Measuring asthma patient satisfaction in Sweden using partial least squares

Examines the relationships between different aspects involved in asthma treatment. Analyses each aspect's impact on overall patient satisfaction with asthma treatment. Also studies how outcome variables such as compliance with physician's recommendations, health-related quality of life and resource use are affected by the degree of patient satisfaction. The results refer to asthma patients as a group but not necessarily to each patient as an individual. The statistical technique applied for this analysis is partial least squares. Tests the suggested generic model on 599 respondents from a questionnaire survey. The structure of the suggested model is well supported by the data.     

Analysis of additive risk model with high-dimensional covariates using partial least squares

In this paper, we construct a partial additive regression (PAR) model to predict the survival times of cancer patients based on microarray gene expression data with right censoring. The area under time-dependent receiver operating characteristic curve is used as a model evaluation criterion. We conduct a simulation study to compare the proposed method with other methods, i.e. partial Cox regression and supervised principal component analysis. Two data sets of breast cancer and diffuse large B-cell lymphoma are analyzed to illustrate our procedure. The outcome indicates great predictive performance on both dimension reduction and predictive performance of the proposed PAR model.     

Improving uncertainty analysis in kinetic evaluations using iteratively reweighted least squares

Kinetic parameters of environmental fate processes are usually inferred by fitting appropriate kinetic models to the data using standard nonlinear least squares (NLS) approaches. Although NLS is appropriate to estimate the optimum parameter values, it implies restrictive assumptions on data variances when the confidence limits of the parameters must also be determined. Particularly in the case of degradation and metabolite formation, the assumption of equal error variance is often not realistic because the parent data usually show higher variances than those of the metabolites. Conventionally, such problems would be tackled by weighted NLS regression, which requires prior knowledge about the data errors. Instead of implicitly assuming equal error variances or giving arbitrary weights decided by the researcher, we use an iteratively reweighted least squares (IRLS) algorithm to obtain the maximum likelihood estimates of the model parameters and the error variances specific for the different species in a model. A study with simulated data shows that IRLS gives reliable results in the case of both unequal and equal error variances. We also compared results obtained by NLS and IRLS, with probability distributions of the parameters inferred with a Markov-Chain Monte-Carlo (MCMC) approach for data from aerobic transformation of different chemicals in soil. Confidence intervals obtained by IRLS and MCMC are consistent, whereas NLS leads to very different results when the error variances are distinctly different between different species. Because the MCMC results can be assumed to reflect the real parameter distribution imposed by the observed data, we conclude that IRLS generally yields more realistic estimates of confidence intervals for model parameters than NLS.     

Sparse partial least squares with group and subgroup structure

Integrative analysis of high dimensional omics datasets has been studied by many authors in recent years. By incorporating prior known relationships among the variables, these analyses have been successful in elucidating the relationships between different sets of omics data. In this article, our goal is to identify important relationships between genomic expression and cytokine data from a human immunodeficiency virus vaccine trial. We proposed a flexible partial least squares technique, which incorporates group and subgroup structure in the modelling process. Our new method accounts for both grouping of genetic markers (eg, gene sets) and temporal effects. The method generalises existing sparse modelling techniques in the partial least squares methodology and establishes theoretical connections to variable selection methods for supervised and unsupervised problems. Simulation studies are performed to investigate the performance of our methods over alternative sparse approaches. Our R package sgspls is available at https://github.com/matt‐sutton/sgspls .     

Prognostic factors affecting survival in multiple myeloma

70 patients suffering from multiple myeloma were observed by authors in the last 15 years and three months. In the meantime fifty-two out of them have died, and 18 patients are under permanent care. 43 IgG, 17 IgA, 6 Bence-Jones, 2 IgD types were diagnosed according to the paraprotein distribution, one patient proved to be nonsecretory, and an other one to osteosclerotic form as well. The median survival time was 27 months in the group of deceased patients. In the group followed-up 50.8 months survival time was observed up to the closing of the study. Several prognostic factors were investigated. According to the classification by Durie and Salmon the survival time was 60 months in the patients with stage I, 33 months in stage II., and 9 months in stage III respectively. The prognosis is much poorer in patients into the "B" category: the survival time was 14 months. Classified in the basis of the type of the myeloma-cell, the cases with well matured cells have had the best prognosis with survival time of 46 months, while the most unfavourable prognosis was observed in patients with blast-cell type, with a median survival time of 10 months. The greatest number of patients suffered from multiple myeloma of IgG paraprotein type, in this group the serum IgA level was found to be significantly decreased in the patients died due to inevitable infections. The survival was injured significantly by the occurrence of concomitant severe diseases, to.(ABSTRACT TRUNCATED AT 250 WORDS)     

