A Mixed-Effects Regression Model for Longitudinal Multivariate Ordinal Data

Statistical analysis of the longitudinal fundamental movement skills data in the REACT project using the multilevel ordinal logistic model

OBJECTIVES

The REACT project was designed around two main aims: (1) to assess children's growth and motor development after the COVID-19 pandemic and (2) to follow their fundamental movement skills' developmental trajectories over 18 months using a novel technological device (Meu Educativo®) in their physical education classes. In this article, our goal is to describe statistical analysis of the longitudinal ordinal motor development data that was obtained from these children using the multilevel ordinal logistic model.

METHODS

Longitudinal ordinal data are often collected in studies on motor development. For example, children or adolescents might be rated as having poor, good, or excellent performance levels in fundamental movement skills, and such ratings may be obtained yearly over time to assess changes in fundamental movement skills levels of performance. However, such longitudinal ordinal data are often analyzed using either methods for continuous outcomes, or by dichotomizing the ordinal outcome and using methods for binary data. These approaches are not optimal, and so we describe in detail the use of the multilevel ordinal logistic model for analysis of such data from the REACT project. Our intent is to provide an accessible description and application of this model for analysis of ordinal motor development data.

DISCUSSION

Our analyses show both the between-subjects and within-subjects effects of age on motor development outcomes across three timepoints. The between-subjects effect of age indicate that children that are older have higher motor development ratings, relative to thoese that are younger, whereas the within-subject effect of age indicates higher motor development ratings as a child ages. It is the latter effect that is particularly of interest in longitudinal studies of motor development, and an important advantage of using the multilevel ordinal logistic model relative to more traditional methods.

A framework for longitudinal latent factor modelling of treatment response in clinical trials with applications to Psoriatic Arthritis and Rheumatoid Arthritis

OBJECTIVE

Clinical trials involve the collection of a wealth of data, comprising multiple diverse measurements performed at baseline and follow-up visits over the course of a trial. The most common primary analysis is restricted to a single, potentially composite endpoint at one time point. While such an analytical focus promotes simple and replicable conclusions, it does not necessarily fully capture the multi-faceted effects of a drug in a complex disease setting. Therefore, to complement existing approaches, we set out here to design a longitudinal multivariate analytical framework that accepts as input an entire clinical trial database, comprising all measurements, patients, and time points across multiple trials.

METHODS

Our framework composes probabilistic principal component analysis with a longitudinal linear mixed effects model, thereby enabling clinical interpretation of multivariate results, while handling data missing at random, and incorporating covariates and covariance structure in a computationally efficient and principled way.

RESULTS

We illustrate our approach by applying it to four phase III clinical trials of secukinumab in Psoriatic Arthritis (PsA) and Rheumatoid Arthritis (RA). We identify three clinically plausible latent factors that collectively explain 74.5% of empirical variation in the longitudinal patient database. We estimate longitudinal trajectories of these factors, thereby enabling joint characterisation of disease progression and drug effect. We perform benchmarking experiments demonstrating our method's competitive performance at estimating average treatment effects compared to existing statistical and machine learning methods, and showing that our modular approach leads to relatively computationally efficient model fitting.

CONCLUSION

Our multivariate longitudinal framework has the potential to illuminate the properties of existing composite endpoint methods, and to enable the development of novel clinical endpoints that provide enhanced and complementary perspectives on treatment response.

How Interactive Visualizations Compare to Ethical Frameworks as Stand-Alone Ethics Learning Tools for Health Researchers and Professionals

BACKGROUND

Despite the bourgeoning of digital tools for bioethics research, education, and engagement, little research has empirically investigated the impact of interactive visualizations as a way to translate ethical frameworks and guidelines. To date, most frameworks take the format of text-only documents that outline and offer ethical guidance on specific contexts. This study's goal was to determine whether an interactive-visual format supports frameworks in transferring ethical knowledge by improving learning, deliberation, and user experience.

METHODS

An experimental comparative study was conducted with a pre-, mid-, and post-test design using the online survey platform Qualtrics. Participants were university based early-stage health researchers who were randomly assigned to either the control condition (text-only document) or the experimental condition (interactive-visual). The primary outcome variables were learning, (measured using a questionnaire), deliberation (using cases studies) and user experience (measured using the SED/UD Scale). Analysis was conducted using descriptive statistics and mixed-effects linear regression.

RESULTS

Of the 80 participants, 44 (55%) used the text-only document and 36 (45%) used the interactive-visual. Results of the knowledge-test scores showed a statistically significant difference between participants' post-test scores, indicating that the interactive-visual format better supported understanding, acquisition, and application of the framework's knowledge. Findings from the case studies showed both formats supported ethical deliberation. Results further indicated the interactive-visual provided an overall better episodic and remembered user experience compared with the text-only document.

CONCLUSIONS

Our findings show that ethical frameworks formatted with interactive and visual qualities provide a more pleasing user experience and are effective formats for ethics learning and deliberation. These findings have implications for practitioners developing and deploying ethical frameworks and guidelines (e.g., in educational or employee-onboarding settings), in that the knowledge generated can lead to more effective dissemination practices of normative guidelines and health data ethics concepts.

