Classification and regression tree (CART) model to predict pulmonary tuberculosis in hospitalized patients

Background: Tuberculosis (TB) remains a public health issue worldwide. The lack of specific clinical symptoms to diagnose TB makes the correct decision to admit patients to respiratory isolation a difficult task for the clinician. Isolation of patients without the disease is common and increases health costs. Decision models for the diagnosis of TB in patients attending hospitals can increase the quality of care and decrease costs, without the risk of hospital transmission. We present a predictive model for predicting pulmonary TB in hospitalized patients in a high prevalence area in order to contribute to a more rational use of isolation rooms without increasing the risk of transmission. Methods: Cross sectional study of patients admitted to CFFH from March 2003 to December 2004. A classification and regression tree (CART) model was generated and validated. The area under the ROC curve (AUC), sensitivity, specificity, positive and negative predictive values were used to evaluate the performance of model. Validation of the model was performed with a different sample of patients admitted to the same hospital from January to December 2005. Results: We studied 290 patients admitted with clinical suspicion of TB. Diagnosis was confirmed in 26.5% of them. Pulmonary TB was present in 83.7% of the patients with TB (62.3% with positive sputum smear) and HIV/AIDS was present in 56.9% of patients. The validated CART model showed sensitivity, specificity, positive predictive value and negative predictive value of 60.00%, 76.16%, 33.33%, and 90.55%, respectively. The AUC was 79.70%. Conclusions: The CART model developed for these hospitalized patients with clinical suspicion of TB had fair to good predictive performance for pulmonary TB. The most important variable for prediction of TB diagnosis was chest radiograph results. Prospective validation is still necessary, but our model offer an alternative for decision making in whether to isolate patients with clinical suspicion of TB in tertiary health facilities in countries with limited resources.

The use of classification and regression trees to predict the likelihood of seasonal influenza.

Background Individual signs and symptoms are of limited value for the diagnosis of influenza. Objective To develop a decision tree for the diagnosis of influenza based on a classification and regression tree (CART) analysis. Methods Data from two previous similar cohort studies were assembled into a single dataset. The data were randomly divided into a development set (70%) and a validation set (30%). We used CART analysis to develop three models that maximize the number of patients who do not require diagnostic testing prior to treatment decisions. The validation set was used to evaluate overfitting of the model to the training set. Results Model 1 has seven terminal nodes based on temperature, the onset of symptoms and the presence of chills, cough and myalgia. Model 2 was a simpler tree with only two splits based on temperature and the presence of chills. Model 3 was developed with temperature as a dichotomous variable (≥38°C) and had only two splits based on the presence of fever and myalgia. The area under the receiver operating characteristic curves (AUROCC) for the development and validation sets, respectively, were 0.82 and 0.80 for Model 1, 0.75 and 0.76 for Model 2 and 0.76 and 0.77 for Model 3. Model 2 classified 67% of patients in the validation group into a high- or low-risk group compared with only 38% for Model 1 and 54% for Model 3. Conclusions A simple decision tree (Model 2) classified two-thirds of patients as low or high risk and had an AUROCC of 0.76. After further validation in an independent population, this CART model could support clinical decision making regarding influenza, with low-risk patients requiring no further evaluation for influenza and high-risk patients being candidates for empiric symptomatic or drug therapy.

Improving generalized regression analysis for the spatial prediction of forest communities

Aim This study used data from temperate forest communities to assess: (1) five different stepwise selection methods with generalized additive models, (2) the effect of weighting absences to ensure a prevalence of 0.5, (3) the effect of limiting absences beyond the environmental envelope defined by presences, (4) four different methods for incorporating spatial autocorrelation, and (5) the effect of integrating an interaction factor defined by a regression tree on the residuals of an initial environmental model. Location State of Vaud, western Switzerland. Methods Generalized additive models (GAMs) were fitted using the grasp package (generalized regression analysis and spatial predictions, http://www.cscf.ch/grasp). Results Model selection based on cross-validation appeared to be the best compromise between model stability and performance (parsimony) among the five methods tested. Weighting absences returned models that perform better than models fitted with the original sample prevalence. This appeared to be mainly due to the impact of very low prevalence values on evaluation statistics. Removing zeroes beyond the range of presences on main environmental gradients changed the set of selected predictors, and potentially their response curve shape. Moreover, removing zeroes slightly improved model performance and stability when compared with the baseline model on the same data set. Incorporating a spatial trend predictor improved model performance and stability significantly. Even better models were obtained when including local spatial autocorrelation. A novel approach to include interactions proved to be an efficient way to account for interactions between all predictors at once. Main conclusions Models and spatial predictions of 18 forest communities were significantly improved by using either: (1) cross-validation as a model selection method, (2) weighted absences, (3) limited absences, (4) predictors accounting for spatial autocorrelation, or (5) a factor variable accounting for interactions between all predictors. The final choice of model strategy should depend on the nature of the available data and the specific study aims. Statistical evaluation is useful in searching for the best modelling practice. However, one should not neglect to consider the shapes and interpretability of response curves, as well as the resulting spatial predictions in the final assessment.

