Covariate-adjusted Regression Model Research Articles

Impact of acute lymphoblastic leukemia induction therapy: findings from metabolomics on non-fasted plasma samples from a biorepository.

Acute lymphoblastic leukemia (ALL) is among the most common cancers in children. With improvements in combination chemotherapy regimens, the overall survival has increased to over 90%. However, the current challenge is to mitigate adverse events resulting from the complex therapy. Several chemotherapies intercept cancer metabolism, but little is known about their collective role in altering host metabolism. We profiled the metabolomic changes in plasma of ALL patients initial- and post- induction therapy. We exploited a biorepository of non-fasted plasma samples derived from the Dana Farber Cancer Institute ALL Consortium; these samples were obtained from 50 ALL patients initial- and post-induction therapy. Plasma metabolites and complex lipids were analyzed by high resolution tandem mass spectrometry and differential mobility tandem mass spectrometry. Data were analyzed using a covariate-adjusted regression model with multiplicity adjustment. Pathway enrichment analysis and co-expression network analysis were performed to identify unique clusters of molecules. More than 1200 metabolites and complex lipids were identified in the total of global metabolomics and lipidomics platforms. Over 20% of those molecules were significantly altered. In the pathway enrichment analysis, lipids, particularly phosphatidylethanolamines (PEs), were identified. Network analysis indicated that the bioactive fatty acids, docosahexaenoic acid (DHA)-containing (22:6) triacylglycerols (TAGs), were decreased in the post-induction therapy. Metabolomic profiling in ALL patients revealed a large number of alterations following induction chemotherapy. In particular, lipid metabolism was substantially altered. The changes in metabolites and complex lipids following induction therapy could provide insight into the adverse events experienced by ALL patients.

Outlier detection under a covariate-adjusted exponential regression model with censored data

Exponential regression models with censored data are most widely used in practice. In the modeling process, there exist situations where the covariates are not directly observed but are observed after being contaminated by unknown functions of an observable confounder in a multiplicative manner. The problem of outlier detection is a fundamental and important problem in applied statistics. In this paper, we use a nonparametric regression method to adjust the covariates and recast the outlier detection issue into a high-dimensional regularization regression issue in the covariate-adjusted exponential regression model with censored data. We propose a smoothly clipped absolute deviation (SCAD) penalized likelihood method to detect the possible outliers, which features that the proposed method can simultaneously deal with outlier detection and estimations for the regression coefficients. The coordinate descent algorithm is employed to facilitate computation. Simulation studies are conducted to evaluate the finite-sample performance of our proposed method. An application to a German breast cancer study demonstrates the utility of the proposed method in practice.

The Relationship Between Personality and Perceived Mental Fatigability

Several personality traits are known to be protective against global fatigue, however perceived mental fatigability (PMF, Pittsburgh Fatigability Scale 0-50) specifically measures an individual’s susceptibility to cognitive tiredness and is associated with mobility decline. We assessed whether optimism, conscientiousness, goal reengagement and goal disengagement contributed to greater PMF in 1,812 men (mean±SD age 84.4±4.2 years, 90.4% white) in the Osteoporotic Fractures in Men Study 4th visit (2014-2016). Covariates included demographic, psychological/behavioral factors, health conditions, physical activity and function. Prevalence of higher PMF (score ≥13) was 25% (n=448). In a covariate-adjusted regression model, each SD lower conscientiousness and lower optimism were associated with 0.93 and 0.61 SDs greater PMF, each p<0.01. Goal disengagement and goal reengagement were not associated with PMF. These findings warrant further investigation into how personality traits may help clinicians design targeted and effective interventions to reduce fatigability, and consequently lower the risk of adverse aging-related health outcomes.