Application of copulas to improve covariance estimation for partial least squares

Dimension reduction techniques, such as partial least squares, are useful for computing summary measures and examining relationships in complex settings. Partial least squares requires an estimate of the covariance matrix as a first step in the analysis, making this estimate critical to the results. In addition, the covariance matrix also forms the basis for other techniques in multivariate analysis, such as principal component analysis and independent component analysis. This paper has been motivated by an example from an imaging study in Alzheimer's disease where there is complete separation between Alzheimer's and control subjects for one of the imaging modalities. This separation occurs in one block of variables and does not occur with the second block of variables resulting in inaccurate estimates of the covariance. We propose the use of a copula to obtain estimates of the covariance in this setting, where one set of variables comes from a mixture distribution. Simulation studies show that the proposed estimator is an improvement over the standard estimators of covariance. We illustrate the methods from the motivating example from a study in the area of Alzheimer's disease. Copyright © 2012 John Wiley & Sons, Ltd.     

A multiple myeloma long term survival case

Multiple myeloma is a malignant plasma cells proliferation in the bone marrow leading to a monoclonal immunoglobulin hypersecretion. The survival duration of this disease ranges usually from 2 to 3 years. However, as this reported case, a long-term survival remains possible. A 29 year old woman was admitted to the internal medicine department for bone pain, weight loss and pathologic fractures. The clinical examination revealed an anaemia, a spinal compression (D10) and atrophia of quadriceps and gluteus muscle. The radiologic findings observed were multiple fractures. The bone marrow aspiration confirmed the plasmocytosis greater than 50%, with immature plasma cells and other lineages rarefication. The disease belonged to the stage III A of the Salmon and Durie classification. Chemotherapy with melphalan associated to prednisone was started with a two to three months biological and clinical follow-up. This treatment allowed 12 years survival. Because of this variety, the search for new prognostic factors would be relevant.     

Addressing the identification problem in age-period-cohort analysis: a tutorial on the use of partial least squares and principal components analysis

In the analysis of trends in health outcomes, an ongoing issue is how to separate and estimate the effects of age, period, and cohort. As these 3 variables are perfectly collinear by definition, regression coefficients in a general linear model are not unique. In this tutorial, we review why identification is a problem, and how this problem may be tackled using partial least squares and principal components regression analyses. Both methods produce regression coefficients that fulfill the same collinearity constraint as the variables age, period, and cohort. We show that, because the constraint imposed by partial least squares and principal components regression is inherent in the mathematical relation among the 3 variables, this leads to more interpretable results. We use one dataset from a Taiwanese health-screening program to illustrate how to use partial least squares regression to analyze the trends in body heights with 3 continuous variables for age, period, and cohort. We then use another dataset of hepatocellular carcinoma mortality rates for Taiwanese men to illustrate how to use partial least squares regression to analyze tables with aggregated data. We use the second dataset to show the relation between the intrinsic estimator, a recently proposed method for the age-period-cohort analysis, and partial least squares regression. We also show that the inclusion of all indicator variables provides a more consistent approach. R code for our analyses is provided in the eAppendix.     

Patient-reported outcomes as predictors of 10-year survival in women after acute myocardial infarction

Background  

Patient-reported outcomes are increasingly seen as complementary to biomedical measures. However, their prognostic importance has yet to be established, particularly in female long-term myocardial infarction (MI) survivors. We aimed to determine whether 10-year survival in older women after MI relates to patient-reported outcomes, and to compare their survival with that of the general female population.     