Visual grading experiments and optimization in CBCT dental implantology imaging: preliminary application of integrated visual grading regression

This study uses a general formulation of integrated visual grading regression (IVGR) and applies it to cone beam computed tomography (CBCT) scan data related to anatomical landmarks for dental implantology. The aim was to assess and predict a minimum acceptable dose for diagnostic imaging and reporting. A skull phantom was imaged with a CBCT unit at various diagnostic exposures. Key anatomical landmarks within the images were independently reviewed by three trained observers. Each provided an overall image quality score. Statistical analysis was carried out to examine the acceptability of the images taken, using an IVGR analysis that was formulized as a three-stage protocol including defining an integrated score, development of an ordinal regression, and investigation of the possibility for dose reduction through estimated parameters. For a unit increase in the logarithm of radiation dose, the odds ratio that the integrated score for an image assessed by observers being rated in a higher category was 3.940 (95% confidence interval: 1.016-15.280). When assessed by the observers, the minimum dose required to achieve a 75% probability for an image to be classified as at least acceptable was 1346.91 mGy·cm² dose area product (DAP), a 31% reduction compared to the 1962 mGy·cm² DAP default dosage of the CBCT unit. The kappa values of the intra and inter-observer reliability indicated moderate agreements, while a discrepancy among observers was also identified because each, as expected, perceived visibility differently. The results of this work demonstrate the IVGR's predictive value of dose saving in the effort to reduce dose to patients while maintaining reportable diagnostic image quality.

An in-Vivo Daily Self-Report Approach to the Assessment of Outcomes of Two Psychotherapies for Women With Posttraumatic Stress Disorder

Emotion regulation and interpersonal psychotherapies that do not require trauma memory processing have been shown to be effective in treating posttraumatic stress disorder (PTSD). This study used a novel method to assess in vivo outcomes in a randomized clinical trial with women (N = 147; ages 18-54; 61% of color; 94% low income) with full (79%) or partial (21%) PTSD. Participants were assigned to affect regulation or interpersonal therapy, or wait-list, and completed daily self-reports for 2 to 4 weeks at baseline and up to 30 days at posttest. Mixed model regression analyses tested pre-post change on five factor analytically derived aggregated daily self-report scores. Emotion regulation-focused therapy was associated with reduced PTSD symptoms, dysregulation, and negative affect, and improvement in adaptive self-regulation and positive affect. Interpersonal-focused therapy was associated with reduced PTSD symptoms and dysregulation. Although both therapies were associated with reduced PTSD symptoms, whether this was due to nonspecific factors rather than the treatments per se could not be determined. Daily self-report data warrant further investigation in psychotherapy research with disorders such as PTSD, in order to assess affective and interpersonal dysregulation and adaptive regulation as they occur in daily life.

Analysis of multivariate longitudinal substance use outcomes using multivariate mixed cumulative logit model

Abstract

Background

Longitudinal assessments of usage are often conducted for multiple substances (e.g., cigarettes, alcohol and marijuana) and research interests are often focused on the inter-substance association. We propose a multivariate longitudinal modeling approach for jointly analyzing the ordinal multivariate substance use data.

Methods

We describe how the binary random slope logistic regression model can be extended to the multi-category ordinal outcomes. We also describe how the proportional odds assumption can be relaxed by allowing differential covariate effects on different cumulative logits for multiple outcomes. Data are analyzed from a P01 study that evaluates the usage levels of cigarettes, alcohol and marijuana repeatedly across 8 measurement waves during 7 consecutive years.

Results

1263 subjects participated in the study with informed consent, among whom 56.6% are females. Males and females show significant differences in terms of the time trend for substance use. Specifically, males showed steeper trends on cigarette and marijuana use over time compared to females, while less so for alcohol. For all three substances, age effects appear to be different for different cumulative logits, indicating the violation of proportional odds assumption.

Conclusions

The multivariate mixed cumulative logit model offers the most flexibility and allows one to examine the inter-substance association when proportional odds assumption is violated.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12874-021-01444-1.

Bivariate Model for Dichotomous Responses and Latent Variables Jointly Assessing Attitude and Attitudinal Stability

In any given survey, individuals are likely to differ in attitudes toward the subject matter. They also may differ in terms of the duration and persistence of attitudes, with some persons' beliefs being much more stable than others. For the purpose of jointly assessing attitude and temporal attitudinal stability, we propose a latent bivariate item response model. Attitudinal stability is operationalized as a construct called response consistency, which is indicated by the concordance of observed responses between two-time points. A simulation experiment assesses the parameter recovery of the proposed model. A real data analysis example uses data collected from a study on folklore beliefs about diabetes (563 individuals from multiple rural communities in North Carolina). On two different occasions, the individuals in the sample completed a 31-item common-sense model of diabetes inventory, which measures the congruence of their beliefs with a biomedical model. Results from the simulation study showed that the model parameters and factor correlation in the latent bivariate IRT model overall recovered well. Results from the real data analysis demonstrated the saliency of the construct. A weak association between having beliefs congruent with the biomedical model and response consistency across the two administrations was found.

Variations in Emotional, Sexual, and Physical Intimate Partner Violence Among Women in Uganda: A Multilevel Analysis

Evidence shows that a significant proportion of ever-partnered women suffer some form of intimate partner violence (IPV) perpetuated by male partners. The prevalence of IPV in sub-Saharan African countries is considerably higher than global estimates. Although existing studies show the effect of women's and intimate male partner's characteristics on IPV, knowledge on how these factors increase or reduce women's risk to specific types of IPV is limited. Using the 2016 Ugandan Demographic and Health Survey (UDHS), we examine regional variations in women's and intimate male partner's characteristics and their effect on emotional, sexual, and physical violence perpetuated by men and experienced by women in Uganda. The result shows that women's educational status is a significant predictor of all forms of IPV, whereas other characteristics, such as employment and housing ownership, have differential effects on specific types of IPV. Less educated women were more likely to experience emotional, sexual, and physical violence. Alcohol abuse was a significant determinant of men perpetuating all types of IPV; other male characteristics had differential effects on specific types of IPV. Male partners who abuse alcohol "often" and "sometimes" were more likely to commit acts of emotional, sexual, and physical violence against their female intimate partners. The findings also show that ~5%, ~8%, and ~2% of the variance in emotional, sexual, and physical violence (respectively; in the final models) are attributable to regional differences. The findings suggest the need for interventions aimed at increasing women's access to higher education, working with men and boys to reduce the occurrence of alcohol abuse and address harmful constructions of masculinity, and promoting gender equality among men as well as women.

