa ◽  
Giuseppe La Rocca ◽  
Teresa Somma ◽  
...  
Keyword(s):  
Surgical Resection ◽  
Classification Tree ◽  
Prognostic Score ◽  
Regression Tree ◽  
Image Data ◽  
Extent Of Resection ◽  
Classification And Regression Tree ◽  
Postoperative Treatment ◽  
Time Data ◽  
Cart Analysis

Despite recent discoveries in genetics and molecular fields, glioblastoma (GBM) prognosis still remains unfavorable with less than 10% of patients alive 5 years after diagnosis. Numerous studies have focused on the research of biological biomarkers to stratify GBM patients. We addressed this issue in our study by using clinical/molecular and image data, which is generally available to Neurosurgical Departments in order to create a prognostic score that can be useful to stratify GBM patients undergoing surgical resection. By using the random forest approach [CART analysis (classification and regression tree)] on Survival time data of 465 cases, we developed a new prediction score resulting in 10 groups based on extent of resection (EOR), age, tumor volumetric features, intraoperative protocols and tumor molecular classes. The resulting tree was trimmed according to similarities in the relative hazard ratios amongst groups, giving rise to a 5-group classification tree. These 5 groups were different in terms of overall survival (OS) (p < 0.000). The score performance in predicting death was defined by a Harrell’s c-index of 0.79 (95% confidence interval [0.76–0.81]). The proposed score could be useful in a clinical setting to refine the prognosis of GBM patients after surgery and prior to postoperative treatment.

scholarly journals Water cut/salt content forecasting in oil wells using a novel data-driven approach

2019 ◽  
Vol 74 ◽  
pp. 68
Author(s):  
Rouhollah Ahmadi ◽  
Jamal Shahrabi ◽  
Babak Aminshahidy
Keyword(s):  
Classification Tree ◽  
Salt Content ◽  
Oil Wells ◽  
Data Driven ◽  
Var Model ◽  
Support Vector ◽  
Water Production ◽  
Linear Discriminant ◽  
Data Driven Approach ◽  
Water Cut

Water cut is an important parameter in reservoir management and surveillance. Unlike traditional approaches, including numerical simulation and analytical techniques, which were developed for predicting water production in oil wells based on some assumptions and limitations, a new data-driven approach is proposed for forecasting water cut in two different types of oil wells in this article. First, a classification approach is presented for water cut prediction in sweet oil wells with discontinuous salt production patterns. Different classification algorithms including Support Vector Machine (SVM), Classification Tree (CT), Random Forest (RF), Multi-Layer Perceptron (MLP), Linear Discriminant Analysis (LDA) and Naïve Bayes (NB) are investigated in this regard. According to the results of a case study on a real Iranian sweet oil well, RF, CT, MLP and SVM can provide the best performance measures, respectively. Next, a Vector Autoregressive (VAR) model is proposed for forecasting water cut in salty oil wells with continuous water production during the life of the well. The proposed VAR model is verified using data of two real salty oil wells. The results confirm that the well-tuned proposed VAR model could provide reliable and acceptable results with very good accuracy in forecasting water production for the near future days.

scholarly journals Ketidaktepatan Waktu Kelulusan Mahasiswa Universitas Terbuka dengan Metode Boosting Cart

Jurnal Varian ◽  
2019 ◽  
Vol 2 (2) ◽  
pp. 37-46
Author(s):  
Gede Suwardika ◽  
I Ketut Putu Suniantara ◽  
Ni Putu Nanik Hendayanti
Keyword(s):  
Predictive Accuracy ◽  
Classification Tree ◽  
Regression Tree ◽  
Majority Voting ◽  
Classification And Regression Tree ◽  
Combination Method ◽  
Student Graduation ◽  
Classification Prediction ◽  
The Stability

The classification tree method or better known as Classification and Regression Tree (CART) has capabilities in various data conditions, but CART is less stable in changing learning data which will cause major changes in the results of the classification tree prediction. Predictive accuracy of an unstable classifier can be corrected by a combination method of many single classifiers where the prediction results of each classifier are combined into the final prediction through the majority voting process for classification or average voting for regression cases. Boosting ensemble method is one method that combines many classification trees to improve stability and determine classification predictions. This research purpose to improve the stability and predictive accuracy of CART with boosting. The case used in this study is the classification of inaccuracies in the Open University student graduation. The results of the analysis show that boosting is able to improve the accuracy of the classification of the inaccuracy of student graduation which reaches a classification prediction of 75.94% which previously reached 65.41% in the classification tree.

scholarly journals ANALISIS RANDOM FOREST PADA KLASIFIKASI CART KETIDAKTEPATAN WAKTU KELULUSAN MAHASISWA UNIVERSITAS TERBUKA

