Survival Analysis with Large Dimensional Covariates: An Application in Microarray Studies

Use of microarray technology often leads to high-dimensional and low- sample size data settings. Over the past several years, a variety of novel approaches have been proposed for variable selection in this context. However, only a small number of these have been adapted for time-to-event data where censoring is present. Among standard variable selection methods shown both to have good predictive accuracy and to be computationally efficient is the elastic net penalization approach. In this paper, adaptation of the elastic net approach is presented for variable selection both under the Cox proportional hazards model and under an accelerated failure time (AFT) model. Assessment of the two methods is conducted through simulation studies and through analysis of microarray data obtained from a set of patients with diffuse large B-cell lymphoma where time to survival is of interest. The approaches are shown to match or exceed the predictive performance of a Cox-based and an AFT-based variable selection method. The methods are moreover shown to be much more computationally efficient than their respective Cox- and AFT- based counterparts.

Practical Large-Scale Spatio-Temporal Modeling of Particulate Matter Concentrations

The last two decades have seen intense scientific and regulatory interest in the health effects of particulate matter (PM). Influential epidemiological studies that characterize chronic exposure of individuals rely on monitoring data that are sparse in space and time, so they often assign the same exposure to participants in large geographic areas and across time. We estimate monthly PM during 1988-2002 in a large spatial domain for use in studying health effects in the Nurses' Health Study. We develop a conceptually simple spatio-temporal model that uses a rich set of covariates. The model is used to estimate concentrations of PM10 for the full time period and PM2.5 for a subset of the period. For the earlier part of the period, 1988-1998, few PM2.5 monitors were operating, so we develop a simple extension to the model that represents PM2.5 conditionally on PM10 model predictions. In the epidemiological analysis, model predictions of PM10 are more strongly associated with health effects than when using simpler approaches to estimate exposure. Our modeling approach supports the application in estimating both fine-scale and large-scale spatial heterogeneity and capturing space-time interaction through the use of monthly-varying spatial surfaces. At the same time, the model is computationally feasible, implementable with standard software, and readily understandable to the scientific audience. Despite simplifying assumptions, the model has good predictive performance and uncertainty characterization.

Population pharmacokinetics of sevoflurane in conjunction with the AnaConDa: toward target-controlled infusion of volatiles into the breathing system

BACKGROUND: The Anesthetic Conserving Device (AnaConDa) uncouples delivery of a volatile anesthetic (VA) from fresh gas flow (FGF) using a continuous infusion of liquid volatile into a modified heat-moisture exchanger capable of adsorbing VA during expiration and releasing adsorbed VA during inspiration. It combines the simplicity and responsiveness of high FGF with low agent expenditures. We performed in vitro characterization of the device before developing a population pharmacokinetic model for sevoflurane administration with the AnaConDa, and retrospectively testing its performance (internal validation). MATERIALS AND METHODS: Eighteen females and 20 males, aged 31-87, BMI 20-38, were included. The end-tidal concentrations were varied and recorded together with the VA infusion rates into the device, ventilation and demographic data. The concentration-time course of sevoflurane was described using linear differential equations, and the most suitable structural model and typical parameter values were identified. The individual pharmacokinetic parameters were obtained and tested for covariate relationships. Prediction errors were calculated. RESULTS: In vitro studies assessed the contribution of the device to the pharmacokinetic model. In vivo, the sevoflurane concentration-time courses on the patient side of the AnaConDa were adequately described with a two-compartment model. The population median absolute prediction error was 27% (interquartile range 13-45%). CONCLUSION: The predictive performance of the two-compartment model was similar to that of models accepted for TCI administration of intravenous anesthetics, supporting open-loop administration of sevoflurane with the AnaConDa. Further studies will focus on prospective testing and external validation of the model implemented in a target-controlled infusion device.