The impact of personality traits on medication adherence and self-care in patients with type 2 diabetes mellitus: The moderating role of gender and age

ObjectivesThis study aimed to investigate the role of the five-factor model of personality (FFM) and the moderating role of gender and age in predicting medication adherence (MA) and self-care behaviors (SCB) among Iranian patients with type 2 diabetes mellitus (T2DM). MethodsThis study was conducted on 495 patients with T2DM (73.5% female; n = 364) from two major cities of Iran (Tehran and Qom) in 2019. Pearson's correlation coefficient, multiple regression analysis, and conditional process analysis were performed. P < .05 and P < .10 were considered significant for the relationships and moderation analysis, respectively. ResultsNeuroticism indicated a negative association with MA and SCB. Positive associations were found between MA and personality traits, including extraversion, agreeableness, and conscientiousness, whereas extraversion showed a weak correlation with SCB. According to the covariate-adjusted regression model, neuroticism had a negative effect on MA and SCB. Agreeableness had a positive effect on MA and a negative effect on SCB. However, extraversion exerted a negative effect on MA and a positive effect on SCB. Also, the negative effect of neuroticism on MA was highlighted in women, indicating marginally significant moderation effect. The positive effects of extraversion and conscientiousness on MA were moderated by age. The effect of conscientiousness on SCB was positive in young patients and negative in old patients. No interaction effect was observed between age and gender. ConclusionThis study indicated that neuroticism, extraversion, and agreeableness significantly contributed to MA, but not to SCB. However, the effects were conditioned by age for extraversion and conscientiousness to some extent.

L_{1}-Estimation for covariate-adjusted regression

We study a covariate-adjusted regression(CAR) model that is proposed for such situations where both predictors and response in a regression model are not directly observable but are distorted by a multiplicative factor that is determined by an unknown function of some observable covariate. By establishing a connection to varying-coefficient models, we present the local linear L_{1}-estimation method when the underlying error distribution deviates from a normal distribution. The robust estimators of parameters are proposed in the underlying regression model. The consistency and asymptotic normality of the robust estimators are investigated. Since the limit distribution depends on the unknown components of the errors, an empirical likelihood ratio method based on L_{1} estimator is proposed. The confidence intervals for the regression coefficients are constructed. Simulation results demonstrate the superiority of the proposed estimators over other classical estimators when the underlying errors have heavy tails. Pima Indian diabetes data set is conducted to illustrate the performance of the proposed method, where the response and predictors are potentially contaminated by body mass index.

The association of age with acute toxicities in NRG oncology combined modality lower GI cancer trials.

649 Background: This study sought to compare adverse events (AEs) of older and younger adults with lower gastrointestinal (GI) malignancies treated on NRG studies. Methods: Data from six NRG trials (RTOG 9811/0012/0247/0529/0822 &amp; NSABP R-04), testing combined modality therapy (radiation and chemotherapy) in patients with anal or rectal cancer, were collected to test the hypothesis that older age was associated with increase in acute ( ≤ 90 days from treatment start) AEs. AEs were defined as GI, Genitourinary (GU), hematologic, or skin. AEs and compliance with protocol-directed therapy were compared between patients aged ≥ 70 years and &lt; 70 years. Categorical variables were compared across age groups using the chi-square test. The association of age on AEs was evaluated using a covariate-adjusted logistic regression model, with odds ratio (OR) reported. To adjust for multiple comparisons, a p-value &lt; 0.01 was considered statistically significant. Results: Data from 2525 patients were collected (43% female, 72% rectal cancer). There were 380 patients ≥ 70 years old (15%). Older patients were more likely to have worse baseline performance status (PS 1 or 2) (23% vs. 16%, p &lt;0.01), but otherwise baseline characteristics were similar. Older patients were less likely to have completed their chemotherapy (78% vs. 87%, p &lt; 0.01), but had similar median RT duration. On univariate analysis, patients ≥ 70 were more likely to experience grade ≥ 3 GI AEs (36% vs. 23%, OR 1.82, p &lt; 0.001), and less likely to experience ≥ 3 skin AEs (8% vs. 14%, OR 0.56, p = 0.002). There was no difference between GU or hematologic AEs. On multivariable analysis, age ≥ 70 was associated with grade ≥ 3 GI AE (OR 1.80, 95% CI: 1.40, 2.31; p &lt; 0.001) after adjusting for gender, PS, T stage, disease site, RT duration, and chemotherapy completion. Conclusions: Older patients with curable lower GI cancers who underwent combined-modality therapy were less likely to complete chemotherapy and were more likely to experience serious GI toxicity, whereas younger patients had higher rates of serious skin AEs.