Tree-structured smooth transition models

The goal of this paper is to introduce a class of tree-structured models that combines aspects of regression trees and smooth transition regression models. The model is called the Smooth Transition Regression Tree (STR-Tree). The main idea relies on specifying a multiple-regime parametric model through a tree-growing procedure with smooth transitions among different regimes. Decisions about splits are entirely based on a sequence of Lagrange Multiplier (LM) tests of hypotheses.

Predicting smear negative pulmonary tuberculosis with classification trees and logistic regression: a cross-sectional study

Abstract Background Smear negative pulmonary tuberculosis (SNPT) accounts for 30% of pulmonary tuberculosis cases reported yearly in Brazil. This study aimed to develop a prediction model for SNPT for outpatients in areas with scarce resources. Methods The study enrolled 551 patients with clinical-radiological suspicion of SNPT, in Rio de Janeiro, Brazil. The original data was divided into two equivalent samples for generation and validation of the prediction models. Symptoms, physical signs and chest X-rays were used for constructing logistic regression and classification and regression tree models. From the logistic regression, we generated a clinical and radiological prediction score. The area under the receiver operator characteristic curve, sensitivity, and specificity were used to evaluate the model's performance in both generation and validation samples. Results It was possible to generate predictive models for SNPT with sensitivity ranging from 64% to 71% and specificity ranging from 58% to 76%. Conclusion The results suggest that those models might be useful as screening tools for estimating the risk of SNPT, optimizing the utilization of more expensive tests, and avoiding costs of unnecessary anti-tuberculosis treatment. Those models might be cost-effective tools in a health care network with hierarchical distribution of scarce resources.

A fuzzy decision tree-based duration model for Standard Yorùbá text-to-speech synthesis

In this paper, we present syllable-based duration modelling in the context of a prosody model for Standard Yorùbá (SY) text-to-speech (TTS) synthesis applications. Our prosody model is conceptualised around a modular holistic framework. This framework is implemented using the Relational Tree (R-Tree) techniques. An important feature of our R-Tree framework is its flexibility in that it facilitates the independent implementation of the different dimensions of prosody, i.e. duration, intonation, and intensity, using different techniques and their subsequent integration. We applied the Fuzzy Decision Tree (FDT) technique to model the duration dimension. In order to evaluate the effectiveness of FDT in duration modelling, we have also developed a Classification And Regression Tree (CART) based duration model using the same speech data. Each of these models was integrated into our R-Tree based prosody model. We performed both quantitative (i.e. Root Mean Square Error (RMSE) and Correlation (Corr)) and qualitative (i.e. intelligibility and naturalness) evaluations on the two duration models. The results show that CART models the training data more accurately than FDT. The FDT model, however, shows a better ability to extrapolate from the training data since it achieved a better accuracy for the test data set. Our qualitative evaluation results show that our FDT model produces synthesised speech that is perceived to be more natural than our CART model. In addition, we also observed that the expressiveness of FDT is much better than that of CART. That is because the representation in FDT is not restricted to a set of piece-wise or discrete constant approximation. We, therefore, conclude that the FDT approach is a practical approach for duration modelling in SY TTS applications. © 2006 Elsevier Ltd. All rights reserved.

