Search

Juvenile North Pacific Albacore tuna (Thunnus alalunga) support commercial and recreational fisheries in the California Current Large Marine Ecosystem (CCLME), where they forage during summer and fall. The distributions of the commercial and recreational fisheries and estimates of forage availability have varied substantially over the past century. Time‐series quantifying Albacore diet can help link forage composition to variability in Albacore abundance and distribution and, consequently, their availability to fishers. Previous diet studies in the CCLME are of relatively short duration, and long‐term variability in Albacore diet remains poorly understood. We describe the diets of juvenile Albacore from three regions in the CCLME from 2007 to 2019 and use classification and regression tree analysis to explore environmental drivers of variability. Important prey include Northern Anchovy (Engraulis mordax), rockfishes (Sebastes spp.), Boreal Clubhook Squid (Onychoteuthis borealijaponica), euphausiids (Order: Euphausiidae), and amphipods (Order: Amphipoda), each contributing >5% mean proportional abundance. Most prey items were short lived species or young‐of‐the‐year smaller than 10 cm. Diet variability was related to environmental conditions over the first 6 months of the year (PDO, sea surface temperature, and NPGO) and conditions concurrent with Albacore capture (region and surface nitrate flux). We describe foraging flexibility over regional and annual scales associated with these environmental influences. Continuous, long‐term studies offer the opportunity to identify flexibility in Albacore foraging behavior and begin to make a predictive link between environmental conditions early in the year and Albacore foraging during summer and fall. [ABSTRACT FROM AUTHOR]

Background: The anorectal malformations (ARMs) with bladder‐neck/urethral‐prostatic fistula in males are the most complex groups in ARMs. It is essential to diagnose them effectively before the primary operation for both surgical modalities and future functional prognosis can be quite different from other types. Our study aimed to develop a classification and regression tree (CART) model for the prediction of ARMs with bladder‐neck/urethral‐prostatic fistula. Methods: A total of 132 newborns with ARMs were included retrospectively and randomly assigned to the training sample and test sample in a 3:1 ratio. The pouch‐perineum distance of ultrasound (PPDU), the pouch‐perineum distance of invertogram (PPDI), and the rectum gas above the coccyx (RGAC) on the invertogram were hypothesized can serve as individual predictors. The CART analysis was used to determine the best combination of candidate predictors. The model's performance was assessed by the area under the receiver operating characteristic curve (AUC) and validated in the test sample. Results: All three individual predictors were included in the CART model to predict the ARMs with bladder‐neck/urethral‐prostatic fistula in the derivation cohort with the following test characteristics (95% CI): sensitivity 75.6% (60.1 to 86.6); specificity 88.9% (76.7 to 95.4); AUC 0.909 (0.854 to 0.965). The model's predicted accuracy was validated in the test cohort (AUC = 0.883). In all 132 subjects, the AUC of the tree model was significantly superior to that of the best individual index: PPDU (0.901 vs. 0.819; p = 0.005). Conclusions: A predictive model that consists of PPDU, PPDI, and RGAC may be useful in predicting ARMs with bladder‐neck/urethral‐prostatic fistula. [ABSTRACT FROM AUTHOR]

Background and objective: Variations in the risk factors for sarcopenia can lead to differences in the likelihood of developing sarcopenia among older adults; however, few studies have explored the interactions among the risk factors. This study examined the interactions among risk factors and identified a discriminative pathway for groups at risk of sarcopenia in community‐dwelling older adults. Methods: A cross‐sectional study was conducted between July and August 2019 to recruit 200 older adults from an outpatient department of a hospital providing care for older people. Data on various risk factors, namely demographics (age, gender, education, comorbidities, and body mass index [BMI]), dietary habits (weekly consumption of milk, coffee, and meat), lifestyle behaviours (vitamin D supplementation, smoking, drinking, and physical activity), and depression symptoms were collected. Sarcopenia was defined according to the Asian Working Group for Sarcopenia criteria. A classification and regression tree (CART) model was used to examine interactions among these factors and identify groups at risk of sarcopenia. Findings: The prevalence of sarcopenia was 38.5%. The CART model identified two end groups at differential risks of sarcopenia, with a minimum of one and a maximum of three risk factors. In the first group, low BMI (<18.5 kg/m2) was a predominant risk factor for sarcopenia among older people. In the second group, older adults with a normal BMI, aged ≥68 years, and without a regular walking habit had a higher probability of developing sarcopenia than did their counterparts. Conclusions: The interactive effects among older age, BMI, and walking may cause different probabilities of developing sarcopenia in the older population. Implications for practice: Older adults with a low or normal BMI but without a regular walking habit could be a predominant risk group for sarcopenia. The appropriate maintenance of body weight and regular walking activity is suggested to prevent sarcopenia in community‐dwelling older adults. [ABSTRACT FROM AUTHOR]

Employees are one of the most important resources of a company. The churn of valuable employees significantly affects a company's performance. The design of systems that predict employee churn is critical importance for companies. At this point, machine learning algorithms offer important opportunities for the diagnosis of employee churn. Nowadays, traditional classification algorithms have been replaced by deep learning models. In this study, firstly, a convolutional neural network (CNN) model was applied on a numerical data set for employee churn prediction in retailing. Later, because the data loss is too much in data transformations, a new hybrid extended convolutional decision tree model (ECDT) was proposed by improving the CNN algorithm. Finally, a novel model (ECDT‐GRID) was developed by applying grid search optimization to improve the classification accuracy of ECDT. Numerical results showed that the developed ECDT‐GRID model outperformed the CNN and ECDT models and basic classification algorithms in terms of classification accuracy, and this model provided an efficient methodology for prediction of employee churn. [ABSTRACT FROM AUTHOR]