Modeling local dependence in latent vector autoregressive models

We propose a Bayesian latent vector autoregressive (LVAR) model to analyze multivariate longitudinal data of binary and ordinal variables (items) as a function of a small number of continuous latent variables. We focus on the evolution of the latent variables while taking into account the correlation structure of the responses. Often local independence is assumed in this context. Local independence implies that, given the latent variables, the responses are assumed mutually independent cross-sectionally and longitudinally. However, in practice conditioning on the latent variables may not remove the dependence of the responses. We address local dependence by further conditioning on item-specific random effects. A simulation study shows that wrongly assuming local independence may give biased estimates for the regression coefficients of the LVAR process as well as the item-specific parameters. Novel features of our proposal include (i) correcting biased estimates of the model parameters, especially the regression coefficients of the LVAR process, obtained when local dependence is ignored and (ii) measuring the magnitude of local dependence. We applied our model on data obtained from a registry on the elderly population in Belgium. The purpose was to examine the values of oral health information on top of general health information.

Modeling daily and weekly moderate and vigorous physical activity using zero-inflated mixture Poisson distribution

Recently developed accelerometer devices have been used in large epidemiological studies for continuous and objective monitoring of physical activities. Typically, physical movements are summarized as minutes in light, moderate, and vigorous physical activities in each wearing day. Because of preponderance of zeros, zero-inflated distributions have been used for modeling the daily moderate or higher levels of physical activity. Yet, these models do not fully account for variations in daily physical activity and cannot be extended to model weekly physical activity explicitly, while the weekly physical activity is considered as an indicator for a subject's average level of physical activity. To overcome these limitations, we propose to use a zero-inflated Poisson mixture distribution that can model daily and weekly physical activity in same family of mixture distributions. Under this method, the likelihood of an inactive day and the amount of exercise in an active day are simultaneously modeled by a joint random effects model to incorporate heterogeneity across participants. If needed, the method has the flexibility to include an additional random effect to address extra variations in daily physical activity. Maximum likelihood estimation can be obtained through Gaussian quadrature technique, which is implemented conveniently in an R package GLMMadaptive. Method performances are examined using simulation studies. The method is applied to data from the Hispanic Community Health Study/Study of Latinos to examine the relationship between physical activity and BMI groups and within a participant the difference in physical activity between weekends and weekdays.

A mHealth intervention to preserve and promote ideal cardiovascular health in college students: Design and protocol of a cluster randomized controlled trial

BACKGROUND

Cardiovascular disease (CVD) remains the leading cause of death globally. Seven health factors are associated with ideal cardiovascular health: being a non-smoker; not overweight; physically active; having a healthy diet; and normal blood pressure; fasting plasma glucose and cholesterol. Whereas approximately half of U.S. youth have ideal levels in at least 5 of the 7 components of cardiovascular health, this proportion falls to 16% by adulthood.

OBJECTIVE

We will evaluate whether the NUYou cardiovascular mHealth intervention is more effective than an active comparator to promote cardiovascular health during the transition to young adulthood.

METHODS

302 incoming freshmen at a midwest university will be cluster randomized by dormitory into one of two mHealth intervention groups: 1) Cardiovascular Health (CVH), addressing behaviors related to CVD risk; or 2) Whole Health (WH), addressing behaviors unrelated to CVD. Both groups will receive smartphone applications, co-designed with students to help them manage time, interact with other participants via social media, and report health behaviors weekly. The CVH group will also have self-monitoring features to track their risk behaviors. Cardiovascular health will be assessed at the beginning of freshman year and the end of freshman and sophomore years. Linear mixed models will be used to compare groups on a composite of the seven cardiovascular-related health factors.

SIGNIFICANCE

This is the first entirely technology-mediated multiple health behavior change intervention delivered to college students to promote cardiovascular health. Findings will inform the potential for primordial prevention in young adulthood.

TRIAL REGISTRATION NUMBER

clinicaltrials.gov #NCT02496728.

Multilevel ordinal model for CD4 count trends in seroconversion among South Africa women

BACKGROUND

Ordinal health longitudinal response variables have distributions that make them unsuitable for many popular statistical models that assume normality. We present a multilevel growth model that may be more suitable for medical ordinal longitudinal outcomes than are statistical models that assume normality and continuous measurements.

METHODS

The data is from an ongoing prospective cohort study conducted amongst adult women who are HIV-infected patients in Kwazulu-Natal, South Africa. Participants were enrolled into the acute infection, then into early infection subsequently into established infection and afterward on cART. Generalized linear multilevel models were applied.

RESULTS

Multilevel ordinal non-proportional and proportional-odds growth models were presented and compared. We observed that the effects of covariates can't be assumed identical across the three cumulative logits. Our analyses also revealed that the rate of change of immune recovery of patients increased as the follow-up time increases. Patients with stable sexual partners, middle-aged, cART initiation, and higher educational levels were more likely to have better immunological stages with time. Similarly, patients having high electrolytes component scores, higher red blood cell indices scores, higher physical health scores, higher psychological well-being scores, a higher level of independence scores, and lower viral load more likely to have better immunological stages through the follow-up time.

CONCLUSION

It can be concluded that the multilevel non-proportional-odds method provides a flexible modeling alternative when the proportional-odds assumption of equal effects of the predictor variables at every stage of the response variable is violated. Having higher clinical parameter scores, higher QoL scores, higher educational levels, and stable sexual partners were found to be the significant factors for trends of CD4 count recovery.

