Direct and Indirect Treatment Effects With Time‐Varying Covariates

Direct Effects of Tadalafil on Lower Urinary Tract Symptoms versus Indirect Effects Mediated through Erectile Dysfunction Symptom Improvement: Integrated Data Analyses from 4 Placebo Controlled Clinical Studies

BackgroundBipolar depression is characterized by depressive symptoms and impairment in many areas of functioning, including work, family, and social life. The objective of this study was to assess the independent, direct effect of lurasidone treatment on functioning improvement, and examine the indirect effect of lurasidone treatment on functioning improvement, mediated through improvements in depression symptoms.MethodsData from a 6-week placebo-controlled trial assessing the effect of lurasidone monotherapy versus placebo in patients with bipolar depression was used. Patient functioning was measured using the Sheehan disability scale (SDS). Descriptive statistics were used to assess the effect of lurasidone on improvement on the SDS total and domain scores (work/school, social, and family life), as well as number of days lost and unproductive due to symptoms. Path analyses evaluated the total effect (β1), as well as the indirect effect (β2×β3) and direct effect (β4) of lurasidone treatment on SDS total score change, using standardized beta path coefficients and baseline scores as covariates. The direct effect of treatment on SDS total score change and indirect effects accounting for mediation through depression improvement were examined for statistical significance and magnitude using MPlus.ResultsIn this 6-week trial (N = 485), change scores from baseline to 6-weeks were significantly larger for both lurasidone treatment dosage groups versus placebo on the SDS total and all three SDS domain scores (p < 0.05). Through path analyses, lurasidone treatment predicted improvement in depression (β2 = −0.33, p = 0.009), subsequently predicting improvement in functional impairment (β3 = 0.70, p < 0.001; indirect effect = −0.23). The direct effect was of medium magnitude (β4 = −0.17, p = 0.04), indicating lurasidone had a significant and direct effect on improvement in functional impairment, after accounting for depression improvement.ConclusionsResults demonstrated statistically significant improvement in functioning among patients on lurasidone monotherapy compared to placebo. Improvement in functioning among patients on lurasidone was largely mediated through a reduction in depression symptoms, but lurasidone also had a medium and statistically significant independent direct effect in improving functioning.

Measuring safety treatment effects using full Bayes non-linear safety performance intervention functions

Current study is the second part of a 2-year cognitive-behavioral-ecological (CB-E) intervention for high-functioning (HF) children with autism spectrum disorder (ASD). We examined the utility of a group-centered intervention on children's ability to interact cooperatively with peers during structured and non-structured social situations. Direct (e.g., social problem solving) and indirect (theory of mind; executive function) treatment effects on social cognitive capabilities were also examined. Participants were 26 preadolescent HF children with ASD. Study results demonstrated direct and indirect treatment effects on social cognition and mixed results regarding children's social interaction capabilities. Although children's cooperative capabilities within the intervention group improved, dyadic, and group social interactions during school recess did not. Discussion focused on the utility of such group-intervention in increasing social functioning.

Measuring direct and indirect treatment effects using safety performance intervention functions

To apportion the direct effect and the indirect effect (through erections) that sildenafil (vs placebo) has on individual satisfaction and couple satisfaction over time, longitudinal mediation modeling was applied to outcomes on the Sexual Experience Questionnaire. The model included data from weeks 4 and 10 (double-blind phase) and week 16 (open-label phase) of a controlled study. Data from 167 patients with erectile dysfunction (ED) were available for analysis. Estimation of statistical significance was based on bootstrap simulations, which allowed inferences at and between time points. Percentages (and corresponding 95% confidence intervals) for direct and indirect effects of treatment were calculated using the model. For the individual satisfaction and couple satisfaction domains, direct treatment effects were negligible (not statistically significant) whereas indirect treatment effects via the erection domain represented >90% of the treatment effects (statistically significant). Week 4 vs week 10 percentages of direct and indirect effects were not statistically different, indicating that the mediation effects are longitudinally invariant. As there was no placebo arm in the open-label phase, mediation effects at week 16 were not estimable. In conclusion, erection has a crucial role as a mediator in restoring individual satisfaction and couple satisfaction in men with ED treated with sildenafil.

When studying the effect of a prenatal treatment on events in the offspring, failure to produce a live birth is a competing event for events in the offspring. A common approach to handle this competing event is reporting both the treatment-specific probabilities of live births and of the event of interest among live births. However, when the treatment affects the competing event, the latter probability cannot be interpreted as the causal effect among live births. Here we provide guidance for researchers interested in the effects of prenatal treatments on events in the offspring in the presence of the competing event "no live birth." We review the total effect of treatment on a composite event and the total effect of treatment on the event of interest. These causal effects are helpful for decision making but are agnostic about the pathways through which treatment affects the event of interest. Therefore, based on recent work, we also review three causal effects that explicitly consider the pathways through which treatment may affect the event of interest in the presence of competing events: the direct effect of treatment on the event of interest under an intervention to eliminate the competing event, the separable direct and indirect effects of treatment on the event of interest, and the effect of treatment in the principal stratum of those who would have had a live birth irrespective of treatment choice. As an illustrative example, we use a randomized trial of fertility treatments and risk of neonatal complications.