Human and ecological health have been threatened by the increase of cyanobacteria harmful algal blooms (cyanoHABs) in freshwater systems. Successful mitigation of this risk requires understanding the factors driving cyanoHABs at a broad scale. To inform management priorities and decisions, we employed random forest modeling to identify major cyanoHAB drivers in 369 freshwater lakes distributed across 15 upper Midwest states during the 2011 bloom season (July–October). We used Cyanobacteria Index (CI_cyano)—A remotely sensed product derived from the MEdium Resolution Imaging Spectrometer (MERIS) aboard the European Space Agency's Envisat satellite—as the response variable to obtain variable importance metrics for 75 landscape and lake physiographic predictor variables. Lakes were stratified into high and low elevation categories to further focus CI_cyano variable importance identification by anthropogenic and natural influences. "High elevation" watershed land cover (LC) was primarily forest or natural vegetation, compared with "low elevation" watersheds LC dominated by anthropogenic landscapes (e.g., agriculture and municipalities). We used the top ranked 25 Random Forest variables to create a classification and regression tree (CART) for both low and high elevation lake designations to identify variable thresholds for possible management mitigation. Mean CI_cyano was 3 times larger for "low elevation" lakes than for "high elevation" lakes, with both mean values exceeding the "High" World Health Organization recreational guidance/action level threshold for cyanobacteria (100,000 cells/mL). Agrarian‐related variables were prominent across all 369 lakes and low elevation lakes. High elevation lakes showed more influence of lakeside LC than for the low elevation lakes. Key Points: Cyanobacteria drivers ranked for 369 freshwater lakes in central United StatesAnthropogenic influences notable in top rankings across all watersheds [ABSTRACT FROM AUTHOR]

Identification of key soil properties is an essential prerequisite to delineating the management zone (MZ), which is traditionally done by selecting soil parameters before crop planting. However, soil properties during sensitive stages of crop growth may have a greater effect on the MZ delineation than those before planting. This study is aimed to determine whether inclusion of soil properties measured in surface layers during the reproductive stage of rice could enhance the appropriateness of MZ delineation based on sodic/saline‐sodic paddy fields. When including soil variables during the reproductive stage, with/without soil variables before planting, a similar MZ pattern (MZ pattern 3) was generated. Furthermore, when including soil variables during the reproductive stage and rice yield components, with/without soil variables before planting, another similar MZ pattern (MZ Pattern 4) was generated. Compared with other patterns, the MZ pattern 4 showed higher relative variances for rice yield and the mean of its most important yield‐influencing factors, with lower coefficient of variation (CV) in all MZs compared with the whole‐paddock CV. Likewise, this pattern showed improvement in discriminating soil and rice variables among MZs. These findings confirm that inclusion of soil properties during the reproductive stage of rice has potential for enhancing the appropriateness of MZ delineation. This study also necessitates inclusion of carbonate‐derived variables when delineating MZs in sodic/saline‐sodic paddy fields. Our results encourage further investigation of the role of soil properties in surface soil layers at critical crop growth stages in MZ delineation under multiple soil and climatic conditions. [ABSTRACT FROM AUTHOR]

Host size, density, and distribution, in addition to climate, can affect the likelihood a pathogen will invade and saturate landscapes. Laurel wilt, caused by the vector‐borne pathogen Raffaelea lauricola, has devastated populations of native Lauraceae in the south‐eastern USA, and continues to spread. We surveyed 87 plots in six coastal islands in South Carolina, Georgia, and north Florida, and one inland site (Archbold Biological Station) in south Florida for laurel wilt‐affected and unaffected individual plants belonging to the genus Persea. The coastal island sites were surveyed once in 2008 or 2009, and the inland site was surveyed eight times from 2011 to 2013. Disease incidence per plot ranged from 0% to 96%, with mean disease incidence 42% across all sites. Disease incidence was positively correlated with trunk diameter and with density of hosts with trunk diameter >5 cm, but negatively correlated with the degree of clustering, which was highest for small trees. A recursive partitioning model indicated that higher disease incidence was associated with moderate temperatures, wider trunk diameter, lower relative humidity, and lower wind speeds. Disease progress over time at Archbold followed a Gompertz curve, plateauing at 3% in 2 years. The dispersal kernel for disease incidence from a focus followed a negative exponential distribution. The number of plots with diseased trees at Archbold was similar for redbay (P. borbonia) and swampbay (P. palustris) but was lower for silkbay (P. humilis). Understanding how host density, size, and diversity interact with environmental effects will help guide future risk prediction efforts. [ABSTRACT FROM AUTHOR]

Diabetes mellitus is one of the most important public health problems affecting millions of people worldwide. An early and accurate diagnosis of diabetes mellitus has critical importance for the medical treatments of patients. In this study, first, artificial neural network (ANN) and classification and regression tree (CART)-based approaches are proposed for the diagnosis of diabetes. Hybrid ANN-GA and CART-GA approaches are then developed using a genetic algorithm (GA) to improve the classification accuracy of these approaches. Finally, the performances of the developed approaches are evaluated with a Pima Indian diabetes data set. Experimental results show that the developed hybrid CART-GA approach outperforms the ANN, CART, and ANN-GA approaches in terms of classification accuracy, and this approach provides an efficient methodology for diagnosis of diabetes mellitus. [ABSTRACT FROM AUTHOR]