On the modeling of drug induced respiratory depression in the non-steady-state

The ability of anesthetic agents to provide adequate analgesia and sedation is limited by the ventilatory depression associated with overdosing in spontaneously breathing patients. Therefore, quantitation of drug induced ventilatory depression is a pharmacokinetic-pharmacodynamic problem relevant to the practice of anesthesia. Although several studies describe the effect of respiratory depressant drugs on isolated endpoints, an integrated description of drug induced respiratory depression with parameters identifiable from clinically available data is not available. This study proposes a physiological model of CO2 disposition, ventilatory regulation, and the effects of anesthetic agents on the control of breathing. The predictive performance of the model is evaluated through simulations aimed at reproducing experimental observations of drug induced hypercarbia and hypoventilation associated with intravenous administration of a fast-onset, highly potent anesthetic mu agonist (including previously unpublished experimental data determined after administration of 1 mg alfentanil bolus). The proposed model structure has substantial descriptive capability and can provide clinically relevant predictions of respiratory inhibition in the non-steady-state to enhance safety of drug delivery in the anesthetic practice.

A simple asthma prediction tool for preschool children with wheeze or cough

BACKGROUND Many preschool children have wheeze or cough, but only some have asthma later. Existing prediction tools are difficult to apply in clinical practice or exhibit methodological weaknesses. OBJECTIVE We sought to develop a simple and robust tool for predicting asthma at school age in preschool children with wheeze or cough. METHODS From a population-based cohort in Leicestershire, United Kingdom, we included 1- to 3-year-old subjects seeing a doctor for wheeze or cough and assessed the prevalence of asthma 5 years later. We considered only noninvasive predictors that are easy to assess in primary care: demographic and perinatal data, eczema, upper and lower respiratory tract symptoms, and family history of atopy. We developed a model using logistic regression, avoided overfitting with the least absolute shrinkage and selection operator penalty, and then simplified it to a practical tool. We performed internal validation and assessed its predictive performance using the scaled Brier score and the area under the receiver operating characteristic curve. RESULTS Of 1226 symptomatic children with follow-up information, 345 (28%) had asthma 5 years later. The tool consists of 10 predictors yielding a total score between 0 and 15: sex, age, wheeze without colds, wheeze frequency, activity disturbance, shortness of breath, exercise-related and aeroallergen-related wheeze/cough, eczema, and parental history of asthma/bronchitis. The scaled Brier scores for the internally validated model and tool were 0.20 and 0.16, and the areas under the receiver operating characteristic curves were 0.76 and 0.74, respectively. CONCLUSION This tool represents a simple, low-cost, and noninvasive method to predict the risk of later asthma in symptomatic preschool children, which is ready to be tested in other populations.

A comparison of Markov and generalized linear models of hospital mortality

This paper reports a comparison of three modeling strategies for the analysis of hospital mortality in a sample of general medicine inpatients in a Department of Veterans Affairs medical center. Logistic regression, a Markov chain model, and longitudinal logistic regression were evaluated on predictive performance as measured by the c-index and on accuracy of expected numbers of deaths compared to observed. The logistic regression used patient information collected at admission; the Markov model was comprised of two absorbing states for discharge and death and three transient states reflecting increasing severity of illness as measured by laboratory data collected during the hospital stay; longitudinal regression employed Generalized Estimating Equations (GEE) to model covariance structure for the repeated binary outcome. Results showed that the logistic regression predicted hospital mortality as well as the alternative methods but was limited in scope of application. The Markov chain provides insights into how day to day changes of illness severity lead to discharge or death. The longitudinal logistic regression showed that increasing illness trajectory is associated with hospital mortality. The conclusion is reached that for standard applications in modeling hospital mortality, logistic regression is adequate, but for new challenges facing health services research today, alternative methods are equally predictive, practical, and can provide new insights. ^

Predicting smoking cessation and its relapse in HIV-infected patients: the Swiss HIV Cohort Study