Background:Rapid and sustained pain control is an important goal for patients (pts) with rheumatoid arthritis (RA). Control of inflammation in RA does not always eliminate pain, which can have multifactorial...

Background:Pain, including inflammatory joint pain, may be debilitating in patients with psoriatic arthritis (PsA). Pain in PsA is multidimensional and can be influenced via reduction of inflammation and potentially by...

Difference-in-differences techniques for spatial data: Local autocorrelation and spatial interaction

Difference-in-Differences Techniques for Spatial Data: Local Autocorrelation and Spatial Interaction

Semicompeting risks refer to the phenomenon that the terminal event (such as death) can censor the nonterminal event (such as disease progression) but not vice versa. The treatment effect on the terminal event can be delivered either directly following the treatment or indirectly through the nonterminal event. We consider 2 strategies to decompose the total effect into a direct effect and an indirect effect under the framework of mediation analysis in completely randomized experiments by adjusting the prevalence and hazard of nonterminal events, respectively. They require slightly different assumptions on cross-world quantities to achieve identifiability. We establish asymptotic properties for the estimated counterfactual cumulative incidences and decomposed treatment effects. We illustrate the subtle difference between these 2 decompositions through simulation studies and two real-data applications in the Supplementary Materials.

Panel data of our interest consist of a moderate number of panels, while the panels contain a small number of observations. An estimator of common breaks in panel means without a boundary issue for this kind of scenario is proposed. In particular, the novel estimator is able to detect a common break point even when the change happens immediately after the first time point or just before the last observation period. Another advantage of the elaborated change point estimator is that it results in the last observation in situations with no structural breaks. The consistency of the change point estimator in panel data is established. The results are illustrated through a simulation study. As a by-product of the developed estimation technique, a theoretical utilization for correlation structure estimation, hypothesis testing and bootstrapping in panel data is demonstrated. A practical application to non-life insurance is presented, as well.

Further test mechanisms of the CHOICES intervention by replicating analyses of the experiential and behavioral processes of change (POC) for alcohol and for contraception as mediators of the intervention for reducing risk of alcohol-exposed pregnancy (AEP) using data from a more recent trial, CHOICES Plus (CP). As in the prior study, replication models examined indirect paths from intervention to experiential POC for alcohol at 3 months, to behavioral POC at 9 months, to risky drinking and risk of AEP at 9 months and experiential POC for contraception at 3 months, to behavioral POC at 9 months, and to ineffective contraception and risk of AEP at 9 months. To test the temporal relationship, additional models examined the indirect path from behavioral POC for alcohol and POC for contraception at 3 months, to the experiential POC at 9 months, and to risk of AEP at 9 months. A final model tested the mediation of experiential and behavioral POC assessed at 3 months. There was an indirect effect of the intervention on risky drinking (total indirect effect = -.13, 95% confidence interval [CI] [-.32, -.02]) but not AEP via the alcohol POC. There was an indirect effect of the intervention on ineffective contraception (total indirect effect = -.27, 95% CI [-.55, -.07]) and AEP (total indirect effect = -.22, 95% CI [-.46, -.06]) via the contraception POC. This study completely replicated the prior indirect effects of the CHOICES intervention on the targeted risk behaviors through the experiential and behavioral POC for each behavior. Findings support the utility of the POC for informing health behavior change interventions. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Ephemeral aquatic habitats and their associated microbial communities (microbiomes) play important roles in the growth and development of numerous aquatic insects, including mosquitoes (Diptera). Biological control agents, such as Bacillus thuringiensis israelensis (Bti) or insect growth regulators (e.g., methoprene), are commonly used to control mosquitoes in these habitats. However, it is unknown how commonly used control compounds affect the mosquito internal microbiome and potentially alter their life history traits. The objectives of this study were threefold: characterize the internal microbiota of Aedes larvae (Culicidae) in ephemeral forested mosquito habitat using high-throughput amplicon based sequencing, assess how mosquito control treatments affect the internal microbial communities of larval mosquitoes, and determine if changes to the microbiome resulted from direct or indirect treatment effects. The larval microbiome varied in community composition and diversity with development stage and treatment, suggesting potential effects of control compounds on insect microbial ecology. While microbial community differences due to Bti treatment were a result of indirect effects on larval development, methoprene had significant impacts on bacterial and algal taxa that could not be explained by indirect treatment effects. These results provide new information on the interactions between pesticide treatments and insect microbial communities.