Objectives: Cefoperazone/sulbactam trough concentration (Cmin) varies widely in cirrhotic patients. The objective of this study was to describe the characteristics of Cmin and to identify factors associated with the pharmacokinetic/pharmacodynamic (PK/PD) target attainment of cefoperazone/sulbactam in cirrhotic patients. Methods: Data were collected retrospectively from cirrhotic patients who received cefoperazone/sulbactam treatment. The Cmin was measured using a validated liquid chromatography‐tandem mass spectrometry. The PK/PD target of 100% fT > MIC was used for cefoperazone/sulbactam. Multivariate logistic regression and classification and regression tree (CART) analysis were performed to identify the factors affecting the PK/PD target attainment in these patients. Results: Cefoperazone and sulbactam Cmin were measured simultaneously in 103 plasma samples from 70 cirrhotic patients. Cefoperazone and sulbactam Cmin were 89.27 ± 44.38 mg/L and 10.09 ± 13.01 mg/L, respectively. The PK/PD target of 100% fT > MIC was achieved in 47.1% (33/70) patients for cefoperazone and in 28.6% (20/70) patients for sulbactam. The CART analysis revealed that cefoperazone Cmin was likely to reach the PK/PD target in patients with serum bilirubin levels between 26.15 μmol/L and 99.15 μmol/L. Inversely, lower cefoperazone Cmin was observed in patients with bilirubin levels ≤26.15 μmol/L and serum albumin >38.45 g/L or in patients with bilirubin levels >99.15 μmol/L and creatinine clearance (CrCl) >139.13 mL/min. Additionally, patients had higher sulbactam Cmin when CrCl was below 62.85 mL/min. Conclusions: This study shows that current cefoperazone/sulbactam dosage regimens may result in inadequate plasma concentrations in cirrhotic patients. We recommend monitoring the Cmin of cefoperazone/sulbactam to ensure efficacy of cefoperazone/sulbactam treatment. [ABSTRACT FROM AUTHOR]

Objective: To identify the clustering of adverse childhood experiences (ACEs) that best characterize child welfare-involved children with known complex health concerns.Data Source: Multi-informant data were obtained from Wave I of the National Survey of Child and Adolescent Well-Being (NSCAW II).Study Design: This study used a cross-sectional design and classification and regression tree (CART) analyses.Data Collection: Data were collected from families with children, aged birth to 17, investigated for child maltreatment and their child protective services caseworkers, including demographic characteristics of the children, their histories of adversity, and a wide range of health concerns.Principal Findings: Results indicate that for children between the ages of six and 17, experiences of physical abuse alone, as well as experiences of physical abuse combined with having a caregiver with mental illness, are most strongly associated with complex health concerns. For children aged 2-5 years, results suggest that caregiver mental illness is a key adverse experience associated with complex health concerns.Conclusions: Identifying specific combinations of ACEs may be a critical next step for child- and youth-serving agencies to allow providers to better calculate risk of health problems among children exposed to adversity. [ABSTRACT FROM AUTHOR]

Objectives: To assess the impact of age on the survival of patients with head and neck squamous cell carcinoma (HNSCC) using different statistical methods. Design: A retrospective population‐based study. Setting: Surveillance, Epidemiology, and End Results database. Subjects and methods: A total of 28 639 patients with newly diagnosed HNSCC were enrolled between 1 January 2007 and 31 December 2013. The effect of age on 5‐year disease‐specific survival was calculated using a Kaplan‐Meier method and compared using log‐rank tests. A Cox proportional hazards model was used for a multivariate analysis. A classification and regression tree (CART) analysis that partitioned patients with significantly different Kaplan‐Meier curves was introduced to identify the important cancer‐related parameters influencing survival. Results: Uni‐ and multivariate analyses indicated that patients who were older than 60 years had poorer 5‐year disease‐specific survival regardless of tumour subsite and tumor‐node‐metastasis (TNM) stage. However, the CART analysis determined that age played only a minor role in survival after comparing with other prognosticators. The relative importance of age using the Gini index was as follows: 3.21% for oral cancer, 8.32% for oropharyngeal cancer, 2.56% for hypopharyngeal cancer and 16.51% for laryngeal cancer. Conclusions: Different to traditional statistical methods, the CART analysis which was used to identify homogeneous populations revealed that the impact of age varied for different patient groups according to the presence or absence of other prognosticators. This important information could help to guide our clinical decisions and future researches. [ABSTRACT FROM AUTHOR]

Abstract: Soil parameters, measured before crop planting, are typically used to quantify the relationship between soil properties and crop yield and to identify factors limiting crop yield. However, soil properties during sensitive stages of crop growth may have a greater effect on crop yield than the initial values. We determined if inclusion of soil properties, measured during the reproductive stage, could improve the accuracy of crop yield prediction. Classification and regression trees were used to determine the explanatory power of different soil and rice variables for predicting rice yield in alkaline salt‐affected paddy fields in northeast China. The traditional method explained 77.5% of the rice yield variation and identified soil CO32− in the 0‐ to 10‐cm soil layer, with single explanatory power of 53.4%, as the most important predictor. The whole explanatory power of the methods including soil variables during the reproductive stage and yield components, with/without soil variables before planting, increased to 81.3%. The residual sodium carbonate, measured in the 0‐ to 10‐cm soil layer during the reproductive stage, was identified as the most limiting factor due to its single maximum explanatory power of 60.5%. We conclude that inclusion of soil properties, measured during the reproductive stage, has potential for improving the rice yield prediction accuracy by enhancing the explanatory power in identification of the most limiting factor. These results encourage further investigation of the role of soil properties during sensitive stages of crop growth in crop yield prediction under different soil and climatic conditions. [ABSTRACT FROM AUTHOR]