OBJECTIVES: The aim of the study was to assess whether prospective follow-up data within the Swiss HIV Cohort Study can be used to predict patients who stop smoking; or among smokers who stop, those who start smoking again. METHODS: We built prediction models first using clinical reasoning ('clinical models') and then by selecting from numerous candidate predictors using advanced statistical methods ('statistical models'). Our clinical models were based on literature that suggests that motivation drives smoking cessation, while dependence drives relapse in those attempting to stop. Our statistical models were based on automatic variable selection using additive logistic regression with component-wise gradient boosting. RESULTS: Of 4833 smokers, 26% stopped smoking, at least temporarily; because among those who stopped, 48% started smoking again. The predictive performance of our clinical and statistical models was modest. A basic clinical model for cessation, with patients classified into three motivational groups, was nearly as discriminatory as a constrained statistical model with just the most important predictors (the ratio of nonsmoking visits to total visits, alcohol or drug dependence, psychiatric comorbidities, recent hospitalization and age). A basic clinical model for relapse, based on the maximum number of cigarettes per day prior to stopping, was not as discriminatory as a constrained statistical model with just the ratio of nonsmoking visits to total visits. CONCLUSIONS: Predicting smoking cessation and relapse is difficult, so that simple models are nearly as discriminatory as complex ones. Patients with a history of attempting to stop and those known to have stopped recently are the best candidates for an intervention.

Role of Urbanization, Land-Use Diversity, and Livestock Intensification in Zoonotic Emerging Infectious Diseases

Emerging infectious diseases (EIDs) continue to significantly threaten human and animal health. While there has been some progress in identifying underlying proximal driving forces and causal mechanisms of disease emergence, the role of distal factors is most poorly understood. This article focuses on analyzing the statistical association between highly pathogenic avian influenza (HPAI) H5N1 and urbanization, land-use diversity and poultry intensification. A special form of the urban transition—peri-urbanization—was hypothesized as being associated with ‘hot-spots’ of disease emergence. Novel metrics were used to characterize these distal risk factors. Our models, which combined these newly proposed risk factors with previously known natural and human risk factors, had a far higher predictive performance compared to published models for the first two epidemiological waves in Viet Nam. We found that when relevant risk factors are taken into account, urbanization is generally not a significant independent risk factor. However, urbanization spatially combines other risk factors leading to peri-urban places being the most likely ‘hot-spots’. The work highlights that peri-urban areas have highest levels of chicken density, duck and geese flock size diversity, fraction of land under rice, fraction of land under aquaculture compared to rural and urban areas. Land-use diversity, which has previously never been studied in the context of HPAI H5N1, was found to be a significant risk factor. Places where intensive and extensive forms of poultry production are collocated were found to be at greater risk.

Selection bias and the cross-validation of regression models for prediction

Strategies are compared for the development of a linear regression model with stochastic (multivariate normal) regressor variables and the subsequent assessment of its predictive ability. Bias and mean squared error of four estimators of predictive performance are evaluated in simulated samples of 32 population correlation matrices. Models including all of the available predictors are compared with those obtained using selected subsets. The subset selection procedures investigated include two stopping rules, C$\sb{\rm p}$ and S$\sb{\rm p}$, each combined with an 'all possible subsets' or 'forward selection' of variables. The estimators of performance utilized include parametric (MSEP$\sb{\rm m}$) and non-parametric (PRESS) assessments in the entire sample, and two data splitting estimates restricted to a random or balanced (Snee's DUPLEX) 'validation' half sample. The simulations were performed as a designed experiment, with population correlation matrices representing a broad range of data structures.^ The techniques examined for subset selection do not generally result in improved predictions relative to the full model. Approaches using 'forward selection' result in slightly smaller prediction errors and less biased estimators of predictive accuracy than 'all possible subsets' approaches but no differences are detected between the performances of C$\sb{\rm p}$ and S$\sb{\rm p}$. In every case, prediction errors of models obtained by subset selection in either of the half splits exceed those obtained using all predictors and the entire sample.^ Only the random split estimator is conditionally (on $\\beta$) unbiased, however MSEP$\sb{\rm m}$ is unbiased on average and PRESS is nearly so in unselected (fixed form) models. When subset selection techniques are used, MSEP$\sb{\rm m}$ and PRESS always underestimate prediction errors, by as much as 27 percent (on average) in small samples. Despite their bias, the mean squared errors (MSE) of these estimators are at least 30 percent less than that of the unbiased random split estimator. The DUPLEX split estimator suffers from large MSE as well as bias, and seems of little value within the context of stochastic regressor variables.^ To maximize predictive accuracy while retaining a reliable estimate of that accuracy, it is recommended that the entire sample be used for model development, and a leave-one-out statistic (e.g. PRESS) be used for assessment. ^