An adaptive estimation for covariate-adjusted nonparametric regression model

For covariate-adjusted nonparametric regression model, an adaptive estimation method is proposed for estimating the nonparametric regression function. Compared with the procedures introduced in the existing literatures, the new method needs less strict conditions and is adaptive to covariate-adjusted nonparametric regression with asymmetric variables. More specifically, when the distributions of the variables are asymmetric, the new procedures can gain more efficient estimators and recover data more accurately by elaborately choosing proper weights; and for the symmetric case, the new estimators can obtain the same asymptotic properties as those obtained by the existing method via designing equal bandwidths and weights. Simulation studies are carried out to examine the performance of the new method in finite sample situations and the Boston Housing data is analyzed as an illustration.

Biological Age, Not Chronological Age, Is Associated with Late-Life Depression.

The pathophysiology of late-life depression (LLD) is complex and heterogeneous, with age-related processes implicated in its pathogenesis. This study examined the cross-sectional and longitudinal association between depressive symptoms and a baseline multibiomarker algorithm of biological age (BA) that aggregates indicators of inflammatory, metabolic, cardiovascular, lung, liver, and kidney functioning. Data were analyzed from 2,776 men and women from the prospective observational Health Aging and Body Composition Study, who had both evaluable chronological age (CA) and BA. Depressive symptoms were assessed using the Center for Epidemiologic Studies Depression (CES-D) scale. A covariate-adjusted regression model showed that BA (B = 0.03, p = .0471) but not CA (B = -0.01, p = .7185) is associated with baseline CES-D scores. The mean baseline BA for individuals with a CES-D ≥ 10 was 1.28 years greater than in those with a CES-D < 10. Comparatively, there is only a 0.05-year difference in mean CA between the two depression groups. A covariate-adjusted longitudinal model found that baseline BA predicts CES-D score at follow-up (B = 0.04, p = .0058), whereas CA does not (B = 0.03, p = .4125). Additionally, an older BA significantly predicted a CES-D ≥ 10 (B = 0.02, p = .032) over a 10-year period. A multibiomarker index of an older adult's BA outperformed their CA in predicting subsequent increased and clinically significant depressive symptoms. This result supports the evolving view of LLD as a brain disorder resulting from deleterious age-associated changes across numerous physiological systems.

Nonparametric covariate adjustment in estimating hazard ratios.

In randomized clinical trials with time-to-event outcomes, the hazard ratio is commonly used to quantify the treatment effect relative to a control. The Cox regression model is commonly used to adjust for relevant covariates to obtain more accurate estimates of the hazard ratio between treatment groups. However, it is well known that the treatment hazard ratio based on a covariate-adjusted Cox regression model is conditional on the specific covariates and differs from the unconditional hazard ratio that is an average across the population. Therefore, covariate-adjusted Cox models cannot be used when the unconditional inference is desired. In addition, the covariate-adjusted Cox model requires the relatively strong assumption of proportional hazards for each covariate. To overcome these challenges, a nonparametric randomization-based analysis of covariance method was proposed to estimate the covariate-adjusted hazard ratios for multivariate time-to-event outcomes. However, empirical evaluations of the performance (power and type I error rate) of the method have not been studied. Although the method is derived for multivariate situations, for most registration trials, the primary endpoint is a univariate outcome. Therefore, this approach is applied to univariate outcomes, and performance is evaluated through a simulation study in this paper. Stratified analysis is also investigated. As an illustration of the method, we also apply the covariate-adjusted and unadjusted analyses to an oncology trial.

Correlates of Depressive Symptoms in Older Adults with Diabetes

Investigators examined correlates of depressive symptoms within a sample of older adults with diabetes. Participants completed a structured telephone interview with measures including depressive symptoms, health conditions, cognitive function, and diabetes distress. Correlations and hierarchical linear regression models were utilized to examine bivariate and covariate-adjusted correlates of depressive symptoms. The sample included 246 community-dwelling adults with diabetes (≥65 years old). In bivariate analyses, African Americans, individuals with specific health issues (neuropathy, stroke, respiratory issues, arthritis, and cardiac issues), and those with higher levels of diabetes distress reported more depressive symptoms. Older age, higher education, more income, and better cognitive function were inversely associated with depressive symptoms. In the final covariate-adjusted regression model, stroke (B = .22, p < .001), cognitive function (B = −.14, p < .01), and higher levels of diabetes-related distress (B = .49, p < .001) each were uniquely associated with more depressive symptoms. Diabetes distress partially mediated the associations between cardiac issues and depressive symptoms and between cognitive function and depressive symptoms. Findings suggest that interventions targeted at helping older adults manage their diabetes-related distress and reducing the likelihood of experiencing additional health complications may reduce depressive symptoms within this population.