Objective: To identify a cut-off value for the 50-g glucose challenge test (GCT) that predicts excess delivery weight.Methods: A retrospective study was conducted among pregnant women who undertook a 50-g GCT at Hacettepe University Hospital, Ankara, Turkey, between January 1, 2000, and December 31, 2016. Patients with singleton pregnancies who delivered live neonates after 28 weeks of pregnancy were included. Patients were classified according to their 50-g GCT values into group 1 (<7.770 mmol/L); group 2 (7.770 to <8.880 mmol/L, group 3 (8.880-9.990 mmol/L); or group 4 (>9.990 mmol/L). Classification and regression tree data mining was performed to identify the 50-g GCT cut-off value corresponding to a substantial increase in delivery weight., Results: Median delivery weight were 3100 g in group 1 (n=352), 3200 g in group 2 (n=165), 3720 g in group 3 (n=47), and 3865 g in group 4 (n=20). Gravidity, 50-g GCT value, and pregnancy duration at delivery explained 30.6% of the observed variance in delivery weight. The cut-off required for maternal blood glucose level to predict excessive delivery weight was 8.741 mmol/L.Conclusion: The 50-g GCT can be used to identify women at risk of delivering offspring with excessive delivery weight. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, an online soft computing model based on an integration between the fuzzy ARTMAP (FAM) neural network and the classification and regression tree (CART) for undertaking data classification problems is presented. Online FAM network is useful for conducting incremental learning with data samples, whereas the CART model prevails in depicting the knowledge learned explicitly in a tree structure. Capitalizing on their respective advantages, the hybrid FAM‐CART model is capable of learning incrementally while explaining its predictions with knowledge elicited from data samples. To evaluate the usefulness of FAM‐CART, 2 sets of benchmark experiments with a total of 12 problems are used in both offline and online learning modes. The results are examined and compared with those published in the literature. The experimental outcome positively indicates that the online FAM‐CART model is useful for tackling data classification tasks. In addition, a decision tree is produced to allow users in understanding the predictions, which is an important property of the hybrid FAM‐CART model in supporting decision‐making tasks. [ABSTRACT FROM AUTHOR]

Interacting effects of climate change and livestock grazing on semi-arid grassland ecosystems have not been well studied, especially on a long-term basis. This paper analyzes changes in plant community composition in relation to grazing intensity and climate change based on repeated monitoring along long-term grazing intensity gradients in three Mongolian ecological zones over 20 yr. We synthesized our findings into state-and-transition models of vegetation change, contributing to our understanding of ecological dynamics in relation to management and environmental change, and to the development of tools for resilience-based rangeland management. In the mountain steppe (MS), community composition was driven largely by climate, and transitions from one community to another were associated with climate change or combined climate and grazing effects. The MS experienced the largest number of long-term transitions (14 of 15 plots) over 20 yr. In the steppe (ST), grazing intensity was the strongest influence on community composition, but transitions between communities from the early 1990s to 2013 were most strongly correlated with climate change. Ten of the 15 ST plots transitioned to other communities over 20 yr. Community composition in the desert steppe (DS) was unrelated to either grazing intensity or climate change and only six of 15 plots transitioned permanently over 20 yr. The MS appears most vulnerable to climate-induced community change, as others have suggested. Some degraded ST communities are resilient to climate change, while ST communities on drier sites are vulnerable to grazing-induced community changes. Our findings illustrate the utility of state-and-transition models as a means to synthesize and depict plant community dynamics in relation to climate and management factors. These models identify communities that may be growing rarer or more common under the combined effects of climate change and grazing, and highlight species and communities that may be useful conservation targets or indicators of climate- or grazing-induced change. [ABSTRACT FROM AUTHOR]

Introduction: Among women with a fetus with a non-cephalic presentation, external cephalic version (ECV) has been shown to reduce the rate of breech presentation at birth and cesarean birth. Compared with ECV at term, beginning ECV prior to 37 weeks' gestation decreases the number of infants in a non-cephalic presentation at birth. The purpose of this secondary analysis was to investigate factors associated with a successful ECV procedure and to present this in a clinically useful format.Material and Methods: Data were collected as part of the Early ECV Pilot and Early ECV2 Trials, which randomized 1776 women with a fetus in breech presentation to either early ECV (34-36 weeks' gestation) or delayed ECV (at or after 37 weeks). The outcome of interest was successful ECV, defined as the fetus being in a cephalic presentation immediately following the procedure, as well as at the time of birth. The importance of several factors in predicting successful ECV was investigated using two statistical methods: logistic regression and classification and regression tree (CART) analyses.Results: Among nulliparas, non-engagement of the presenting part and an easily palpable fetal head were independently associated with success. Among multiparas, non-engagement of the presenting part, gestation less than 37 weeks and an easily palpable fetal head were found to be independent predictors of success. These findings were consistent with results of the CART analyses.Conclusions: Regardless of parity, descent of the presenting part was the most discriminating factor in predicting successful ECV and cephalic presentation at birth. [ABSTRACT FROM AUTHOR]