Impact of cancer-related symptom synergisms on health-related quality of life and performance status

To identify the impact of multiple symptoms and their co-occurrence on health-related quality of life (HRQOL) dimensions and performance status (PS), 115 outpatients with cancer, who were not receiving active cancer treatment and were recruited from, a university hospital in Sao Paulo, Brazil completed the European Organization for Research and Treatment of Cancer Quality of Life Questionnaire-C30, the Beck Depression Inventory, and the Brief Pain Inventory. Karnofsky Performance Status scores also were completed. Application of TwoStep Cluster analysis resulted in two distinct patient subgroups based on 113 patient experiences with pain, depression, fatigue, insomnia, constipation, lack of appetite, dyspnea, nausea, vomiting, and diarrhea. One group had multiple and severe symptom subgroup and another had Less symptoms and with lower severity. Multiple and severe symptoms had worse PS, role functioning, and physical, emotional, cognitive, social, and overall HRQOL. Multiple and severe symptom subgroup was also six times as likely as lower severity to have poor role functioning;five times more likely to have poor emotional;four times more likely to have poor PS, physical, and overall HRQOL, and three times as likely to have poor cognitive and social HRQOL, independent of gender, age, level of education, and economic condition. Classification and Regression Tree analyses were undertaken to identify which co-occurring symptoms would best determine reduction in HRQOL and PS. Pain and fatigue were identified as indicators of reduction on physical HRQOL and PS. Fatigue and insomnia were associated with reduction in cognitive; depression and pain in social; and fatigue and constipation in role functioning. Only depression was associated with reduction in overall HRQOL. These data demonstrate that there is a synergic effect among distinct cancer symptoms that result in reduction in HRQOL dimensions and PS.

Context-based identification of energy consumption in industrial plants

Nowadays, reducing energy consumption is one of the highest priorities and biggest challenges faced worldwide and in particular in the industrial sector. Given the increasing trend of consumption and the current economical crisis, identifying cost reductions on the most energy-intensive sectors has become one of the main concerns among companies and researchers. Particularly in industrial environments, energy consumption is affected by several factors, namely production factors(e.g. equipments), human (e.g. operators experience), environmental (e.g. temperature), among others, which influence the way of how energy is used across the plant. Therefore, several approaches for identifying consumption causes have been suggested and discussed. However, the existing methods only provide guidelines for energy consumption and have shown difficulties in explaining certain energy consumption patterns due to the lack of structure to incorporate context influence, hence are not able to track down the causes of consumption to a process level, where optimization measures can actually take place. This dissertation proposes a new approach to tackle this issue, by on-line estimation of context-based energy consumption models, which are able to map operating context to consumption patterns. Context identification is performed by regression tree algorithms. Energy consumption estimation is achieved by means of a multi-model architecture using multiple RLS algorithms, locally estimated for each operating context. Lastly, the proposed approach is applied to a real cement plant grinding circuit. Experimental results prove the viability of the overall system, regarding both automatic context identification and energy consumption estimation.

Health-related quality of life assessment in people with multiple sclerosis and their family caregivers. A multicenter study in Catalonia (Southern Europe)

Objectives: To measure the health-related quality of life (HRQoL) of multiple sclerosis (MS) patients and their caregivers, and to assess which factors can best describe HRQoL. Methods: A cross-sectional multicenter study of nine hospitals enrolled MS patients and their caregivers who attended outpatient clinics consecutively. The instruments used were the SF-36 for patients and the SF-12 and GHQ-12 for caregivers. Classification and regression tree analysis was used to analyze the explanatory factors of HRQoL. Results: A total of 705 patients (mean age 40.4 years, median Expanded Disability Status Scale 2.5, 77.8% with relapsing-remitting MS) and 551 caregivers (mean age 45.4 years) participated in the study. MS patients had significantly lower HRQoL than in the general population (physical SF-36: 39.9; 95% confidence interval [CI]: 39.1–40.6; mental SF-36: 44.4; 95% CI: 43.5–45.3). Caregivers also presented lower HRQoL than general population, especially in its mental domain (mental SF-12: 46.4; 95% CI: 45.5–47.3). Moreover, according to GHQ-12, 27% of caregivers presented probable psychological distress. Disability and co-morbidity in patients, and co-morbidity and employment status in caregivers, were the most important explanatory factors of their HRQoL. Conclusions: Not only the HRQoL of patients with MS, but also that of their caregivers, is indeed notably affected. Caregivers’ HRQoL is close to population of chronic illness even that the patients sample has a mild clinical severity and that caregiving role is a usual task in the study context

BrainCheck - a very brief tool to detect incipient cognitive decline: optimized case-finding combining patient- and informant-based data.

