The first-order Markov conditional linear expectation approach for analysis of longitudinal data

We consider longitudinal discrete data that may be unequally spaced in time and may exhibit overdispersion, so that the variance of the outcome variable is inflated relative to its assumed distribution. We implement an approach that extends generalized linear models for analysis of longitudinal data and is likelihood based, in contrast to generalized estimating equations (GEE) that are semiparametric. The method assumes independence between subjects; first-order antedependence within subjects; exponential family distributions for the first outcome on each subject and for the subsequent conditional distributions; and linearity of the expectations of the conditional distributions. We demonstrate application of the method in an analysis of seizure counts and in a study to evaluate the performance of transplant centers. Simulations for both studies demonstrate the benefits of the proposed likelihood based approach; however, they also demonstrate better than anticipated performance for GEE.

Small-sample inference for cluster-based outcome-dependent sampling schemes in resource-limited settings: Investigating low birthweight in Rwanda

The neonatal mortality rate in Rwanda remains above the United Nations Sustainable Development Goal 3 target of 12 deaths per 1000 live births. As part of a larger effort to reduce preventable neonatal deaths in the country, we conducted a study to examine risk factors for low birthweight. The data were collected via a cost-efficient cluster-based outcome-dependent sampling (ODS) scheme wherein clusters of individuals (health centers) were selected on the basis of, in part, the outcome rate of the individuals. For a given data set collected via a cluster-based ODS scheme, estimation for a marginal model may proceed via inverse-probability-weighted generalized estimating equations, where the cluster-specific weights are the inverse probability of the health center's inclusion in the sample. In this paper, we provide a detailed treatment of the asymptotic properties of this estimator, together with an explicit expression for the asymptotic variance and a corresponding estimator. Furthermore, motivated by the study we conducted in Rwanda, we propose a number of small-sample bias corrections to both the point estimates and the standard error estimates. Through simulation, we show that applying these corrections when the number of clusters is small generally reduces the bias in the point estimates, and results in closer to nominal coverage. The proposed methods are applied to data from 18 health centers and 1 district hospital in Rwanda.

Using Multiple Imputation with GEE with Non-monotone Missing Longitudinal Binary Outcomes

This paper considers multiple imputation (MI) approaches for handling non-monotone missing longitudinal binary responses when estimating parameters of a marginal model using generalized estimating equations (GEE). GEE has been shown to yield consistent estimates of the regression parameters for a marginal model when data are missing completely at random (MCAR). However, when data are missing at random (MAR), the GEE estimates may not be consistent; the MI approaches proposed in this paper minimize bias under MAR. The first MI approach proposed is based on a multivariate normal distribution, but with the addition of pairwise products among the binary outcomes to the multivariate normal vector. Even though the multivariate normal does not impute 0 or 1 values for the missing binary responses, as discussed by Horton et al. (Am Stat 57:229-232, 2003), we suggest not rounding when filling in the missing binary data because it could increase bias. The second MI approach considered is the fully conditional specification (FCS) approach. In this approach, we specify a logistic regression model for each outcome given the outcomes at other time points and the covariates. Typically, one would only include main effects of the outcome at the other times as predictors in the FCS approach, but we explore if bias can be reduced by also including pairwise interactions of the outcomes at other time point in the FCS. In a study of asymptotic bias with non-monotone missing data, the proposed MI approaches are also compared to GEE without imputation. Finally, the proposed methods are illustrated using data from a longitudinal clinical trial comparing four psychosocial treatments from the National Institute on Drug Abuse Collaborative Cocaine Treatment Study, where patients' cocaine use is collected monthly for 6 months during treatment.

A robust and unified framework for estimating heritability in twin studies using generalized estimating equations

The 'heritability' of a phenotype measures the proportion of trait variance due to genetic factors in a population. In the past 50 years, studies with monozygotic and dizygotic twins have estimated heritability for 17,804 traits;¹ thus twin studies are popular for estimating heritability. Researchers are often interested in estimating heritability for non-normally distributed outcomes such as binary, counts, skewed or heavy-tailed continuous traits. In these settings, the traditional normal ACE model (NACE) and Falconer's method can produce poor coverage of the true heritability. Therefore, we propose a robust generalized estimating equations (GEE2) framework for estimating the heritability of non-normally distributed outcomes. The traditional NACE and Falconer's method are derived within this unified GEE2 framework, which additionally provides robust standard errors. Although the traditional Falconer's method cannot adjust for covariates, the corresponding 'GEE2-Falconer' can incorporate mean and variance-level covariate effects (e.g. let heritability vary by sex or age). Given a non-normally distributed outcome, the GEE2 models are shown to attain better coverage of the true heritability compared to traditional methods. Finally, a scenario is demonstrated where NACE produces biased estimates of heritability while Falconer remains unbiased. Therefore, we recommend GEE2-Falconer for estimating the heritability of non-normally distributed outcomes in twin studies.