2019 ◽  
Vol 13 (3) ◽  
pp. 177-184
Author(s):  
Gede Suwardika Suwardika ◽  
I Ketut Putu Suniantara
Keyword(s):  
Random Forest ◽  
Classification Tree ◽  
Regression Tree ◽  
University Student ◽  
Classification And Regression Tree ◽  
Random Forest Method ◽  
Student Graduation ◽  
Stability And Accuracy ◽  
Learning Data

Classification and Regression Tree (CART) is one of the classification methods that are popularly used in various fields. The method is considered capable of dealing with various data conditions. However, the CART method has weaknesses in the classification tree prediction, which is less stable in changes in learning data which will cause major changes in the results of the classification tree prediction. Improving the predictions of the CART classification tree, an ensemble random forest method was developed that combines many classification trees to improve stability and determine classification predictions. This study aims to improve CART predictive stability and accuracy with Random Forest. The case used in this study is the classification of inaccuracies in Open University student graduation. The results of the analysis show that random forest is able to increase the accuracy of the classification of the inaccuracy of student graduation that reaches convergence with the prediction of classification reaching 93.23%.

Cutaneous complications in hematopoietic cell transplant recipients: Impact of biopsy on patient management.

2013 ◽  
Vol 31 (15_suppl) ◽  
pp. 7036-7036
Author(s):  
Oana Valeria Paun ◽  
Tycel Jovelle Phillips ◽  
PingFu Fu ◽  
Robert Novoa ◽  
Kord Honda ◽  
...  
Keyword(s):  
Classification Tree ◽  
Regression Tree ◽  
Hematopoietic Cell ◽  
Classification And Regression Tree ◽  
Cell Transplant ◽  
Hematopoietic Cell Transplant ◽  
Data Set ◽  
Post Transplant ◽  
Skin Biopsies ◽  
The Impact

7036 Background: Although skin biopsies are recommended for diagnostic purposes in hematopoietic cell transplant (HCT) recipients, their utility in directing management of post transplant cutaneous eruptions remains uncertain. Little evidence was found in support of this procedure either from a diagnostic or prognostic perspective. Methods: We retrospectively evaluated 351 consecutive HCT recipients transplanted at our institution between January 2005 and December 2011; 156 patients underwent 388 cutaneous biopsies. Results: The group that underwent cutaneous biopsy after transplantation and the group that was spared the procedure were homogenous with regards to age and gender. The pre-biopsy diagnosis and final diagnosis differed in 213 episodes (55%) as determined by histologic evaluation. Biopsy results led to a change in therapy in 61 of 388 (16%) biopsied rashes. With regards to therapy changes, 24 of 61 (39%) occurred in response to a clinical diagnosis of GVHD. In this situation the most frequently noted change was augmentation or addition of systemic immuno-suppression (19 of 24). Changes in systemic therapy occurred with similar frequencies with respect to concordance or discordance between clinical and histopathologic diagnosis (p = 0.12). We used classification and regression tree analysis to develop an algorithm to predict the biopsy yield as expressed by change of management. This is a non-parametric decision tree learning technique that produces a classification tree based on a categorical dependent variable, formed by a collection of rules based on variables in the modeling data set. Conclusions: Cutaneous biopsy findings often changed the clinical dermatologic diagnoses of HCT recipients; however, the impact of biopsy results on treatment decisions was less profound; altered diagnoses in patients who underwent biopsy often did not lead to therapy changes. Skin biopsies of post-transplant patients may not be mandatory for either diagnostic or therapeutic reasons, but in carefully chosen circumstances can yield extremely important data. A prospective study should be undertaken in order to evaluate current practice data and to validate our decision making analysis tree.

scholarly journals Over-indebted Households in Poland: Classification Tree Analysis

2020 ◽  
Author(s):  
Grzegorz Wałęga ◽  
Agnieszka Wałęga
Keyword(s):  
Classification Tree ◽  
Regression Tree ◽  
Poverty Line ◽  
Classification And Regression Tree ◽  
Vulnerable Groups ◽  
Psychological Burden ◽  
Tree Analysis ◽  
Level Data ◽  
Income Ratio ◽  
Definition Of

Abstract Increasing a personal debt burden implies greater financial vulnerability and threats for macroeconomic stability. It also generates a risk of the households over-indebtedness. The assessment of over-indebtedness is conducted with the use of various objective and subjective measures based on the micro-level data. The aim of the study is to investigate over-indebted households in Poland using a unique dataset obtained from the CATI survey. We discuss and compare the usefulness of various over-indebtedness measures across different socio-economic characteristics. Due to the differences in over-indebtedness across single measures, we perform a more complex assessment using a mix of indicators. As an alternative to other commonly criticised over-indebtedness measures, we apply the “below the poverty line” (BPL) measure. In order to obtain the profile of over-indebted households, we use classification and regression tree analysis as an alternative to logit or probit models. We find that DSTI (“debt service to income”) ratio underestimates the extent of over-indebtedness in vulnerable groups of households in comparison with the BPL. We highlight the necessity to use different measures depending on the adopted definition of over-indebtedness. A psychological burden of debts is particularly strong among older and poorly educated respondents. We also find that the age structure of over-indebted households in Poland differs from this structure in countries with a broader access to consumer credits. Our results can be used to enrich the methods of assessing the household over-indebtedness.