INTRODUCTION: Optimal identification of subtle cognitive impairment in the primary care setting requires a very brief tool combining (a) patients' subjective impairments, (b) cognitive testing, and (c) information from informants. The present study developed a new, very quick and easily administered case-finding tool combining these assessments ('BrainCheck') and tested the feasibility and validity of this instrument in two independent studies. METHODS: We developed a case-finding tool comprised of patient-directed (a) questions about memory and depression and (b) clock drawing, and (c) the informant-directed 7-item version of the Informant Questionnaire on Cognitive Decline in the Elderly (IQCODE). Feasibility study: 52 general practitioners rated the feasibility and acceptance of the patient-directed tool. Validation study: An independent group of 288 Memory Clinic patients (mean ± SD age = 76.6 ± 7.9, education = 12.0 ± 2.6; 53.8% female) with diagnoses of mild cognitive impairment (n = 80), probable Alzheimer's disease (n = 185), or major depression (n = 23) and 126 demographically matched, cognitively healthy volunteer participants (age = 75.2 ± 8.8, education = 12.5 ± 2.7; 40% female) partook. All patient and healthy control participants were administered the patient-directed tool, and informants of 113 patient and 70 healthy control participants completed the very short IQCODE. RESULTS: Feasibility study: General practitioners rated the patient-directed tool as highly feasible and acceptable. Validation study: A Classification and Regression Tree analysis generated an algorithm to categorize patient-directed data which resulted in a correct classification rate (CCR) of 81.2% (sensitivity = 83.0%, specificity = 79.4%). Critically, the CCR of the combined patient- and informant-directed instruments (BrainCheck) reached nearly 90% (that is 89.4%; sensitivity = 97.4%, specificity = 81.6%). CONCLUSION: A new and very brief instrument for general practitioners, 'BrainCheck', combined three sources of information deemed critical for effective case-finding (that is, patients' subject impairments, cognitive testing, informant information) and resulted in a nearly 90% CCR. Thus, it provides a very efficient and valid tool to aid general practitioners in deciding whether patients with suspected cognitive impairments should be further evaluated or not ('watchful waiting').

Incidência de úlceras por pressão em pacientes de Unidade de Terapia Intensiva Cardiopneumológica

RESUMO Objetivo Identificar e analisar os coeficientes de incidência de úlceras por pressão (UP) e os fatores de risco para o seu desenvolvimento em pacientes críticos com doenças cardiopneumológicas. Método Estudo de coorte, prospectivo realizado na Unidade de Terapia Intensiva (UTI) Cardiopneumológica de um hospital de grande porte na cidade de São Paulo, durante os meses de novembro de 2013 a fevereiro de 2014. Participaram do estudo 370 pacientes maiores de 18 anos, que não apresentavam UP na admissão e que estavam na UTI há menos de 24 horas. Os dados foram analisados por meio de análises univariadas e multivariada (Classification And Regression Tree - CART). Resultados Os coeficientes de incidência de UP foram: 11,0% para o total, distribuindo-se em 8,0% entre os homens e 3,0% para as mulheres (p=0,018); 10,0% na raça branca e 6,5% em pessoas com idade igual e superior a 60 anos. Os principais fatores de risco encontrados foram tempo de permanência na UTI igual ou superior a 9,5 dias, idade igual ou superior a 42,5 anos e raça branca. Conclusão O estudo contribui para os conhecimentos relacionados à epidemiologia das UP em pacientes críticos com doenças cardiopneumológicas, favorecendo o planejamento de cuidados preventivos específicos para essa clientela.