Bases metodológicas para un sistema de apoyo a la selección de especies en la restauración de la vegetación

RESUMEN El apoyo a la selección de especies a la restauración de la vegetación en España en los últimos 40 años se ha basado fundamentalmente en modelos de distribución de especies, también llamados modelos de nicho ecológico, que estiman la probabilidad de presencia de las especies en función de las condiciones del medio físico (clima, suelo, etc.). Con esta tesis se ha intentado contribuir a la mejora de la capacidad predictiva de los modelos introduciendo algunas propuestas metodológicas adaptadas a los datos disponibles actualmente en España y enfocadas al uso de los modelos en la selección de especies. No siempre se dispone de datos a una resolución espacial adecuada para la escala de los proyectos de restauración de la vegetación. Sin embrago es habitual contar con datos de baja resolución espacial para casi todas las especies vegetales presentes en España. Se propone un método de recalibración que actualiza un modelo de regresión logística de baja resolución espacial con una nueva muestra de alta resolución espacial. El método permite obtener predicciones de calidad aceptable con muestras relativamente pequeñas (25 presencias de la especie) frente a las muestras mucho mayores (más de 100 presencias) que requería una estrategia de modelización convencional que no usara el modelo previo. La selección del método estadístico puede influir decisivamente en la capacidad predictiva de los modelos y por esa razón la comparación de métodos ha recibido mucha atención en la última década. Los estudios previos consideraban a la regresión logística como un método inferior a técnicas más modernas como las de máxima entropía. Los resultados de la tesis demuestran que esa diferencia observada se debe a que los modelos de máxima entropía incluyen técnicas de regularización y la versión de la regresión logística usada en las comparaciones no. Una vez incorporada la regularización a la regresión logística usando penalización, las diferencias en cuanto a capacidad predictiva desaparecen. La regresión logística penalizada es, por tanto, una alternativa más para el ajuste de modelos de distribución de especies y está a la altura de los métodos modernos con mejor capacidad predictiva como los de máxima entropía. A menudo, los modelos de distribución de especies no incluyen variables relativas al suelo debido a que no es habitual que se disponga de mediciones directas de sus propiedades físicas o químicas. La incorporación de datos de baja resolución espacial proveniente de mapas de suelo nacionales o continentales podría ser una alternativa. Los resultados de esta tesis sugieren que los modelos de distribución de especies de alta resolución espacial mejoran de forma ligera pero estadísticamente significativa su capacidad predictiva cuando se incorporan variables relativas al suelo procedente de mapas de baja resolución espacial. La validación es una de las etapas fundamentales del desarrollo de cualquier modelo empírico como los modelos de distribución de especies. Lo habitual es validar los modelos evaluando su capacidad predictiva especie a especie, es decir, comparando en un conjunto de localidades la presencia o ausencia observada de la especie con las predicciones del modelo. Este tipo de evaluación no responde a una cuestión clave en la restauración de la vegetación ¿cuales son las n especies más idóneas para el lugar a restaurar? Se ha propuesto un método de evaluación de modelos adaptado a esta cuestión que consiste en estimar la capacidad de un conjunto de modelos para discriminar entre las especies presentes y ausentes de un lugar concreto. El método se ha aplicado con éxito a la validación de 188 modelos de distribución de especies leñosas orientados a la selección de especies para la restauración de la vegetación en España. Las mejoras metodológicas propuestas permiten mejorar la capacidad predictiva de los modelos de distribución de especies aplicados a la selección de especies en la restauración de la vegetación y también permiten ampliar el número de especies para las que se puede contar con un modelo que apoye la toma de decisiones. SUMMARY During the last 40 years, decision support tools for plant species selection in ecological restoration in Spain have been based on species distribution models (also called ecological niche models), that estimate the probability of occurrence of the species as a function of environmental predictors (e.g., climate, soil). In this Thesis some methodological improvements are proposed to contribute to a better predictive performance of such models, given the current data available in Spain and focusing in the application of the models to selection of species for ecological restoration. Fine grained species distribution data are required to train models to be used at the scale of the ecological restoration projects, but this kind of data are not always available for every species. On the other hand, coarse grained data are available for almost every species in Spain. A recalibration method is proposed that updates a coarse grained logistic regression model using a new fine grained updating sample. The method allows obtaining acceptable predictive performance with reasonably small updating sample (25 occurrences of the species), in contrast with the much larger samples (more than 100 occurrences) required for a conventional modeling approach that discards the coarse grained data. The choice of the statistical method may have a dramatic effect on model performance, therefore comparisons of methods have received much interest in the last decade. Previous studies have shown a poorer performance of the logistic regression compared to novel methods like maximum entropy models. The results of this Thesis show that the observed difference is caused by the fact that maximum entropy models include regularization techniques and the versions of logistic regression compared do not. Once regularization has been added to the logistic regression using a penalization procedure, the differences in model performance disappear. Therefore, penalized logistic regression may be considered one of the best performing methods to model species distributions. Usually, species distribution models do not consider soil related predictors because direct measurements of the chemical or physical properties are often lacking. The inclusion of coarse grained soil data from national or continental soil maps could be a reasonable alternative. The results of this Thesis suggest that the performance of the models slightly increase after including soil predictors form coarse grained soil maps. Model validation is a key stage of the development of empirical models, such as species distribution models. The usual way of validating is based on the evaluation of model performance for each species separately, i.e., comparing observed species presences or absence to predicted probabilities in a set of sites. This kind of evaluation is not informative for a common question in ecological restoration projects: which n species are the most suitable for the environment of the site to be restored? A method has been proposed to address this question that estimates the ability of a set of models to discriminate among present and absent species in a evaluation site. The method has been successfully applied to the validation of 188 species distribution models used to support decisions on species selection for ecological restoration in Spain. The proposed methodological approaches improve the predictive performance of the predictive models applied to species selection in ecological restoration and increase the number of species for which a model that supports decisions can be fitted.