Bayesian analysis of Turkish Income and Living Conditions data, using clustered longitudinal ordinal modelling with Bridge distributed random effects

This article is motivated by the panel surveys, called Statistics on Income and Living Conditions (SILC), conducted annually on (randomly selected) country representative households to monitor EU 2020 aims on poverty reduction. We particularly consider the surveys conducted in Turkey within the scope of integration to the EU. Our main interests are on health aspects of economic and living conditions. The outcome is self-reported health that is clustered longitudinal ordinal, since repeated measures of it are nested within individuals and individuals are nested within families. Economic and living conditions have been measured through a number of individual- and family-level explanatory variables. The questions of interest are on the marginal relationships between the outcome and covariates that we address using a polytomous logistic regression with Bridge distributed random effects. This choice of distribution allows us to directly obtain marginal inferences in the presence of random effects. Widely used Normal distribution is also considered as the random effects distribution. Samples from the joint posterior densities of parameters and random effects are drawn using Markov Chain Monte Carlo. Interesting findings from the public health point of view are that differences were found between the subgroups of employment status, income level and panel year in terms of odds of reporting better health.

Using multivariate mixed-effects selection models for analyzing batch-processed proteomics data with non-ignorable missingness

In quantitative proteomics, mass tag labeling techniques have been widely adopted in mass spectrometry experiments. These techniques allow peptides (short amino acid sequences) and proteins from multiple samples of a batch being detected and quantified in a single experiment, and as such greatly improve the efficiency of protein profiling. However, the batch-processing of samples also results in severe batch effects and non-ignorable missing data occurring at the batch level. Motivated by the breast cancer proteomic data from the Clinical Proteomic Tumor Analysis Consortium, in this work, we developed two tailored multivariate MIxed-effects SElection models (mvMISE) to jointly analyze multiple correlated peptides/proteins in labeled proteomics data, considering the batch effects and the non-ignorable missingness. By taking a multivariate approach, we can borrow information across multiple peptides of the same protein or multiple proteins from the same biological pathway, and thus achieve better statistical efficiency and biological interpretation. These two different models account for different correlation structures among a group of peptides or proteins. Specifically, to model multiple peptides from the same protein, we employed a factor-analytic random effects structure to characterize the high and similar correlations among peptides. To model biological dependence among multiple proteins in a functional pathway, we introduced a graphical lasso penalty on the error precision matrix, and implemented an efficient algorithm based on the alternating direction method of multipliers. Simulations demonstrated the advantages of the proposed models. Applying the proposed methods to the motivating data set, we identified phosphoproteins and biological pathways that showed different activity patterns in triple negative breast tumors versus other breast tumors. The proposed methods can also be applied to other high-dimensional multivariate analyses based on clustered data with or without non-ignorable missingness.

Acute effects of ambient PM2.5 on lung function among schoolchildren

Previous studies have found that fine particulate matter (PM_2.5) air pollution is associated with decreased lung function. However, most current research focuses on children with asthma, leading to small sample sizes and limited generalization of results. The current study aimed to measure the short-term and lag effects of PM_2.5 among school-aged children using repeated measurements of lung function.This prospective panel study included 848 schoolchildren in Zhejiang Province, China. Each year from 2014–2017, two lung function tests were conducted from November 15^th to December 31^st. Daily air pollution data were derived from the monitoring stations nearest to the schools. A mixed-effects regression model was used to investigate the relationship between PM_2.5 and lung function. The effect of PM_2.5 on lung function reached its greatest at 1-day moving average PM_2.5 exposure. For every 10 μg/m³ increase in the 1-day moving average PM_2.5 concentration, Forced Vital Capacity (FVC) of children decreased by 33.74 mL (95% CI: 22.52, 44.96), 1-s Forced Expiratory Volume (FEV₁) decreased by 32.56 mL (95% CI: 21.41, 43.70), and Peak Expiratory Flow (PEF) decreased by 67.45 mL/s (95% CI: 45.64, 89.25). Stronger associations were found in children living in homes with smokers. Short-term exposure to PM_2.5 was associated with reductions in schoolchildren’s lung function. This finding indicates that short-term exposure to PM_2.5 is harmful to children’s respiratory health, and appropriate protective measures should be taken to reduce the adverse effects of air pollution on children’s health.

Health-related quality of life of patients treated with chemoradiotherapy plus or minus prophylactic antibiotics to reduce the number of pneumonias for locally advanced head and neck cancer, the PANTAP study

OBJECTIVES

The recent PANTAP trial showed that administration of prophylactic antibiotics in locally advanced head and neck carcinoma (LAHNC) patients treated with chemoradiotherapy reduced fever, hospitalization and costs. The current study describes the effect of prophylactic antibiotics on health-related quality of life (HRQoL), another secondary endpoint of the trial.

MATERIALS AND METHODS

In this multicenter randomized trial, LAHNC patients treated with chemoradiotherapy received prophylactic antibiotics or standard care. HRQoL was assessed at baseline (before chemoradiotherapy), day 28 of chemoradiotherapy (one day before starting prophylactic antibiotics), the final day of radiotherapy, and 3.5 months after the end of chemoradiotherapy, using the European Organisation for Research and Treatment of Cancer (EORTC) QLQ-C30, EORTC H&N35 module, and the Performance Status Scale for Head & Neck cancer patients (PSS-HN).

RESULTS

Ninety-five patients were randomized: 48 patients were allocated to the standard group and 47 patients to the prophylaxis group. Thirty-four patients in the standard group (70.8%) and 28 patients in the prophylaxis group (59.6%) completed the questionnaires at baseline and at follow-up. No significant differences in HRQoL were found at baseline and at day 28. At the end of radiotherapy, the prophylaxis group performed better on almost all functional subscales of the EORTC QLQ-C30 and reported less symptoms. At the end of follow up, almost no differences were seen between the two treatment groups.