Predictive analysis and mapping of indoor radon concentrations in Switzerland

It is estimated that around 230 people die each year due to radon (222Rn) exposure in Switzerland. 222Rn occurs mainly in closed environments like buildings and originates primarily from the subjacent ground. Therefore it depends strongly on geology and shows substantial regional variations. Correct identification of these regional variations would lead to substantial reduction of 222Rn exposure of the population based on appropriate construction of new and mitigation of already existing buildings. Prediction of indoor 222Rn concentrations (IRC) and identification of 222Rn prone areas is however difficult since IRC depend on a variety of different variables like building characteristics, meteorology, geology and anthropogenic factors. The present work aims at the development of predictive models and the understanding of IRC in Switzerland, taking into account a maximum of information in order to minimize the prediction uncertainty. The predictive maps will be used as a decision-support tool for 222Rn risk management. The construction of these models is based on different data-driven statistical methods, in combination with geographical information systems (GIS). In a first phase we performed univariate analysis of IRC for different variables, namely the detector type, building category, foundation, year of construction, the average outdoor temperature during measurement, altitude and lithology. All variables showed significant associations to IRC. Buildings constructed after 1900 showed significantly lower IRC compared to earlier constructions. We observed a further drop of IRC after 1970. In addition to that, we found an association of IRC with altitude. With regard to lithology, we observed the lowest IRC in sedimentary rocks (excluding carbonates) and sediments and the highest IRC in the Jura carbonates and igneous rock. The IRC data was systematically analyzed for potential bias due to spatially unbalanced sampling of measurements. In order to facilitate the modeling and the interpretation of the influence of geology on IRC, we developed an algorithm based on k-medoids clustering which permits to define coherent geological classes in terms of IRC. We performed a soil gas 222Rn concentration (SRC) measurement campaign in order to determine the predictive power of SRC with respect to IRC. We found that the use of SRC is limited for IRC prediction. The second part of the project was dedicated to predictive mapping of IRC using models which take into account the multidimensionality of the process of 222Rn entry into buildings. We used kernel regression and ensemble regression tree for this purpose. We could explain up to 33% of the variance of the log transformed IRC all over Switzerland. This is a good performance compared to former attempts of IRC modeling in Switzerland. As predictor variables we considered geographical coordinates, altitude, outdoor temperature, building type, foundation, year of construction and detector type. Ensemble regression trees like random forests allow to determine the role of each IRC predictor in a multidimensional setting. We found spatial information like geology, altitude and coordinates to have stronger influences on IRC than building related variables like foundation type, building type and year of construction. Based on kernel estimation we developed an approach to determine the local probability of IRC to exceed 300 Bq/m3. In addition to that we developed a confidence index in order to provide an estimate of uncertainty of the map. All methods allow an easy creation of tailor-made maps for different building characteristics. Our work is an essential step towards a 222Rn risk assessment which accounts at the same time for different architectural situations as well as geological and geographical conditions. For the communication of 222Rn hazard to the population we recommend to make use of the probability map based on kernel estimation. The communication of 222Rn hazard could for example be implemented via a web interface where the users specify the characteristics and coordinates of their home in order to obtain the probability to be above a given IRC with a corresponding index of confidence. Taking into account the health effects of 222Rn, our results have the potential to substantially improve the estimation of the effective dose from 222Rn delivered to the Swiss population.

Biomarkers of Host Response Predict Primary End-Point Radiological Pneumonia in Tanzanian Children with Clinical Pneumonia: A Prospective Cohort Study.

BACKGROUND: Diagnosing pediatric pneumonia is challenging in low-resource settings. The World Health Organization (WHO) has defined primary end-point radiological pneumonia for use in epidemiological and vaccine studies. However, radiography requires expertise and is often inaccessible. We hypothesized that plasma biomarkers of inflammation and endothelial activation may be useful surrogates for end-point pneumonia, and may provide insight into its biological significance. METHODS: We studied children with WHO-defined clinical pneumonia (n = 155) within a prospective cohort of 1,005 consecutive febrile children presenting to Tanzanian outpatient clinics. Based on x-ray findings, participants were categorized as primary end-point pneumonia (n = 30), other infiltrates (n = 31), or normal chest x-ray (n = 94). Plasma levels of 7 host response biomarkers at presentation were measured by ELISA. Associations between biomarker levels and radiological findings were assessed by Kruskal-Wallis test and multivariable logistic regression. Biomarker ability to predict radiological findings was evaluated using receiver operating characteristic curve analysis and Classification and Regression Tree analysis. RESULTS: Compared to children with normal x-ray, children with end-point pneumonia had significantly higher C-reactive protein, procalcitonin and Chitinase 3-like-1, while those with other infiltrates had elevated procalcitonin and von Willebrand Factor and decreased soluble Tie-2 and endoglin. Clinical variables were not predictive of radiological findings. Classification and Regression Tree analysis generated multi-marker models with improved performance over single markers for discriminating between groups. A model based on C-reactive protein and Chitinase 3-like-1 discriminated between end-point pneumonia and non-end-point pneumonia with 93.3% sensitivity (95% confidence interval 76.5-98.8), 80.8% specificity (72.6-87.1), positive likelihood ratio 4.9 (3.4-7.1), negative likelihood ratio 0.083 (0.022-0.32), and misclassification rate 0.20 (standard error 0.038). CONCLUSIONS: In Tanzanian children with WHO-defined clinical pneumonia, combinations of host biomarkers distinguished between end-point pneumonia, other infiltrates, and normal chest x-ray, whereas clinical variables did not. These findings generate pathophysiological hypotheses and may have potential research and clinical utility.