Many clinical trials repeatedly measure several longitudinal outcomes on patients. Patient follow‐up can discontinue due to an outcome‐dependent event, such as clinical diagnosis, death, or dropout. ...Joint modeling is a popular choice for the analysis of this type of data. Using example data from a prodromal Alzheimer's disease trial, we propose a new type of multivariate joint model in which longitudinal brain imaging outcomes and memory impairment ratings are allowed to be associated both with time to open‐label medication and dropout, and where the brain imaging outcomes may also directly affect the memory impairment ratings. Existing joint models for multivariate longitudinal outcomes account for the correlation between the longitudinal outcomes through the random effects, often by assuming a multivariate normal distribution. However, for these models, it is difficult to interpret how the longitudinal outcomes affect each other. We model the dependence between the longitudinal outcomes differently so that a first longitudinal outcome affects a second one. Specifically, for each longitudinal outcome, we use a linear mixed‐effects model to estimate its trajectory, where, for the second longitudinal outcome, we include the linear predictor of the first outcome as a time‐varying covariate. This facilitates an easy and direct interpretation of the association between the longitudinal outcomes and provides a framework for latent mediation analysis to understand the underlying biological processes. For the trial considered here, we found that part of the intervention effect is mediated through hippocampal brain atrophy. The proposed joint models are fitted using a Bayesian framework via MCMC simulation.
Colonization of the infant gut is believed to be critically important for a healthy growth as it influences gut maturation, metabolic, immune and brain development in early life. Understanding ...factors that influence this process is important, since an altered colonization has been associated with a higher risk of diseases later in life. Fecal samples were collected from 108 healthy neonates in the first half year of life. The composition and functionality of the microbiota was characterized by measuring 33 different bacterial taxa by qPCR/RT qPCR, and 8 bacterial metabolites. Information regarding gender, place and mode of birth, presence of siblings or pets; feeding pattern and antibiotic use was collected by using questionnaires. Regression analysis techniques were used to study associations between microbiota parameters and confounding factors over time. Bacterial DNA was detected in most meconium samples, suggesting bacterial exposure occurs in utero. After birth, colonization by species of Bifidobacterium, Lactobacillus and Bacteroides was influenced by mode of delivery, type of feeding and presence of siblings, with differences found at species level and over time. Interestingly, infant-type bifidobacterial species such as B. breve or B. longum subsp infantis were confirmed as early colonizers apparently independent of the factors studied here, while B. animalis subsp. lactis presence was found to be dependent solely on the type of feeding, indicating that it might not be a common infant gut inhabitant. One interesting and rather unexpected confounding factor was gender. This study contributes to our understanding of the composition of the microbiota in early life and the succession process and the evolution of the microbial community as a function of time and events occurring during the first 6 months of life. Our results provide new insights that could be taken into consideration when selecting nutritional supplementation strategies to support the developing infant gut microbiome.
Souvenaid aims to improve synapse formation and function. An earlier study in patients with Alzheimer's disease (AD) showed that Souvenaid increased memory performance after 12 weeks in drug-naïve ...patients with mild AD. The Souvenir II study was a 24-week, randomized, controlled, double-blind, parallel-group, multi-country trial to confirm and extend previous findings in drug-naïve patients with mild AD. Patients were randomized 1:1 to receive Souvenaid or an iso-caloric control product once daily for 24 weeks. The primary outcome was the memory function domain Z-score of the Neuropsychological Test Battery (NTB) over 24 weeks. Electroencephalography (EEG) measures served as secondary outcomes as marker for synaptic connectivity. Assessments were done at baseline, 12, and 24 weeks. The NTB memory domain Z-score was significantly increased in the active versus the control group over the 24-week intervention period (p = 0.023; Cohen's d = 0.21; 95% confidence interval -0.06-0.49). A trend for an effect was observed on the NTB total composite z-score (p = 0.053). EEG measures of functional connectivity in the delta band were significantly different between study groups during 24 weeks in favor of the active group. Compliance was very high (96.6% control and 97.1% active). No difference between study groups in the occurrence of (serious) adverse events. This study demonstrates that Souvenaid is well tolerated and improves memory performance in drug-naïve patients with mild AD. EEG outcomes suggest that Souvenaid has an effect on brain functional connectivity, supporting the underlying hypothesis of changed synaptic activity.
Many prodromal Alzheimer's disease trials collect two types of data: the time until clinical diagnosis of dementia and longitudinal patient information. These data are often analysed separately, ...although they are strongly associated. By combining the longitudinal and survival data into a single statistical model, joint models can account for the dependencies between the two types of data.