CONCLUSION

Prophylactic antibiotics during chemoradiotherapy for LAHNC patients improved HRQoL at the end of the radiotherapy, however no differences were found 3.5 months after the end of chemoradiotherapy.

Acute effects of PM2.5 on lung function parameters in schoolchildren in Nanjing, China: a panel study

The association between exposure to ambient particulate matter (PM) and reduced lung function parameters has been reported in many works. However, few studies have been conducted in developing countries with high levels of air pollution like China, and little attention has been paid to the acute effects of short-term exposure to air pollution on lung function. The study design consisted of a panel comprising 86 children from the same school in Nanjing, China. Four measurements of lung function were performed. A mixed-effects regression model with study participant as a random effect was used to investigate the relationship between PM_2.5 and lung function. An increase in the current day, 1-day and 2-day moving average PM_2.5 concentration was associated with decreases in lung function indicators. The greatest effect of PM_2.5 on lung function was detected at 1-day moving average PM_2.5 exposure. An increase of 10 μg/m³ in the 1-day moving average PM_2.5 concentration was associated with a 23.22 mL decrease (95% CI: 13.19, 33.25) in Forced Vital Capacity (FVC), a 18.93 mL decrease (95% CI: 9.34, 28.52) in 1-s Forced Expiratory Volume (FEV₁), a 29.38 mL/s decrease (95% CI: -0.40, 59.15) in Peak Expiratory Flow (PEF), and a 27.21 mL/s decrease (95% CI: 8.38, 46.04) in forced expiratory flow 25-75% (FEF_25-75%). The effects of PM_2.5 on lung function had significant lag effects. After an air pollution event, the health effects last for several days and we still need to pay attention to health protection.

Item response models for the longitudinal analysis of health-related quality of life in cancer clinical trials

Background

The use of health-related quality of life (HRQoL) as an endpoint in cancer clinical trials is growing rapidly. Hence, research into the statistical approaches used to analyze HRQoL data is of major importance, and could lead to a better understanding of the impact of treatments on the everyday life and care of patients. Amongst the models that are used for the longitudinal analysis of HRQoL, we focused on the mixed models from item response theory, to directly analyze raw data from questionnaires.

Methods

We reviewed the different item response models for ordinal responses, using a recent classification of generalized linear models for categorical data. Based on methodological and practical arguments, we then proposed a conceptual selection of these models for the longitudinal analysis of HRQoL in cancer clinical trials.

Results

To complete comparison studies already present in the literature, we performed a simulation study based on random part of the mixed models, so to compare the linear mixed model classically used to the selected item response models. As expected, the sensitivity of the item response models to detect random effects with lower variance is better than that of the linear mixed model. We then used a cumulative item response model to perform a longitudinal analysis of HRQoL data from a cancer clinical trial.

Conclusions

Adjacent and cumulative item response models seem particularly suitable for HRQoL analysis. In the specific context of cancer clinical trials and the comparison between two groups of HRQoL data over time, the cumulative model seems to be the most suitable, given that it is able to generate a more complete set of results and gives an intuitive illustration of the data.

Electronic supplementary material

The online version of this article (doi:10.1186/s12874-017-0410-9) contains supplementary material, which is available to authorized users.

The role of predictive coding in the pathogenesis of delirium

Delirium and dementia represent an emerging global crisis in healthcare. Attempts have been made to identify the pathognomonic feature that would make delirium stand out from dementia but unfortunately the global neural dysfunction of both disorders has made the establishment of a direct measurement difficult. Modern conceptualisations of delirium have been influenced by the assessment tools used to assess, detect, and analyse its complex and transient nature. Recent publication of the DSM-V criteria for delirium has marginally altered the previous DSM-IV criteria with a focus upon inattention with vague terms such as consciousness downplayed. Such an alteration has been found to be restrictive and thus impact upon delirium case identification. Although these findings are approximating the empirical state of delirium as measured by validated instruments, a more refined neuroscientifically informed phenomenological framework is required in order to enhance the theoretical understanding of delirium assessment and resolve these challenges. One such application is the predictive coding (PC) model, also known as the hierarchical Bayesian inference model, to interpreting delirium pathophysiology. Therefore, the aims of this paper are to 1) propose the hypothesis that delirium pathophysiology can be explained in terms of the PC model, 2) support this hypothesis by applying this model to current methods of assessing delirium phenomenology, particularly attention, and 3) outline a future programme of research to test many of the parameters of this application.

Catechol-O-methyltransferase gene variants may associate with negative symptom response and plasma concentrations of prolactin in schizophrenia after amisulpride treatment

Catechol-O-methyltransferase (COMT) enzyme is involved in the pathogenesis of psychotic symptoms and may be associated with a therapeutic response to antipsychotic drugs. The aim of this study was to examine the relationship between COMT variants, plasma prolactin level, and the therapeutic effectiveness of amisulpride treatment in patients with schizophrenia. A 12-week naturalistic study of amisulpride treatment was carried out in 185 Han Chinese patients with schizophrenia. The patients were screened for 14 single-nucleotide polymorphisms of the COMT gene. The Positive and Negative Syndrome Scale (PANSS) was used to assess the improvement of psychopathological symptoms from the baseline to the end point in each subject. For better presentation of time-course changes in response status, a mixed model for repeated-measures (MMRM) analysis of symptom improvement during the 12-week treatment period was conducted. The change in plasma prolactin level after amisulpride treatment was also examined (n=51). No significant differences in the genotype frequencies of the COMT variants investigated were observed between responders and non-responders. Moreover, an MMRM analysis of psychopathological symptom improvement during the 12-week treatment course showed that it depended significantly on COMT variants (rs4680, rs4633, and rs6267), particularly regarding changes in negative symptoms. The increase in plasma prolactin levels observed was influenced by the COMT rs4680 variant and was positively correlated with a reduction in PANSS negative scores. Our results suggest that variation of the COMT gene is associated with treatment response regarding negative symptoms and prolactin changes after amisulpride treatment in patients with schizophrenia.