Artificial metaplasticity prediction model for cognitive rehabilitation outcome in acquired brain injury patients

Objective The main purpose of this research is the novel use of artificial metaplasticity on multilayer perceptron (AMMLP) as a data mining tool for prediction the outcome of patients with acquired brain injury (ABI) after cognitive rehabilitation. The final goal aims at increasing knowledge in the field of rehabilitation theory based on cognitive affectation. Methods and materials The data set used in this study contains records belonging to 123 ABI patients with moderate to severe cognitive affectation (according to Glasgow Coma Scale) that underwent rehabilitation at Institut Guttmann Neurorehabilitation Hospital (IG) using the tele-rehabilitation platform PREVIRNEC©. The variables included in the analysis comprise the neuropsychological initial evaluation of the patient (cognitive affectation profile), the results of the rehabilitation tasks performed by the patient in PREVIRNEC© and the outcome of the patient after a 3–5 months treatment. To achieve the treatment outcome prediction, we apply and compare three different data mining techniques: the AMMLP model, a backpropagation neural network (BPNN) and a C4.5 decision tree. Results The prediction performance of the models was measured by ten-fold cross validation and several architectures were tested. The results obtained by the AMMLP model are clearly superior, with an average predictive performance of 91.56%. BPNN and C4.5 models have a prediction average accuracy of 80.18% and 89.91% respectively. The best single AMMLP model provided a specificity of 92.38%, a sensitivity of 91.76% and a prediction accuracy of 92.07%. Conclusions The proposed prediction model presented in this study allows to increase the knowledge about the contributing factors of an ABI patient recovery and to estimate treatment efficacy in individual patients. The ability to predict treatment outcomes may provide new insights toward improving effectiveness and creating personalized therapeutic interventions based on clinical evidence.