Risk factors for hospitalization in youth with type 1 diabetes: Development and validation of a multivariable prediction model

OBJECTIVE

To develop a multivariable prediction model to identify patients with type 1 diabetes at increased risk of hospitalization for diabetic ketoacidosis or hyperglycemia with ketosis in the 12 months following assessment.

METHODS

Retrospective review of clinical data from patients with type 1 diabetes less than 17 years old at a large academic children's hospital (5732 patient years, 652 admissions). Data from the previous 12 months were assessed on October 15, 2015, 2016, 2017, and 2018, and used to predict hospitalization in the following 12 months using generalized estimating equations. Variables that were significant predictors of hospitalization in univariate analyses were entered into a multivariable model. 2014 to 2016 data were used as a training dataset, and 2017 to 2019 data for validation. Discrimination of the model was assessed with receiver operator characteristic curves.

RESULTS

Admission in the preceding year, hemoglobin (Hb)A1c, non-commercial insurance, female sex, and non-White race were all individual predictors of hospitalization, but age, duration of diabetes and number of office visits in the preceding year were not. In multivariable analysis with threshold P < .0033, admissions in the previous 12 months, HbA1c, and non-commercial insurance remained as significant predictors. The model identified a subset of ~8% of the patients with a collective 42% risk of hospitalization, thus increased 5-fold compared with the 8% risk of hospitalization in the remaining 93% of patients. Similar results were obtained with the validation dataset.

CONCLUSION

Our multivariable prediction model identified patients at increased risk of admission in the 12 months following assessment.

A trait-like propensity to experience internalizing symptoms is associated with problem alcohol involvement across adulthood, but not adolescence

There are stable between-person differences in an internalizing "trait," or the propensity to experience symptoms of internalizing disorders, such as social anxiety, generalized anxiety disorder, and depression. Trait internalizing may serve as a marker of heightened risk for problem alcohol outcomes (such as heavier drinking, binge drinking, or alcohol dependence). However, prior research on the association between internalizing symptoms and alcohol outcomes has been largely mixed in adolescence, with more consistent support for an association during adulthood. It may be that trait internalizing is only associated with problem alcohol outcomes in adulthood, after individuals have gained experience with alcohol. Some evidence suggested that these effects may be stronger for women than men. We used data from a community sample (n = 790) interviewed during adolescence (ages 14-16) and again at ages 21, 24, 27, 30, 33, and 39. Using generalized estimating equations, we tested the association between trait internalizing and alcohol outcomes during both adolescence and adulthood, and tested whether adult trait internalizing mediated the association between adolescent trait internalizing and adult alcohol outcomes. Trait internalizing in adulthood (but not adolescence) was associated with more frequent alcohol use, binge drinking and symptoms of alcohol use disorders, and mediated the effects of adolescent trait internalizing on alcohol outcomes. We observed no moderation by gender or change in these associations over time. Understanding the developmental pathways of trait internalizing may provide further insights into preventing the emergence of problem alcohol use behavior during adulthood. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

Excess cumulative incidence estimation for matched cohort survival studies

We suggest a regression approach to estimate the excess cumulative incidence function (CIF) when matched data are available. In a competing risk setting, we define the excess risk as the difference between the CIF in the exposed group and the background CIF observed in the unexposed group. We show that the excess risk can be estimated through an extended binomial regression model that actively uses the matched structure of the data, avoiding further estimation of both the exposed and the unexposed CIFs. The method naturally deals with two time scales, age and time since exposure and simplifies how to deal with the left truncation on the age time-scale. The model makes it easy to predict individual excess risk scenarios and allows for a direct interpretation of the covariate effects on the cumulative incidence scale. After introducing the model and some theory to justify the approach, we show via simulations that our model works well in practice. We conclude by applying the excess risk model to data from the ALiCCS study to investigate the excess risk of late events in childhood cancer survivors.

Glucose control and cognitive and physical function in adults 80+ years of age with diabetes

INTRODUCTION

We modeled associations between glycated hemoglobin (HbA1c) levels (<7%, 7% to 8%, and >8%) and cognitive and physical function among adults 80+ years of age with diabetes and determined whether associations differ by frailty, multimorbidity, and disability.