Adipose derived mesenchymal stem cell therapy in the treatment of isolated knee chondral lesions: design of a randomised controlled pilot study comparing arthroscopic microfracture versus arthroscopic microfracture combined with postoperative mesenchymal stem cell injections

INTRODUCTION

The management of intra-articular chondral defects in the knee remains a challenge. Inadequate healing in areas of weight bearing leads to impairment in load transmission and these defects predispose to later development of osteoarthritis. Surgical management of full thickness chondral defects include arthroscopic microfracture and when appropriate autologous chondrocyte implantation. This latter method however is technically challenging, and may not offer significant improvement over microfracture. Preclinical and limited clinical trials have indicated the capacity of mesenchymal stem cells to influence chondral repair. The aim of this paper is to describe the methodology of a pilot randomised controlled trial comparing arthroscopic microfracture alone for isolated knee chondral defects versus arthroscopic microfracture combined with postoperative autologous adipose derived mesenchymal stem cell injections.

METHODS AND ANALYSIS

A pilot single-centre randomised controlled trial is proposed. 40 participants aged 18-50 years, with isolated femoral condyle chondral defects and awaiting planned arthroscopic microfracture will be randomly allocated to a control group (receiving no additional treatment) or treatment group (receiving postoperative adipose derived mesenchymal stem cell treatment). Primary outcome measures will include MRI assessment of cartilage volume and defects and the Knee Injury and Osteoarthritis Outcome Score. Secondary outcomes will include further MRI assessment of bone marrow lesions, bone area and T2 cartilage mapping, a 0-10 Numerical Pain Rating Scale, a Global Impression of Change score and a treatment satisfaction scale. Adverse events and cointerventions will be recorded. Initial outcome follow-up for publication of results will be at 12 months. Further annual follow-up to assess long-term differences between the two group will occur.

ETHICS AND DISSEMINATION

This trial has received prospective ethics approval through the Latrobe University Human Research Ethics Committee. Dissemination of outcome data is planned through both national and international conferences and formal publication in a peer-reviewed journal.

TRIAL REGISTRATION NUMBER

Australia and New Zealand Clinical Trials Register (ANZCTR Trial ID: ACTRN12614000812695).

Realizing the potential of mobile mental health: new methods for new data in psychiatry

Smartphones are now ubiquitous and can be harnessed to offer psychiatry a wealth of real-time data regarding patient behavior, self-reported symptoms, and even physiology. The data collected from smartphones meet the three criteria of big data: velocity, volume, and variety. Although these data have tremendous potential, transforming them into clinically valid and useful information requires using new tools and methods as a part of assessment in psychiatry. In this paper, we introduce and explore numerous analytical methods and tools from the computational and statistical sciences that appear readily applicable to psychiatric data collected using smartphones. By matching smartphone data with appropriate statistical methods, psychiatry can better realize the potential of mobile mental health and empower both patients and providers with novel clinical tools.

Hypoxia and Outcome Prediction in Early-Stage Coma (Project HOPE): an observational prospective cohort study

BACKGROUND

The number of resuscitated cardiac arrest patients suffering from anoxic-ischemic encephalopathy is considerable. However, outcome prediction parameters such as somatosensory evoked potentials need revision because they are based on data predating the implementation of mild therapeutical hypothermia and because data from our own laboratory suggest that they may fail to predict prognosis accurately. The present research project "Hypoxia and Outcome Prediction in Early-Stage Coma" is an ongoing observational prospective cohort study that aims to improve outcome prediction in anoxic coma by limiting the effects of falsely pessimistic predictions at the intensive care unit.

METHODS

Our outcome analysis is based on functional and behavioural definitions. This implies the analysis of the positive predictive value of prognostic markers yielding either positive or negative results. We also analyse the effect of covariates adjusted for age and sex such as sociodemographic variables, prognostic variables and treatment factors on functional and behavioural outcomes, with mixed effects regression models (i.e. fixed and random effects). We expect to enrol 172 patients based on the result of previous research. The null hypothesis is that there is a probability of <10 % that a positive outcome will be observed despite the presence of any of the predictors of a poor/negative outcome. We test the null hypothesis against a one-sided alternative using a Simon's two-stage design to determine whether it is warranted to recruit the full number of patients suggested by a power analysis. The second stage has a design with a Type I error rate of 0.05 and 80 % power if the true response rate is 25 %.

DISCUSSION

We aim to make a significant contribution to the revision and improvement of current outcome prediction methods in anoxic-ischemic encephalopathy patients. As a result, neurocritical care specialists worldwide will have considerably more accurate methods for prognosticating the outcome of anoxic-ischemic encephalopathy following cardiac arrest. This will facilitate the provision of treatment tailored to individual patients and the attainment of an optimal quality of life. It will also inform the decision to withdraw treatment with a level of accuracy never seen before in the field.

TRIAL REGISTRATION

ClinicalTrials.gov NCT02231060 (registered 29 August 2014).