scholarly journals SELECTING KDD FEATURES AND USING RANDOM CLASSIFICATION TREE FOR PREDICTING ATTACKS

2014 ◽  
pp. 115-123
Author(s):  
Rachid Beghdad
Keyword(s):  
Machine Learning ◽  
Classification Tree ◽  
Regression Tree ◽  
Classification Trees ◽  
Classification And Regression Tree ◽  
Data Sets ◽  
Machine Learning Technique ◽  
Learning Technique ◽  
Classification And Regression ◽  
Anova Technique

The purpose of this study is to identify some higher-level KDD features, and to train the resulting set with an appropriate machine learning technique, in order to classify and predict attacks. To achieve that, a two-steps approach is proposed. Firstly, the Fisher’s ANOVA technique was used to deduce the important features. Secondly, 4 types of classification trees: ID3, C4.5, classification and regression tree (CART), and random tree (RnDT), were tested to classify and detect attacks. According to our tests, the RndT leads to the better results. That is why we will present here the classification and prediction results of this technique in details. Some of the remaining results will be used later to make comparisons. We used the KDD’99 data sets to evaluate the considered algorithms. For these evaluations, only the four attack categories’ case was considered. Our simulations show the efficiency of our approach, and show also that it is very competitive with some similar previous works.

scholarly journals Decision Trees for Evaluation of Mathematical Competencies in the Higher Education: A Case Study

Mathematics ◽  
2020 ◽  
Vol 8 (5) ◽  
pp. 748 ◽  
Author(s):  
Atanas Ivanov
Keyword(s):  
Higher Education ◽  
Classification Tree ◽  
Regression Tree ◽  
Educational Process ◽  
Classification And Regression Tree ◽  
Choice Test ◽  
Knowledge And Skills ◽  
Mathematical Competencies ◽  
Tree Models

The assessment of knowledge and skills acquired by the student at each academic stage is crucial for every educational process. This paper proposes and tests an approach based on a structured assessment test for mathematical competencies in higher education and methods for statistical evaluation of the test. A case study is presented for the assessment of knowledge and skills for solving linear algebra and analytic geometry problems by first-year university students. The test includes three main parts—a multiple-choice test with four selectable answers, a solution of two problems with and without the use of specialized mathematical software, and a survey with four questions for each problem. The processing of data is performed mainly by the classification and regression tree (CART) method. Comparative analysis, cross-tables, and reliability statistics were also used. Regression tree models are built to assess the achievements of students and classification tree models for competency assessment on a three-categorical scale. The influence of 31 variables and groups of them on the assessment of achievements and grading of competencies is determined. Regression models show over 94% fit with data and classification ones—up to 92% correct classifications. The models can be used to predict students’ grades and assess their mathematical competency.

Atlantic cod (Gadus morhua) distribution response to environmental variability in the northern Gulf of St. Lawrence

2009 ◽  
Vol 66 (6) ◽  
pp. 909-918 ◽  
Author(s):  
Jonathan L.W. Ruppert ◽  
Marie-Josée Fortin ◽  
George A. Rose ◽  
Rodolphe Devillers
Keyword(s):  
Gadus Morhua ◽  
Environmental Variability ◽  
Atlantic Cod ◽  
Classification Tree ◽  
Regression Tree ◽  
Distribution Patterns ◽  
Classification And Regression Tree ◽  
Bottom Temperature ◽  
Tree Analysis ◽  
Regression Tree Analysis

Atlantic cod ( Gadus morhua ) distribution patterns and the behavioral (site fidelity), biotic (prey and predators), and environmental factors that determine them are fundamental to cod’s historic importance as a commercial species in the North Atlantic. Using classification and regression tree analysis (CART), we compared two periods (1991–1995 and 1998–2004) with contrasting bottom temperature and salinity regimes to determine regional factors that best explained cod distribution and catch weight per tow from summer surveys in the northern Gulf of St. Lawrence (the feeding period of cod). The classification tree analysis indicated that the presence or absence of cod was chiefly determined by depth in both of these periods. In contrast, the regression tree analysis determined that cod catch weight distributions were explained by different variables in each period. In the colder period (1991–1995), the distribution of catch weights was explained well by environmental variables (bottom temperature, salinity, depth); however, in the warmer period (1998–2004), distributions were best explained by variables from the previous year. These results indicate that the spatiotemporal dynamics of environmental conditions are likely to influence the loyalty of cod to specific feeding grounds and imply that cod responses to the environment could be susceptible to long-term environmental (e.g., bottom–habitat) and climate change.

Sign in / Sign up

Export Citation Format

Share Document