Gain in efficiency from using generalized least squares in the Haseman-Elston test

Techniques that test for linkage between a marker and a trait locus based on the regression methods proposed by Haseman and Elston [1972] involve testing a null hypothesis of no linkage by examination of the regression coefficient. Modified Haseman-Elston methods accomplish this using ordinary least squares (OLS), weighted least squares (WLS), in which weights are reciprocals of estimated variances, and generalized estimating equations (GEE). Methods implementing the WLS and GEE currently use a diagonal covariance matrix, thus incorrectly treating the squared trait differences of two sib pairs within a family as uncorrelated. Correctly specifying the correlations between sib pairs in a family yields the best linear unbiased estimator of the regression coefficient [Scheffe, 1959]. This estimator will be referred to as the generalized least squares (GLS) estimator. We determined the null variance of the GLS estimator and the null variance of the WLS/OLS estimator. The correct null variance of the WLS/OLS estimate of the Haseman-Elston (H-E) regression coefficient may be either larger or smaller than the variance of the WLS/OLS estimate calculated assuming that the squared sib-pair differences are uncorrelated. For a fully informative marker locus, the gain in efficiency using GLS rather than WLS/OLS under the null hypothesis is approximately 11% in a large multifamily study with three siblings per family and 25% for families with four siblings each. © 1995 Wiley-Liss, Inc.     

An in-depth discussion and illustration of partial least squares structural equation modeling in health care

Partial least squares structural equation modeling (PLS-SEM) has become more popular across many disciplines including health care. However, articles in health care often fail to discuss the choice of PLS-SEM and robustness testing is not undertaken. This article presents the steps to be followed in a thorough PLS-SEM analysis, and includes a conceptual comparison of PLS-SEM with the more traditional covariance-based structural equation modeling (CB-SEM) to enable health care researchers and policy makers make appropriate choices. PLS-SEM allows for critical exploratory research to lay the groundwork for follow-up studies using methods with stricter assumptions. The PLS-SEM analysis is illustrated in the context of residential aged care networks combining low-level and high-level care. Based on the illustrative setting, low-level care does not make a significant contribution to the overall quality of care in residential aged care networks. The article provides key references from outside the health care literature that are often overlooked by health care articles. Choosing between PLS-SEM and CB-SEM should be based on data characteristics, sample size, the types and numbers of latent constructs modelled, and the nature of the underlying theory (exploratory versus advanced). PLS-SEM can become an indispensable tool for managers, policy makers and regulators in the health care sector.     

Understanding neural networks using regression trees: an application to multiple myeloma survival data

Neural networks are becoming very popular tools for analysing data. It is however quite difficult to understand the neural network output in terms of the original covariates or input variables. In this paper we provide, using readily available software, an easy way of understanding the output of the neural network using regression trees. We focus on the problem in the context of censored survival data for patients with multiple myeloma, where identifying groups of patients with different prognosis is an important aspect of clinical studies. The use of regression trees to help understand neural networks can be easily applied to uncensored situations.     

Patient-reported outcomes as predictors of survival in patients with bowel cancer: a systematic review

Quality of Life Research - The prognostic value of patient-reported outcomes (PROs) has been determined in some cancers, but a focussed review in colorectal cancer (CRC) has not yet been conducted....     

Single index of multimorbidity did not predict multiple outcomes

BACKGROUND AND OBJECTIVES: Measurement of multimorbidity and comorbidity is important in epidemiologic and health services research. The aim of this research was to derive a generic multimorbidity index based on patient self-report, incorporating severity, for predicting a range of outcomes. METHODS: The dataset was obtained from a trial including 1,541 Veterans and war widows aged 70 years and over. The survey included sociodemographics, hospital admissions, SF-36, and information on deaths was obtained. The methods of Charlson were used to derive Multimorbidity Indices. RESULTS: All indices predicted quality of life, with decreasing quality of life for each increase in multimorbidity category. Multimorbidity scores incorporating severity significantly contributed to the prediction of mortality, hospital admission, and follow-up quality of life, regardless of adjustment for baseline quality of life. CONCLUSIONS: Our results indicate that a single index cannot predict a variety of relevant outcomes. Consequently, research undertaken to assess the impact of intervention or illness on health outcomes should use an index that is valid for predicting the specific outcome of interest.     