Aim: Data mining enables further insights from nutrition ‐ related research, but caution is required. The aim of this analysis was to demonstrate and compare the utility of data mining methods in classifying a categorical outcome derived from a nutrition ‐ related intervention. Methods: Baseline data (23 variables, 8 categorical) on participants (n = 295) in an intervention trial were used to classify participants in terms of meeting the criteria of achieving 10 000 steps per day. Results from classification and regression trees (CARTs), random forests, adaptive boosting, logistic regression, support vector machines and neural networks were compared using area under the curve (AUC) and error assessments. Results: The CART produced the best model when considering the AUC (0.703), overall error (18%) and within class error (28%). Logistic regression also performed reasonably well compared to the other models (AUC 0.675, overall error 23%, within class error 36%). All the methods gave different rankings of variables’ importance. CART found that body fat, quality of life using the SF ‐ 12 Physical Component Summary (PCS) and the cholesterol: HDL ratio were the most important predictors of meeting the 10 000 steps criteria, while logistic regression showed the SF ‐ 12PCS, glucose levels and level of education to be the most significant predictors (P ≤ 0.01). Conclusions: Differing outcomes suggest caution is required with a single data mining method, particularly in a dataset with nonlinear relationships and outliers and when exploring relationships that were not the primary outcomes of the research. [ABSTRACT FROM AUTHOR]

At present, there is no ideal model for predicting the short-term outcome of patients with acute-on-chronic hepatitis B liver failure ( ACHBLF). This study aimed to establish and validate a prognostic model by using the classification and regression tree ( CART) analysis. A total of 1047 patients from two separate medical centres with suspected ACHBLF were screened in the study, which were recognized as derivation cohort and validation cohort, respectively. CART analysis was applied to predict the 3-month mortality of patients with ACHBLF. The accuracy of the CART model was tested using the area under the receiver operating characteristic curve, which was compared with the model for end-stage liver disease ( MELD) score and a new logistic regression model. CART analysis identified four variables as prognostic factors of ACHBLF: total bilirubin, age, serum sodium and INR, and three distinct risk groups: low risk (4.2%), intermediate risk (30.2%-53.2%) and high risk (81.4%-96.9%). The new logistic regression model was constructed with four independent factors, including age, total bilirubin, serum sodium and prothrombin activity by multivariate logistic regression analysis. The performances of the CART model (0.896), similar to the logistic regression model (0.914, P=.382), exceeded that of MELD score (0.667, P<.001). The results were confirmed in the validation cohort. We have developed and validated a novel CART model superior to MELD for predicting three-month mortality of patients with ACHBLF. Thus, the CART model could facilitate medical decision-making and provide clinicians with a validated practical bedside tool for ACHBLF risk stratification. [ABSTRACT FROM AUTHOR]

Data mining methods for classification and regression are becoming increasingly popular in various scientific fields. However, these methods have not been explored much in educational measurement. This module first provides a review, which should be accessible to a wide audience in education measurement, of some of these methods. The module then demonstrates using three real-data examples that these methods may lead to an improvement over traditionally used methods such as linear and logistic regression in educational measurement. [ABSTRACT FROM AUTHOR]

Reasons for performing study There are few studies on the correlations between radiographic measurements of the foot and abnormalities of specific structures found with magnetic resonance imaging ( MRI). Objectives To document the relationship between radiographic measurements of the equine foot and the presence of lesions in the foot on MRI. We hypothesised that different radiographic measurements would be associated with specific lesions detected by MRI. Study design Retrospective analysis of radiographs and MRI studies. Methods Seventy-four feet from 52 lame horses were included. Twenty parameters were measured on radiographs, whereas the signal intensity, homogeneity and size of each structure in the foot were evaluated on magnetic resonance images. The data were analysed using simple linear correlation analysis and classification and regression trees ( CARTs). Results Linear correlations were found between the navicular bone compacta thickness and injuries of the deep digital flexor tendon, collateral sesamoidean ligament, navicular spongiosa and navicular bone proximal border. Long-toed horses had a high incidence of lesions involving the spongiosa and proximal border of the navicular bone. Elongation of the navicular bone was associated with proximal and distal border injuries. A reduced palmar angle and increased angle between the middle and distal phalanx were observed in horses with alterations of collateral ligaments of the distal interphalangeal joint and navicular bone spongiosa, respectively. For each structure under investigation, CARTs predicting the presence of MRI pathology based on radiographic measurements had excellent performance, with >80% correct classification of cases, when using one of 3 data sources. Conclusions This study demonstrated a relationship between radiographic measurements of the foot and the presence of lesions detected on MRI, while CARTs illustrated that different radiographic measurements were associated with different MRI lesions. [ABSTRACT FROM AUTHOR]

Introduction Haemophilia is a rare genetic haemorrhagic disease characterized by partial or complete deficiency of coagulation factor VIII, for haemophilia A, or IX, for haemophilia B. As in any other medical research domain, the field of haemophilia research is increasingly concerned with finding factors associated with binary or continuous outcomes through multivariable models. Traditional models include multiple logistic regressions, for binary outcomes, and multiple linear regressions for continuous outcomes. Yet these regression models are at times difficult to implement, especially for non-statisticians, and can be difficult to interpret. Aims The present paper sought to didactically explain how, why, and when to use classification and regression tree (CART) analysis for haemophilia research. Materials & methods The CART method is non-parametric and non-linear, based on the repeated partitioning of a sample into subgroups based on a certain criterion. Breiman developed this method in 1984. Classification trees (CTs) are used to analyse categorical outcomes and regression trees (RTs) to analyse continuous ones. Results The CART methodology has become increasingly popular in the medical field, yet only a few examples of studies using this methodology specifically in haemophilia have to date been published. Two examples using CART analysis and previously published in this field are didactically explained in details. Conclusion There is increasing interest in using CART analysis in the health domain, primarily due to its ease of implementation, use, and interpretation, thus facilitating medical decision-making. This method should be promoted for analysing continuous or categorical outcomes in haemophilia, when applicable. [ABSTRACT FROM AUTHOR]