Analysis of multivariate mixed longitudinal data: a flexible latent process approach

Multivariate ordinal and quantitative longitudinal data measuring the same latent construct are frequently collected in psychology. We propose an approach to describe change over time of the latent process underlying multiple longitudinal outcomes of different types (binary, ordinal, quantitative). By relying on random-effect models, this approach handles individually varying and outcome-specific measurement times. A linear mixed model describes the latent process trajectory while equations of observation combine outcome-specific threshold models for binary or ordinal outcomes and models based on flexible parameterized non-linear families of transformations for Gaussian and non-Gaussian quantitative outcomes. As models assuming continuous distributions may be also used with discrete outcomes, we propose likelihood and information criteria for discrete data to compare the goodness of fit of models assuming either a continuous or a discrete distribution for discrete data. Two analyses of the repeated measures of the Mini-Mental State Examination, a 20-item psychometric test, illustrate the method. First, we highlight the usefulness of parameterized non-linear transformations by comparing different flexible families of transformation for modelling the test as a sum score. Then, change over time of the latent construct underlying directly the 20 items is described using two-parameter longitudinal item response models that are specific cases of the approach.

A latent factor linear mixed model for high-dimensional longitudinal data analysis

High-dimensional longitudinal data involving latent variables such as depression and anxiety that cannot be quantified directly are often encountered in biomedical and social sciences. Multiple responses are used to characterize these latent quantities, and repeated measures are collected to capture their trends over time. Furthermore, substantive research questions may concern issues such as interrelated trends among latent variables that can only be addressed by modeling them jointly. Although statistical analysis of univariate longitudinal data has been well developed, methods for modeling multivariate high-dimensional longitudinal data are still under development. In this paper, we propose a latent factor linear mixed model (LFLMM) for analyzing this type of data. This model is a combination of the factor analysis and multivariate linear mixed models. Under this modeling framework, we reduced the high-dimensional responses to low-dimensional latent factors by the factor analysis model, and then we used the multivariate linear mixed model to study the longitudinal trends of these latent factors. We developed an expectation-maximization algorithm to estimate the model. We used simulation studies to investigate the computational properties of the expectation-maximization algorithm and compare the LFLMM model with other approaches for high-dimensional longitudinal data analysis. We used a real data example to illustrate the practical usefulness of the model.

Statistical methods for the meta-analysis of diagnostic tests must take into account the use of surrogate standards

BACKGROUND

Evaluating the performance of a new diagnostic test presents a challenge if the conventional "gold" standard is invasive, hazardous, or expensive, especially if that test has been supplanted in usual clinical practice by a "silver" standard test that is more acceptable and perhaps only slightly suboptimal. In such a case, a systematic literature review will typically uncover a mix of study types, some using the gold and some the silver.

OBJECTIVE

We sought to develop and compare statistical methods to account for this kind of heterogeneity in performing a meta-analysis.

STUDY DESIGN AND SETTING

We compared the performance of estimation methods based on generalized mixed models which incorporate heterogeneity, especially choice of reference test, and random between-study variation in sensitivity and specificity with more conventional methods which neglect the differences in reference tests. Computer simulations were conducted to assess bias and root mean square error of point estimates and coverage of interval estimates.

RESULTS

Methods ignoring the difference in reference tests severely underestimated sensitivity and specificity under the assumption of conditional independence. Bias was substantial even for references with small departure from the standard and persisted with increasing sample size. Coverage of interval estimates was far from nominal level.

CONCLUSION

In the presence of varying reference tests, avoidance of bias and invalid confidence intervals for diagnostic performance requires applying a model that accounts for differences in reference test and heterogeneity among studies.

Modeling nicotine dependence: an application of a longitudinal IRT model for the analysis of adolescent nicotine dependence syndrome scale

INTRODUCTION

Measures of nicotine dependence typically use the item average or total score from rating scales, such as the Nicotine Dependence Syndrome Scale (NDSS). Alternatively, item response theory (IRT) methods can provide useful item-specific information. IRT methods developed for longitudinal data can additionally provide information about item-specific changes over time.

METHODS

We describe a longitudinal 2-parameter ordinal IRT model, and compare the results from this model with those from an IRT model for only the baseline item responses, and a conventional longitudinal analysis of the item-average NDSS score. We examined a 10-item, adolescent version of the NDSS at baseline, 6, 15, and 24 months for 1,097 9th or 10th graders.

RESULTS

IRT analysis of the baseline data revealed that the items "willing to go out of the house in a storm to find a cigarette," "choose to spend money on cigarettes than lunch," "function better after morning cigarette," and "worth smoking in cold or rain," were good items at distinguishing individuals' levels of nicotine dependency. While the analysis of the averaged NDSS score indicated linear growth over time, the longitudinal IRT method revealed that only 5 out of the 10 items showed statistical increase over time.

CONCLUSIONS

Infrequently endorsed NDSS items were generally better able to distinguish higher levels of dependency. The endorsement of such items increased over time. Items that changed significantly over time reflected the general drive concept of dependence, as well as the total first overarching dimension of dependence.

Flexible marginalized models for bivariate longitudinal ordinal data

Random effects models are commonly used to analyze longitudinal categorical data. Marginalized random effects models are a class of models that permit direct estimation of marginal mean parameters and characterize serial correlation for longitudinal categorical data via random effects (Heagerty, 1999). Marginally specified logistic-normal models for longitudinal binary data. Biometrics 55, 688-698; Lee and Daniels, 2008. Marginalized models for longitudinal ordinal data with application to quality of life studies. Statistics in Medicine 27, 4359-4380). In this paper, we propose a Kronecker product (KP) covariance structure to capture the correlation between processes at a given time and the correlation within a process over time (serial correlation) for bivariate longitudinal ordinal data. For the latter, we consider a more general class of models than standard (first-order) autoregressive correlation models, by re-parameterizing the correlation matrix using partial autocorrelations (Daniels and Pourahmadi, 2009). Modeling covariance matrices via partial autocorrelations. Journal of Multivariate Analysis 100, 2352-2363). We assess the reasonableness of the KP structure with a score test. A maximum marginal likelihood estimation method is proposed utilizing a quasi-Newton algorithm with quasi-Monte Carlo integration of the random effects. We examine the effects of demographic factors on metabolic syndrome and C-reactive protein using the proposed models.