We illustrate the major steps in a joint modelling approach, motivated by data from a prodromal Alzheimer's disease study: the LipiDiDiet trial.
By using joint models we are able to disentangle baseline confounding from the intervention effect and moreover, to investigate the association between longitudinal patient information and the time until clinical dementia diagnosis.
Joint models provide a valuable tool in the statistical analysis of clinical studies with longitudinal and survival data, such as in prodromal Alzheimer's disease trials, and have several added values compared to separate analyses.
Joint models for longitudinal and survival data are increasingly used and enjoy a wide range of application areas. In this article, we focus on the application of joint models on clinical trial data ...with special interest in the treatment effect on the survival outcome. Within a joint model, the estimated treatment effect on the survival outcome is an aggregate comprising the indirect treatment effect through the longitudinal outcome and the direct treatment effect on the survival outcome. This overall treatment effect is, however, conditional on random effects, and therefore has a subject‐specific interpretation. The conditional interpretation arises from the shared random effects between the longitudinal and survival process in combination with the nonlinear link function of the survival model. The overall treatment effect is, therefore, not valid for population‐based inference, which is the goal for most clinical trials. We propose a method to obtain a marginal estimate of the overall treatment effect on the survival outcome in a joint model. Additionally, we extend our proposal to allow for different parameterizations for the association between the longitudinal and survival outcome. The proposed method is demonstrated on data of a clinical study on the effect of synbiotic on the gut microbiota of cesarean delivered infants, where we estimate the marginal overall treatment effect on the risk of eczema or atopic dermatitis using longitudinal information on fecal bifidobacteria.
This study on sensitivity and attachment included 55 toddlers and their parents. Samples included children with autism spectrum disorder (ASD), mental retardation, language delay, and typical ...development. Children were diagnosed at 4 years of age. Two years before diagnosis, attachment was assessed with the Strange Situation procedure, and parental sensitivity and child involvement during free play were assessed with the Emotional Availability Scale. Parents of children with ASD were equally sensitive as parents of children without ASD, but their children showed more attachment disorganization and less child involvement. More sensitive parents had more secure children, but only in the group without ASD. Less severe autistic symptoms in the social domain predicted more attachment security. Autism challenges the validity of attachment theory.
Missing data can complicate the interpretability of a clinical trial, especially if the proportion is substantial and if there are different, potentially outcome-dependent causes.
We aimed to obtain ...unbiased estimates, in the presence of a high level of missing data, for the intervention effects in a prodromal Alzheimer's disease trial: the LipiDiDiet study. We used a competing risk joint model that can simultaneously model each patient's longitudinal outcome trajectory in combination with the timing and type of missingness.
Using the competing risk joint model, we were able to provide unbiased estimates of the intervention effects in the presence of the different types of missingness. For the LipiDiDiet study, the intervention effects remained statistically significant after this correction for the timing and type of missingness.
Missing data is a common problem in (Alzheimer) clinical trials. It is important to realize that statistical techniques make specific assumptions about the missing data mechanisms. When there are different missing data sources, a competing risk joint model is a powerful method because it can explicitly model the association between the longitudinal data and each type of missingness.
Dutch Trial Register, NTR1705 . Registered on 9 March 2009.
It is unclear whether symptoms of autism spectrum disorder (ASD) in young children in the population fit the three-factor structure of ASD as described in the DSM-IV, and cluster together in ...individual subjects. This study analysed questionnaire data on ASD symptoms filled in by mothers of 11,332 18-month-old children that was collected in the context of the Norwegian Mother and Child Cohort Study conducted by the Norwegian Institute of Public Health. Confirmatory Factor Analyses showed that the three-factor model had a significantly better fit then the two- and one-factor model of ASD symptoms. Latent class analysis revealed four homogeneous groups of children (classes) with different scores for Social Interaction and Communication at one hand and Stereotypies/Rigidity at the other hand.
This article describes the development of a screening instrument for young children. Screening items were tested first in a non-selected population of children aged 8-20 months (n = 478). Then, ...parents of children with clinically diagnosed ASD (n = 153, average age 87 months) or ADHD (n = 76, average age 112 months) were asked to score the items retrospectively for when their child was 14 months old. A 14-item screening instrument, Early Screening of Autistic Traits (ESAT) which had maximal sensitivity and specificity for ASD was developed. The sensitivity of the ESAT was checked in an independent sample of 34 children aged 16-48 months clinically diagnosed with ASD. A 4-item version appears to be a promising prescreening instrument.