Background Identification of patient subgroups to enhance treatment effects is an important topic in personalized (or tailored) alcohol treatment. Recently, several recursive partitioning methods have been proposed to identify subgroups benefiting from treatment. These novel data mining methods help to address the limitations of traditional regression-based methods that focus on interactions. Methods We propose an exploratory approach, using recursive partitioning methods, for example, interaction trees (IT) and virtual twins ( VT), to flexibly identify subgroups in which the treatment effect is likely to be large. We apply these tree-based methods to a pharmacogenetic trial of ondansetron. Results Our methods identified several subgroups based on patients' genetic and other prognostic covariates. Among the 251 subjects with complete genotype information, the IT method identified 118 with specific genetic and other prognostic factors, resulting in a 17.2% decrease in the percentage of heavy drinking days ( PHDD). The VT method identified 88 subjects with a 21.8% decrease in PHDD. Overall, the VT subgroup achieved a good balance between the treatment effect and the group size. Conclusions A data mining approach is proposed as a valid exploratory method to identify a sufficiently large subgroup of subjects that is likely to receive benefit from treatment in an alcohol dependence pharmacotherapy trial. Our results provide new insights into the heterogeneous nature of alcohol dependence and could help clinicians to tailor treatment to the biological profile of individual patients, thereby achieving better treatment outcomes. [ABSTRACT FROM AUTHOR]

Boosting is one of the most important strategies in ensemble learning because of its ability to improve the stability and performance of weak learners. It is nonparametric, multivariate, fast and interpretable but is not robust against outliers. To enhance its prediction accuracy as well as immunize it against outliers, a modified version of a boosting algorithm (AdaBoost R2) was developed and called AdaBoost R3. In the sampling step, extremum samples were added to the boosting set. In the robustness step, a modified Huber loss function was applied to overcome the outlier problem. In the output step, a deterministic threshold was used to guarantee that bad predictions do not participate in the final output. The performance of the modified algorithm was investigated with two anticancer data sets of tyrosine kinase inhibitors, and the mechanism of inhibition was studied using the relative weighted variable importance procedure. Investigating the effect of base learner's strength reveals that boosting is only successful using the classification and regression tree method (a weak to moderate learner) and does not have a significant effect using the radial basis functions partial least square method (a strong base learners). Copyright © 2015 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Background A wide spectrum of laboratory tests is available to aid diagnosis and classification of equine inflammatory disease. Objectives To compare diagnostic efficacy and combined predictive capability of the myeloperoxidase index ( MPXI), and plasma fibrinogen, iron and serum amyloid A ( SAA) concentrations for the diagnosis of inflammation. Animals Twenty-six hospitalized horses with systemic inflammation ( SI), 114 with local inflammation ( LI) and 61 healthy horses or those with noninflammatory disease ( NI) were included. Methods A retrospective study was performed; clinicopathologic data from horses were compared between groups. Receiver-operator characteristic ( ROC) curves were used to evaluate diagnostic efficacy; classification and regression tree analysis ( CART) and logistic regression analysis were used to generate diagnostic algorithms. Results Horses with SI had significantly higher SAA than horses with LI ( P = .007) and NI ( P < .001) and lower iron concentrations than horses with LI ( P < .001) and NI ( P < .001). Fibrinogen concentration was higher in horses with inflammation than in those without inflammation ( P = .002). There was no difference between the SI and LI groups. White blood cell count, neutrophil count and MPXI were similar between groups. SAA had the highest accuracy for diagnosing inflammation (area under ROC curve [ AUC], 0.83 ± 0.06) and iron and SAA concentration had the highest accuracy for differentiating SI from LI ( AUC, 0.80 ± 0.09 and 0.73 ± 0.10 respectively). Predictive modeling failed to generate useful algorithms and classification of cases was moderate. Conclusions and Clinical Importance Very high SAA and low iron concentrations may reflect SI, but diagnostic guidelines based on quantitative results of inflammatory markers could not be formulated. [ABSTRACT FROM AUTHOR]

Background and purpose Migraine pathophysiology involves a complex interplay of processes wherein the hormonal, neurotransmitter and inflammatory pathways interact to influence the migraine phenotype. However, all studies pertaining to the role of genetic variants in migraine have been restricted to a specific pathway and none of the studies has looked into inter-pathway genetic analysis. Our aim was to combine all the genetic variants from our previously reported studies to conduct higher order gene-gene interaction analysis using different multi-analytical approaches. Methods The study group included 324 migraine patients and 134 healthy controls. The study included 20 polymorphisms from hormonal, neurotransmitter, inflammatory and genome-wide associated variants from our published reports. Univariate and multivariate analyses were carried out by logistic regression. Classification and regression tree ( CART) analysis was performed to build a decision tree via recursive partitioning. The high order genetic interactions associated with migraine risk were analyzed using multifactor dimensionality reduction ( MDR). Results Univariate analysis revealed significant associations of polymorphisms in CYP19 A1, ESR1, TNFA and PRDM16 genes with migraine susceptibility. Multiple regression analysis found significant results for four markers in CYP19 A1, TNFA, ESR1 and LRP1 genes. In CART, the most prominent splitting variable was CYP19 A1 polymorphism followed by TNFA, ESR1 and PRDM16 markers. The MDR analysis identified markers of CYP19 A1, CYP19 A1- TNFA, CYP19A1- ESR1- TNFA and CYP19 A1- ESR1- TRPM8- PRDM16 as best models for one, two, three and four factors, respectively. Conclusions The present study suggests interactions amongst hormonal, inflammatory and genome-wide associated variants but not with neurotransmitter pathway variants in migraine susceptibility. [ABSTRACT FROM AUTHOR]