Associations of Social Support and Self-Efficacy With Quality of Life in Older Adults With Diabetes.

Older adults are disproportionately affected by diabetes, which is associated with increased prevalence of cardiovascular disease, decreased quality of life (QOL), and increased health care costs. The purpose of the current study was to assess the relationships between social support, self-efficacy, and QOL in a sample of 187 older African American and Caucasian individuals with diabetes. Greater satisfaction with social support related to diabetes (but not the amount of support received) was significantly correlated with QOL. In addition, individuals with higher self-efficacy in managing diabetes had better QOL. In a covariate-adjusted regression model, self-efficacy remained a significant predictor of QOL. Findings suggest the potential importance of incorporating the self-efficacy concept within diabetes management and treatment to empower older adults living with diabetes to adhere to care. Further research is needed to determine whether improving self-efficacy among vulnerable older adult populations may positively influence QOL.

Covariate-Adjusted Regression for Time Series

The main purpose of this article is to consider the covariate-adjusted regression (CAR) model for time series. The CAR model was initially proposed by Sentürk and Müller (2005) for such situations where predictor and response variables are not directly observed, but are distorted by some common observable covariate. Despite CAR being originally designed for independent cross-sectional data, multiple works have extended this method to dependent data setting. In this article, the authors extend CAR to the distorted time series setting. This extension is meaningful in many fields such as econometrics, mathematical finance, and signal processing. The estimates of regression parameters are proposed by establishing connection with functional-coefficient time series model. The consistency and asymptotic normality of the proposed estimates are investigated under the α-mixing conditions. Real data and simulated examples are provided for illustration.

Inhaled corticosteroid use is associated with lower mortality for subjects with COPD and hospitalised with pneumonia

Recent studies suggest that use of inhaled corticosteroids (ICS) in chronic obstructive pulmonary disease (COPD) may be associated with a higher incidence of pneumonia. However, it is unclear whether COPD subjects on ICS who develop pneumonia have worse outcomes. Therefore, our aim was to examine the association of prior outpatient ICS therapy with mortality in hospitalised COPD subjects with pneumonia. We included subjects ≥64 yrs of age, hospitalised with pneumonia in US Veterans Affairs hospitals, and assessed the association of ICS exposure with mortality for hospitalised COPD subjects with pneumonia in a covariate-adjusted regression model. We identified 6,353 subjects with a diagnosis of pneumonia and prior COPD, of whom 38% were on ICS. Mortality was 9% at 30 days and 16% at 90 days. In regression analyses, outpatient ICS therapy was associated with lower mortality at both 30 days (OR 0.76, 95% CI 0.70-0.83), and 90 days (OR 0.80, 95% CI 0.75-0.86). Outpatient therapy with ICS was associated with a significantly lower 30- and 90-day mortality in hospitalised COPD patients with pneumonia.

Covariate-adjusted regression

mue11er@wa1d.ucdavis.edu SUMMARY We introduce covariate-adjusted regression for situations where both predictors and response in a regression model are not directly observable, but are contaminated with a multiplicative factor that is determined by the value of an unknown function of an observable covariate. We demonstrate how the regression coefficients can be estimated by establishing a connection to varying-coefficient regression. The proposed covariate adjustment method is illustrated with an analysis of the regression of plasma fibrinogen concentration as response on serum transferrin level as predictor for 69 haemodialysis patients. In this example, both response and predictor are thought to be influenced in a multiplicative fashion by body mass index. A bootstrap hypothesis test enables us to test the significance of the regression parameters. We establish consistency and convergence rates of the parameter estimators for this new covariate-adjusted regression model. Simulation studies demonstrate the efficacy of the proposed method.