The analysis of multivariate longitudinal data: a review

Longitudinal experiments often involve multiple outcomes measured repeatedly within a set of study participants. While many questions can be answered by modeling the various outcomes separately, some questions can only be answered in a joint analysis of all of them. In this article, we will present a review of the many approaches proposed in the statistical literature. Four main model families will be presented, discussed and compared. Focus will be on presenting advantages and disadvantages of the different models rather than on the mathematical or computational details.

Misuse of the linear mixed model when evaluating risk factors of cognitive decline

The linear mixed model (LMM), which is routinely used to describe change in outcomes over time and its association with risk factors, assumes that a unit change in any predictor is associated with a constant change in the outcome. When it is used on psychometric tests, this assumption may not hold. Indeed, psychometric tests usually suffer from ceiling and/or floor effects and curvilinearity (i.e., varying sensitivity to change). The authors aimed to determine the consequences of such misspecification when evaluating predictors of cognitive decline. As an alternative to the LMM, they considered 2 mixed models based on latent processes that handle discrete and bounded outcomes. Model differences are illustrated here using data on 4 psychometric tests from the Personnes Agées QUID (PAQUID) Study (1989-2004). The type I error of the Wald test for risk-factor regression parameters was formally assessed in a simulation study. It demonstrated that type I errors in the LMM could be dramatically inflated for some tests, such that spurious associations with risk factors were found. In particular, confusion between effects on mean level and effects on change over time was highlighted. The authors recommend use of the alternative mixed models when studying psychometric tests and more generally quantitative scales (quality of life, activities of daily living).

Advances in analysis of longitudinal data

In this review, we explore recent developments in the area of linear and nonlinear generalized mixed-effects regression models and various alternatives, including generalized estimating equations for analysis of longitudinal data. Methods are described for continuous and normally distributed as well as categorical (binary, ordinal, nominal) and count (Poisson) variables. Extensions of the model to three and four levels of clustering, multivariate outcomes, and incorporation of design weights are also described. Linear and nonlinear models are illustrated using an example involving a study of the relationship between mood and smoking.

A model for incomplete longitudinal multivariate ordinal data

In studies where multiple outcome items are repeatedly measured over time, missing data often occur. A longitudinal item response theory model is proposed for analysis of multivariate ordinal outcomes that are repeatedly measured. Under the MAR assumption, this model accommodates missing data at any level (missing item at any time point and/or missing time point). It allows for multiple random subject effects and the estimation of item discrimination parameters for the multiple outcome items. The covariates in the model can be at any level. Assuming either a probit or logistic response function, maximum marginal likelihood estimation is described utilizing multidimensional Gauss-Hermite quadrature for integration of the random effects. An iterative Fisher-scoring solution, which provides standard errors for all model parameters, is used. A data set from a longitudinal prevention study is used to motivate the application of the proposed model. In this study, multiple ordinal items of health behavior are repeatedly measured over time. Because of a planned missing design, subjects answered only two-third of all items at a given point.

Marginalized models for longitudinal ordinal data with application to quality of life studies

Random effects are often used in generalized linear models to explain the serial dependence for longitudinal categorical data. Marginalized random effects models (MREMs) for the analysis of longitudinal binary data have been proposed to permit likelihood-based estimation of marginal regression parameters. In this paper, we propose a model to extend the MREM to accommodate longitudinal ordinal data. Maximum marginal likelihood estimation is proposed utilizing quasi-Newton algorithms with Monte Carlo integration of the random effects. Our approach is applied to analyze the quality of life data from a recent colorectal cancer clinical trial. Dropout occurs at a high rate and is often due to tumor progression or death. To deal with events due to progression/death, we used a mixture model for the joint distribution of longitudinal measures and progression/death times and use principal stratification to draw causal inferences about survivors.

A class of markov models for longitudinal ordinal data

Generalized linear models with serial dependence are often used for short longitudinal series. Heagerty (2002, Biometrics58, 342-351) has proposed marginalized transition models for the analysis of longitudinal binary data. In this article, we extend this work to accommodate longitudinal ordinal data. Fisher-scoring algorithms are developed for estimation. Methods are illustrated on quality-of-life data from a recent colorectal cancer clinical trial.

Using polytomous item response models to assess death anxiety

BACKGROUND

: The study of human attitudes toward death has given rise to a substantial body of empirical research. Psychometric instruments have been developed to measure fear of death, or death anxiety, and its psychological consequences in people who continually come into contact with stimuli related to mortality.

OBJECTIVES

: To analyze the 20-item Death Anxiety Inventory (DAI) within the framework of item response theory (IRT) and using the generalized partial credit model.

METHODS

: The sample comprised 154 men and 550 women and was drawn from nurses, doctors, industrial workers, teachers, undergraduates, and retired persons. Subjects completed the DAI, a self-administered, Likert-type questionnaire of 20 items, each with six response options.

RESULTS

: The DAI showed a relatively adequate fit to the generalized partial credit model. Thus, 4 of the 20 items presented a poor fit to the model. The analysis of item information and test information functions revealed that the 20-item test was appropriate for differentiating subjects with medium or high levels of death anxiety. The test information function was higher in this range of scores, indicating greater precision in the estimate of death anxiety for these subjects.

DISCUSSION

: The generalized partial credit model can be used to obtain detailed information about a clinical test and its items, and there are advantages to this approach when working with polytomous tests.