Background The FRAX algorithm is a diffuse tool to assess fracture risk, but it has not been clinically applied in European patients with diabetes. We investigated FRAX-estimated fracture risk in patients with type 2 diabetes mellitus (DM), compared with concomitantly enrolled control subjects. Methods In our multicentric cross-sectional study, we assessed the FRAX scores of 974 DM and 777 control subjects from three Italian diabetes outpatient clinics, and in DM. We tested the association between parameters and complications of the disease and FRAX scores. Results DM had significantly lower FRAX-estimated probability of both major osteoporotic fracture (MOF) and hip fracture (HF) than control subjects (6.35 ± 5.07% versus 7.75 ± 6.93%, p < 0.001, and 2.17 ± 3.07% versus 2.91 ± 4.56%, p = 0.023, respectively). When grouping by gender, such differences were found only in men. In DM, the frequency of previous fracture was higher than in control subjects (29.88% versus 20.46%, p < 0.001). In diabetic patients, age, sex, body mass index, HbA1c and hypoglycaemia are significantly associated with FRAX scores; gender-specific regression models differed. Among DM, the tree-based regression (classification and regression tree (CART)) analysis identified groups of patients with different mean FRAX scores. In female DM aged >65 years with or without obesity, MOF > 20% was found in 5.66% and 13.53% and HF > 3% in 40.57% and 63.91% of patients, respectively. Conclusions Patients with DM had mean FRAX scores lower than control subjects, despite the higher number of previous fractures. Some features and complications of DM did associate with FRAX scores. Among DM patients, the CART analysis identified subgroups with higher FRAX scores. However, despite its potential utility, concerns still remain for using FRAX in DM patients. Copyright © 2013 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The development of screening instruments for psychiatric disorders involves item selection from a pool of items in existing questionnaires assessing clinical and behavioral phenotypes. A screening instrument should consist of only a few items and have good accuracy in classifying cases and non-cases. Variable/item selection methods such as Least Absolute Shrinkage and Selection Operator (LASSO), Elastic Net, Classification and Regression Tree, Random Forest, and the two-sample t-test can be used in such context. Unlike situations where variable selection methods are most commonly applied (e.g., ultra high-dimensional genetic or imaging data), psychiatric data usually have lower dimensions and are characterized by the following factors: correlations and possible interactions among predictors, unobservability of important variables (i.e., true variables not measured by available questionnaires), amount and pattern of missing values in the predictors, and prevalence of cases in the training data. We investigate how these factors affect the performance of several variable selection methods and compare them with respect to selection performance and prediction error rate via simulations. Our results demonstrated that: (1) for complete data, LASSO and Elastic Net outperformed other methods with respect to variable selection and future data prediction, and (2) for certain types of incomplete data, Random Forest induced bias in imputation, leading to incorrect ranking of variable importance. We propose the Imputed-LASSO combining Random Forest imputation and LASSO; this approach offsets the bias in Random Forest and offers a simple yet efficient item selection approach for missing data. As an illustration, we apply the methods to items from the standard Autism Diagnostic Interview-Revised version. Copyright © 2013 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Kernel partial least squares (KPLS) has become a popular technique for regression and classification of complex data sets, which is a nonlinear extension of linear PLS in which training samples are transformed into a feature space via a nonlinear mapping. The PLS algorithm can then be carried out in the feature space. In the present study, we attempt to develop a novel tree KPLS (TKPLS) classification algorithm by constructing an informative kernel on the basis of decision tree ensembles. The constructed tree kernel can effectively discover the similarities of samples and select informative features by variable importance ranking in the process of building the kernel. Simultaneously, TKPLS can also handle nonlinear relationships in the structure-activity relationship data by such a kernel. Finally, three data sets related to different categorical bioactivities of compounds are used to evaluate the performance of TKPLS. The results show that the TKPLS algorithm can be regarded as an alternative and promising classification technique. Copyright © 2013 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

The article discusses the study based on habitat models to determine species habitat requirement conservation efforts. It mentions that the mode of measurement of environmental predictors can affect the model performance. It also reports that landscape predictors are best represented by landscape composition-based measurements rather than distance-based measurements.

Background The Integrated Relaxation Pressure (IRP) is the esophageal pressure topography (EPT) metric used for assessing the adequacy of esophagogastric junction (EGJ) relaxation in the Chicago Classification of motility disorders. However, because the IRP value is also influenced by distal esophageal contractility, we hypothesized that its normal limits should vary with different patterns of contractility. Methods Five hundred and twenty two selected EPT studies were used to compare the accuracy of alternative analysis paradigms to that of a motility expert (the 'gold standard'). Chicago Classification metrics were scored manually and used as inputs for MATLAB™ programs that utilized either strict algorithm-based interpretation (fixed abnormal IRP threshold of 15 mmHg) or a classification and regression tree (CART) model that selected variable IRP thresholds depending on the associated esophageal contractility. Key Results The sensitivity of the CART model for achalasia (93%) was better than that of the algorithm-based approach (85%) on account of using variable IRP thresholds that ranged from a low value of >10 mmHg to distinguish type I achalasia from absent peristalsis to a high value of >17 mmHg to distinguish type III achalasia from distal esophageal spasm. Additionally, type II achalasia was diagnosed solely by panesophageal pressurization without the IRP entering the algorithm. Conclusions & Inferences Automated interpretation of EPT studies more closely mimics that of a motility expert when IRP thresholds for impaired EGJ relaxation are adjusted depending on the pattern of associated esophageal contractility. The range of IRP cutoffs suggested by the CART model ranged from 10 to 17 mmHg. [ABSTRACT FROM AUTHOR]

The article presents a study which compares statistical and theoretical habitat modeling approaches used for avian conservation planning. It focuses on models for priority forest-breeding species when comparing the models. It uses rank correlations among model outputs and comparison of spatial correspondence to illuminate the differences between the approaches. It notes that rank correlations were positive on models for avian species which indicate an agreement among models.

