Fitting of Mixtures with Unspecified Number of Components Using Cross Validation Distance Estimate

Estimation of the number of mixture components (k) is an unsolved problem. Available methods for estimation of k include bootstrapping the likelihood ratio test statistics and optimizing a variety of validity functionals such as AIC, BIC/MDL, and ICOMP. We investigate the minimization of distance between fitted mixture model and the true density as a method for estimating k. The distances considered are Kullback-Leibler (KL) and “L sub 2”. We estimate these distances using cross validation. A reliable estimate of k is obtained by voting of B estimates of k corresponding to B cross validation estimates of distance. This estimation methods with KL distance is very similar to Monte Carlo cross validated likelihood methods discussed by Smyth (2000). With focus on univariate normal mixtures, we present simulation studies that compare the cross validated distance method with AIC, BIC/MDL, and ICOMP. We also apply the cross validation estimate of distance approach along with AIC, BIC/MDL and ICOMP approach, to data from an osteoporosis drug trial in order to find groups that differentially respond to treatment.

Fitting ACE Structural Equation Models to Case-Control Family Data

Investigators interested in whether a disease aggregates in families often collect case-control family data, which consist of disease status and covariate information for families selected via case or control probands. Here, we focus on the use of case-control family data to investigate the relative contributions to the disease of additive genetic effects (A), shared family environment (C), and unique environment (E). To this end, we describe a ACE model for binary family data and then introduce an approach to fitting the model to case-control family data. The structural equation model, which has been described previously, combines a general-family extension of the classic ACE twin model with a (possibly covariate-specific) liability-threshold model for binary outcomes. Our likelihood-based approach to fitting involves conditioning on the proband’s disease status, as well as setting prevalence equal to a pre-specified value that can be estimated from the data themselves if necessary. Simulation experiments suggest that our approach to fitting yields approximately unbiased estimates of the A, C, and E variance components, provided that certain commonly-made assumptions hold. These assumptions include: the usual assumptions for the classic ACE and liability-threshold models; assumptions about shared family environment for relative pairs; and assumptions about the case-control family sampling, including single ascertainment. When our approach is used to fit the ACE model to Austrian case-control family data on depression, the resulting estimate of heritability is very similar to those from previous analyses of twin data.

Multicentre study on peri- and postoperative central venous oxygen saturation in high-risk surgical patients

Introduction Low central venous oxygen saturation (ScvO2) has been associated with increased risk of postoperative complications in high-risk surgery. Whether this association is centre-specific or more generalisable is not known. The aim of this study was to assess the association between peri- and postoperative ScvO2 and outcome in high-risk surgical patients in a multicentre setting. Methods Three large European university hospitals (two in Finland, one in Switzerland) participated. In 60 patients with intra-abdominal surgery lasting more than 90 minutes, the presence of at least two of Shoemaker's criteria, and ASA (American Society of Anesthesiologists) class greater than 2, ScvO2 was determined preoperatively and at two hour intervals during the operation until 12 hours postoperatively. Hospital length of stay (LOS) mortality, and predefined postoperative complications were recorded. Results The age of the patients was 72 ± 10 years (mean ± standard deviation), and simplified acute physiology score (SAPS II) was 32 ± 12. Hospital LOS was 10.5 (8 to 14) days, and 28-day hospital mortality was 10.0%. Preoperative ScvO2 decreased from 77% ± 10% to 70% ± 11% (p < 0.001) immediately after surgery and remained unchanged 12 hours later. A total of 67 postoperative complications were recorded in 32 patients. After multivariate analysis, mean ScvO2 value (odds ratio [OR] 1.23 [95% confidence interval (CI) 1.01 to 1.50], p = 0.037), hospital LOS (OR 0.75 [95% CI 0.59 to 0.94], p = 0.012), and SAPS II (OR 0.90 [95% CI 0.82 to 0.99], p = 0.029) were independently associated with postoperative complications. The optimal value of mean ScvO2 to discriminate between patients who did or did not develop complications was 73% (sensitivity 72%, specificity 61%). Conclusion Low ScvO2 perioperatively is related to increased risk of postoperative complications in high-risk surgery. This warrants trials with goal-directed therapy using ScvO2 as a target in high-risk surgery patients.

Application and comparison of classification algorithms for recognition of Alzheimer's disease in electrical brain activity (EEG)

The early detection of subjects with probable Alzheimer's disease (AD) is crucial for effective appliance of treatment strategies. Here we explored the ability of a multitude of linear and non-linear classification algorithms to discriminate between the electroencephalograms (EEGs) of patients with varying degree of AD and their age-matched control subjects. Absolute and relative spectral power, distribution of spectral power, and measures of spatial synchronization were calculated from recordings of resting eyes-closed continuous EEGs of 45 healthy controls, 116 patients with mild AD and 81 patients with moderate AD, recruited in two different centers (Stockholm, New York). The applied classification algorithms were: principal component linear discriminant analysis (PC LDA), partial least squares LDA (PLS LDA), principal component logistic regression (PC LR), partial least squares logistic regression (PLS LR), bagging, random forest, support vector machines (SVM) and feed-forward neural network. Based on 10-fold cross-validation runs it could be demonstrated that even tough modern computer-intensive classification algorithms such as random forests, SVM and neural networks show a slight superiority, more classical classification algorithms performed nearly equally well. Using random forests classification a considerable sensitivity of up to 85% and a specificity of 78%, respectively for the test of even only mild AD patients has been reached, whereas for the comparison of moderate AD vs. controls, using SVM and neural networks, values of 89% and 88% for sensitivity and specificity were achieved. Such a remarkable performance proves the value of these classification algorithms for clinical diagnostics.