Neither fixed nor random: weighted least squares meta‐analysis

This study challenges two core conventional meta‐analysis methods: fixed effect and random effects. We show how and explain why an unrestricted weighted least squares estimator is superior to conventional random‐effects meta‐analysis when there is publication (or small‐sample) bias and better than a fixed‐effect weighted average if there is heterogeneity. Statistical theory and simulations of effect sizes, log odds ratios and regression coefficients demonstrate that this unrestricted weighted least squares estimator provides satisfactory estimates and confidence intervals that are comparable to random effects when there is no publication (or small‐sample) bias and identical to fixed‐effect meta‐analysis when there is no heterogeneity. When there is publication selection bias, the unrestricted weighted least squares approach dominates random effects; when there is excess heterogeneity, it is clearly superior to fixed‐effect meta‐analysis. In practical applications, an unrestricted weighted least squares weighted average will often provide superior estimates to both conventional fixed and random effects. Copyright © 2015 John Wiley & Sons, Ltd.     

Mendelian randomization analysis with survival outcomes

Mendelian randomization (MR) is an established approach for assessing the causal effects of heritable exposures on outcomes. Outcomes of interest often include binary clinical endpoints, but may also include censored survival times. We explore the implications of both the Cox proportional hazard model and the additive hazard model in the context of MR, with a specific emphasis on two‐stage methods. We show that naive application of standard MR approaches to censored survival times may induce significant bias. Through simulations and analysis of data from the Women's Health Initiative, we provide practical advice on modeling survival outcomes in MRs.     

Robustness of ordinary least squares in randomized clinical trials

There has been a series of occasional papers in this journal about semiparametric methods for robust covariate control in the analysis of clinical trials. These methods are fairly easy to apply on currently available computers, but standard software packages do not yet support these methods with easy option selections. Moreover, these methods can be difficult to explain to practitioners who have only a basic statistical education. There is also a somewhat neglected history demonstrating that ordinary least squares (OLS) is very robust to the types of outcome distribution features that have motivated the newer methods for robust covariate control. We review these two strands of literature and report on some new simulations that demonstrate the robustness of OLS to more extreme normality violations than previously explored. The new simulations involve two strongly leptokurtic outcomes: near‐zero binary outcomes and zero‐inflated gamma outcomes. Potential examples of such outcomes include, respectively, 5‐year survival rates for stage IV cancer and healthcare claim amounts for rare conditions. We find that traditional OLS methods work very well down to very small sample sizes for such outcomes. Under some circumstances, OLS with robust standard errors work well with even smaller sample sizes. Given this literature review and our new simulations, we think that most researchers may comfortably continue using standard OLS software, preferably with the robust standard errors. Copyright © 2015 John Wiley & Sons, Ltd.     

Pairwise multiple comparison adjustment in survival analysis

Many clinical studies have as their endpoint the time until some event (such as death) occurs. Often in such studies researchers are interested in comparing several treatment or prognostic groups with one another in terms of their survival curves. When many such pairwise group comparisons are done, the chance of finding a false significance among all of the comparisons is inflated above the usual desired significance level. This paper investigates methods of adjusting the survival analysis for the number of comparisons being made. These methods are applied to a retrospective study conducted by the International Bone Marrow Transplant Registry and compared in a simulation study in terms of the power to detect actual differences in the survival curves between the groups.     

多发性骨髓瘤合并HBV感染的临床分析

目的探讨多发性骨髓瘤合并乙型肝炎病毒(HBV)感染的临床特点。方法选择2010年1月-2016年12月医院多发性骨髓瘤患者250例作为多发性骨髓瘤组,体检者250名作为对照组,多发性骨髓瘤患者根据HBsAg是否阳性分为HBsAg阳性患者22例和HBsAg阴性患者228例;测定HBsAg阳性与阴性患者血清肝炎病毒标记物。结果多发性骨髓瘤组HBsAg阳性率为8.8%,高于对照组的2.8%(P<0.05);多发性骨髓瘤患者中,HBsAg阳性患者肝硬化率高于HBsAg阴性患者(P<0.05);HBsAg阳性患者治疗前、治疗中和治疗后肝损伤比例均高于HBsAg阴性患者(P<0.05);HBsAg阳性患者HBV再激活率高于HBsAg阴性患者(P<0.05)。结论多发性骨髓瘤患者HBsAg阳性率高,多发性骨髓瘤合并HBsAg阳性患者肝硬化、治疗前后肝损伤及HBV再激活率均升高。