In order to reduce the variation in a manufacturing process, traditional statistical process control (SPC) techniques are the most frequently used tools in monitoring engineering process control (EPC)-controlled processes for detecting assignable cause process variation. Even though application of SPC with EPC can successfully detect time points when abnormalities occur during process, their combination can also cause an increased occurrence of false alarms when autocorrelation is present in the process. In this paper, we propose an independent component analysis-based signal extraction technique with classification and regression tree approach to identify disturbance levels in the correlated process parameters. For comparison, traditional cumulative sum (CUSUM) chart was constructed to evaluate the identifying capability of the proposed approach. The experimental results show that the proposed method outperforms CUSUM control chart in most instances. Copyright © 2008 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Aim To investigate the influence of sampling and methodological artefacts on the correlation between abundance and occupancy. Location Global scope. Methods A fixed effects weighted regression model was fitted to standardized effect size for 175 examples of correlations between abundance and occupancy. A regression tree model with standard effect size as the dependent variable was also fitted to the data. Results Standard effect size, and therefore the correlation between abundance and occupancy, was found to be strongly influenced by the type of abundance measure used to characterize the abundance–occupancy relationship. Local mean abundance (also referred to as ecological mean abundance) was primarily responsible for negative correlations. Negative correlations also resulted from a mismatch in the sampling extents of abundance and occupancy measures. Main conclusions The combination of abundance and occupancy measures selected to characterize the abundance–occupancy relationship for a given set of data has a profound impact on the sign of the correlation between the selected measures. Previous attempts to understand the processes giving rise to the pattern represented by the abundance–occupancy relationship have confounded sampling artefacts (e.g. spatial extent of abundance and occupancy information) and methodological artefacts (e.g. combining a truncated abundance measure such as local mean abundance with an untruncated occupancy measure such as proportion of occupied samples). Thus, a revision of the approach currently used to define and evaluate competing explanatory models of the abundance–occupancy relationship appears to be necessary. [ABSTRACT FROM AUTHOR]

OBJECTIVE To evaluate several methods of predicting prostate cancer-related outcomes, i.e. nomograms, look-up tables, artificial neural networks (ANN), classification and regression tree (CART) analyses and risk-group stratification (RGS) models, all of which represent valid alternatives. METHODS We present four direct comparisons, where a nomogram was compared to either an ANN, a look-up table, a CART model or a RGS model. In all comparisons we assessed the predictive accuracy and performance characteristics of both models. RESULTS Nomograms have several advantages over ANN, look-up tables, CART and RGS models, the most fundamental being a higher predictive accuracy and better performance characteristics. CONCLUSION These results suggest that nomograms are more accurate and have better performance characteristics than their alternatives. However, ANN, look-up tables, CART analyses and RGS models all rely on methodologically sound and valid alternatives, which should not be abandoned. [ABSTRACT FROM AUTHOR]

A population of endangered Sonoran pronghorn (Antilocapra americana sonoriensis the United States, and 2 populations exist in Mexico. Because of the vulnerability of small, remnant populations of this subspecies to stochastic events, an important aspect of recovery planning is identifying suitable areas for establishment of new populations. To support translocation efforts, we developed landscape- level Classification and Regression Tree (CARD and logistic regression models of potential Sonoran pronghorn habitat in southwestern Arizona through a 2-part modeling process. First, we used approximately half of Sonoran pronghorn locations (total n=3,219, collected from 1994 to 2002 from radiocollared animals in the United States) and unused points (total n=3,142, randomly generated in areas with in the range of Sonoran pronghorn below 21% slope, but >1.6 km from pronghorn locations) to create habitat models from 5 explanatory variables (i.e., slope, aspect, biome, distance to wash, and soil category). We validated models with the second half of pronghorn and unused points. Both models determined whether areas would or would not be used by Sonoran pronghorn based upon values of explanatory variables at Sonoran pronghorn locations and unused points. The CART model correctly identified 63% of pronghorn locations and 65% of unused points. The logistic regression model correctly identified 57% of pronghorn locations and 62% of unused points. Second, we created a predictive Geographic Information System (GIS) map of Sonoran pronghorn habitat and applied it to the evaluation area. Both models identified >12,000 km2 of potential habitat for Sonoran pronghorn on the evaluation area. Our models are a first step toward identifying potential translocation sites for Sonoran pronghorn. Potential translocation sites should be further evaluated with respect to habitat factors not included in our models, including barriers to pronghorn movements, water supplies, and forage resources. [ABSTRACT FROM AUTHOR]

Logistic Multiple Regression, Principal Component Regression and Classification and Regression Tree Analysis (CART), commonly used in ecological modelling using GIS, are compared with a relatively new statistical technique, Multivariate Adaptive Regression Splines (MARS), to test their accuracy, reliability, implementation within GIS and ease of use. All were applied to the same two data sets, covering a wide range of conditions common in predictive modelling, namely geographical range, scale, nature of the predictors and sampling method. We ran two series of analyses to verify if model validation by an independent data set was required or cross-validation on a learning data set sufficed. Results show that validation by independent data sets is needed. Model accuracy was evaluated using the area under Receiver Operating Characteristics curve (AUC). This measure was used because it summarizes performance across all possible thresholds, and is independent of balance between classes. MARS and Regression Tree Analysis achieved the best prediction success, although the CART model was difficult to use for cartographic purposes due to the high model complexity. [ABSTRACT FROM AUTHOR]