Classification Using Generalized Partial Least Squares

The advances in computational biology have made simultaneous monitoring of thousands of features possible. The high throughput technologies not only bring about a much richer information context in which to study various aspects of gene functions but they also present challenge of analyzing data with large number of covariates and few samples. As an integral part of machine learning, classification of samples into two or more categories is almost always of interest to scientists. In this paper, we address the question of classification in this setting by extending partial least squares (PLS), a popular dimension reduction tool in chemometrics, in the context of generalized linear regression based on a previous approach, Iteratively ReWeighted Partial Least Squares, i.e. IRWPLS (Marx, 1996). We compare our results with two-stage PLS (Nguyen and Rocke, 2002A; Nguyen and Rocke, 2002B) and other classifiers. We show that by phrasing the problem in a generalized linear model setting and by applying bias correction to the likelihood to avoid (quasi)separation, we often get lower classification error rates.

Model Evaluation Based on the Distribution of Estimated Absolute Prediction Error

The construction of a reliable, practically useful prediction rule for future response is heavily dependent on the "adequacy" of the fitted regression model. In this article, we consider the absolute prediction error, the expected value of the absolute difference between the future and predicted responses, as the model evaluation criterion. This prediction error is easier to interpret than the average squared error and is equivalent to the mis-classification error for the binary outcome. We show that the distributions of the apparent error and its cross-validation counterparts are approximately normal even under a misspecified fitted model. When the prediction rule is "unsmooth", the variance of the above normal distribution can be estimated well via a perturbation-resampling method. We also show how to approximate the distribution of the difference of the estimated prediction errors from two competing models. With two real examples, we demonstrate that the resulting interval estimates for prediction errors provide much more information about model adequacy than the point estimates alone.

NONLINEAR TUBE-FITTING FOR THE ANALYSIS OF ANATOMICAL AND FUNCTIONAL STRUCTURES

We are concerned with the estimation of the exterior surface of tube-shaped anatomical structures. This interest is motivated by two distinct scientific goals, one dealing with the distribution of HIV microbicide in the colon and the other with measuring degradation in white-matter tracts in the brain. Our problem is posed as the estimation of the support of a distribution in three dimensions from a sample from that distribution, possibly measured with error. We propose a novel tube-fitting algorithm to construct such estimators. Further, we conduct a simulation study to aid in the choice of a key parameter of the algorithm, and we test our algorithm with validation study tailored to the motivating data sets. Finally, we apply the tube-fitting algorithm to a colon image produced by single photon emission computed tomography (SPECT)and to a white-matter tract image produced using diffusion tensor `imaging (DTI).

A systematic review of the survival and complication rates of resin-bonded bridges after an observation period of at least 5 years

OBJECTIVES: The objectives of this systematic review were to assess the 5-year survival of resin-bonded bridges (RBBs) and to describe the incidence of technical and biological complications. METHODS: An electronic Medline search complemented by manual searching was conducted to identify prospective and retrospective cohort studies on RBBs with a mean follow-up time of at least 5 years. Patients had to have been examined clinically at the follow-up visit. Assessment of the identified studies and data extraction were performed independently by two reviewers. Failure and complication rates were analyzed using random-effects Poissons regression models to obtain summary estimates of 5-year proportions. RESULTS: The search provided 6110 titles and 214 abstracts. Full-text analysis was performed for 93 articles, resulting in 17 studies that met the inclusion criteria. Meta-analysis of these studies indicated an estimated survival of RBBs of 87.7% (95% confidence interval (CI): 81.6-91.9%) after 5 years. The most frequent complication was debonding (loss of retention), which occurred in 19.2% (95% CI: 13.8-26.3%) of RBBs over an observation period of 5 years. The annual debonding rate for RBBs placed on posterior teeth (5.03%) tended to be higher than that for anterior-placed RBBs (3.05%). This difference, however, did not reach statistical significance (P=0.157). Biological complications, like caries on abutments and RBBs lost due to periodontitis, occurred in 1.5% of abutments and 2.1% of RBBs, respectively. CONCLUSION: Despite the high survival rate of RBBs, technical complications like debonding are frequent. This in turn means that a substantial amount of extra chair time may be needed following the incorporation of RBBs. There is thus an urgent need for studies with a follow-up time of 10 years or more, to evaluate the long-term outcomes.

Methacholine responsiveness in mice from 2 to 8 wk of age

Many chronic human lung diseases have their origin in early childhood, yet most murine models used to study them utilize adult mice. An important component of the asthma phenotype is exaggerated airway responses, frequently modelled by methacholine (MCh) challenge. The present study was undertaken to characterize MCh responses in mice from 2 to 8 wk of age measuring absolute lung volume and volume-corrected respiratory mechanics as outcome variables. Female BALB/c mice aged 2, 3, 4, 6, and 8 wk were studied during cumulative intravenous MCh challenge. Following each MCh dose, absolute lung volume was measured plethysmographically at functional residual volume and during a slow inflation to 20-hPa transrespiratory pressure. Respiratory system impedance was measured continuously during the inflation maneuver and partitioned into airway and constant-phase parenchymal components by model fitting. Volume-corrected (specific) estimates of respiratory mechanics were calculated. Intravenous MCh challenge induced a predominantly airway response with no evidence of airway closure in any age group. No changes in functional residual volume were seen in mice of any age during the MCh challenge. The specific airway resistance MCh dose response curves did not show significant differences between the age groups. The results from the present study do not show systematic differences in MCh responsiveness in mice from 2 to 8 wk of age.