Multiple proportion case-basing driven CBRE and its application in the evaluation of possible failure of firms

Case-based reasoning (CBR) is a unique tool for the evaluation of possible failure of firms (EOPFOF) for its eases of interpretation and implementation. Ensemble computing, a variation of group decision in society, provides a potential means of improving predictive performance of CBR-based EOPFOF. This research aims to integrate bagging and proportion case-basing with CBR to generate a method of proportion bagging CBR for EOPFOF. Diverse multiple case bases are first produced by multiple case-basing, in which a volume parameter is introduced to control the size of each case base. Then, the classic case retrieval algorithm is implemented to generate diverse member CBR predictors. Majority voting, the most frequently used mechanism in ensemble computing, is finally used to aggregate outputs of member CBR predictors in order to produce final prediction of the CBR ensemble. In an empirical experiment, we statistically validated the results of the CBR ensemble from multiple case bases by comparing them with those of multivariate discriminant analysis, logistic regression, classic CBR, the best member CBR predictor and bagging CBR ensemble. The results from Chinese EOPFOF prior to 3 years indicate that the new CBR ensemble, which significantly improved CBRs predictive ability, outperformed all the comparative methods.

Predicting EQ-5D from the Parkinson's disease questionnaire PDQ-8 using multi-dimensional Bayesian network classifiers

The impact of the Parkinson's disease and its treatment on the patients' health-related quality of life can be estimated either by means of generic measures such as the european quality of Life-5 Dimensions (EQ-5D) or specific measures such as the 8-item Parkinson's disease questionnaire (PDQ-8). In clinical studies, PDQ-8 could be used in detriment of EQ-5D due to the lack of resources, time or clinical interest in generic measures. Nevertheless, PDQ-8 cannot be applied in cost-effectiveness analyses which require generic measures and quantitative utility scores, such as EQ-5D. To deal with this problem, a commonly used solution is the prediction of EQ-5D from PDQ-8. In this paper, we propose a new probabilistic method to predict EQ-5D from PDQ-8 using multi-dimensional Bayesian network classifiers. Our approach is evaluated using five-fold cross-validation experiments carried out on a Parkinson's data set containing 488 patients, and is compared with two additional Bayesian network-based approaches, two commonly used mapping methods namely, ordinary least squares and censored least absolute deviations, and a deterministic model. Experimental results are promising in terms of predictive performance as well as the identification of dependence relationships among EQ-5D and PDQ-8 items that the mapping approaches are unable to detect

Efficient Monte Carlo methods for multi-dimensional learning with classifier chains

Multi-dimensional classification (MDC) is the supervised learning problem where an instance is associated with multiple classes, rather than with a single class, as in traditional classification problems. Since these classes are often strongly correlated, modeling the dependencies between them allows MDC methods to improve their performance – at the expense of an increased computational cost. In this paper we focus on the classifier chains (CC) approach for modeling dependencies, one of the most popular and highest-performing methods for multi-label classification (MLC), a particular case of MDC which involves only binary classes (i.e., labels). The original CC algorithm makes a greedy approximation, and is fast but tends to propagate errors along the chain. Here we present novel Monte Carlo schemes, both for finding a good chain sequence and performing efficient inference. Our algorithms remain tractable for high-dimensional data sets and obtain the best predictive performance across several real data sets.

Disentangling the impact of seroconversion age and set-point viral load on ART-free HIV survival

Thesis (Master's)--University of Washington, 2016-06