METHODS

A total of 316, adults with diabetes, 80+ years of age, were from the Adult Changes in Thought Study. The Cognitive Abilities Screening Instrument Item Response Theory (CASI-IRT) measured cognition. Short performance-based physical function (sPPF) and gait speed measured physical function. Glycosylated hemoglobin (HbA1c) levels were from clinical measurements. Analyses estimated associations between average HbA1c levels (<7%, 7% to 8%, and >8%) and functional outcomes using linear regressions estimated with generalized estimating equations.

RESULTS

sPPF scores did not differ significantly by HbA1c levels. Gait speed did, but only for non-frail individuals; those with HbA1c >8% were slower (-0.10 m/s [95% CI, -0.16 to -0.04]) compared to those with HbA1c 7% to 8%. The association between HbA1c and CASI-IRT varied with age (interaction P = 0.04). At age 80, for example, relative to people with HbA1c levels of 7% to 8%, CASI-IRT scores were, on average, 0.18 points lower (95% CI, -0.35 to -0.02) for people with HbA1c <7% and 0.22 points lower (95% CI, -0.40 to -0.05) for people with HbA1c >8%. At older ages, these estimated differences were attenuated. Estimated associations were not modified by multimorbidity or disability.

DISCUSSION

Moderate HbA1c levels of 7% to 8% were associated with better cognition in early but not late octogenarians with diabetes. Furthermore, HbA1c >8% was associated with slower gait speed among those without frailty. These results add to an evidence base for determining glucose targets for very old adults with diabetes.

Ultra high-dimensional semiparametric longitudinal data analysis

As ultra high-dimensional longitudinal data are becoming ever more apparent in fields such as public health and bioinformatics, developing flexible methods with a sparse model is of high interest. In this setting, the dimension of the covariates can potentially grow exponentially as exp ( n 1 / 2 ) with respect to the number of clusters n. We consider a flexible semiparametric approach, namely, partially linear single-index models, for ultra high-dimensional longitudinal data. Most importantly, we allow not only the partially linear covariates but also the single-index covariates within the unknown flexible function estimated nonparametrically to be ultra high dimensional. Using penalized generalized estimating equations, this approach can capture correlation within subjects, can perform simultaneous variable selection and estimation with a smoothly clipped absolute deviation penalty, and can capture nonlinearity and potentially some interactions among predictors. We establish asymptotic theory for the estimators including the oracle property in ultra high dimension for both the partially linear and nonparametric components, and we present an efficient algorithm to handle the computational challenges. We show the effectiveness of our method and algorithm via a simulation study and a yeast cell cycle gene expression data.

Tutorial on Biostatistics: Longitudinal Analysis of Correlated Continuous Eye Data

PURPOSE

To describe and demonstrate methods for analyzing longitudinal correlated eye data with a continuous outcome measure.

METHODS

We described fixed effects, mixed effects and generalized estimating equations (GEE) models, applied them to data from the Complications of Age-Related Macular Degeneration Prevention Trial (CAPT) and the Age-Related Eye Disease Study (AREDS). In CAPT (N = 1052), we assessed the effect of eye-specific laser treatment on change in visual acuity (VA). In the AREDS study, we evaluated effects of systemic supplement treatment among 1463 participants with AMD category 3.

RESULTS

In CAPT, the inter-eye correlations (0.33 to 0.53) and longitudinal correlations (0.31 to 0.88) varied. There was a small treatment effect on VA change (approximately one letter) at 24 months for all three models (p = .009 to 0.02). Model fit was better with the mixed effects model than the fixed effects model (p < .001). In AREDS, there was no significant treatment effect in all models (p > .55). Current smokers had a significantly greater VA decline than non-current smokers in the fixed effects model (p = .04) and the mixed effects model with random intercept (p = .0003), but marginally significant in the mixed effects model with random intercept and slope (p = .08), and GEE models (p = .054 to 0.07). The model fit was better with the fixed effects model than the mixed effects model (p < .0001).

CONCLUSION

Longitudinal models using the eye as the unit of analysis can be implemented using available statistical software to account for both inter-eye and longitudinal correlations. Goodness-of-fit statistics may guide the selection of the most appropriate model.

The life-course association of birth-weight genes with self-rated health

This study examines the impact of genes associated with normal-range birth weight (2500-4500 grams) on self-rated health in mid-to-late life course. Fifty-eight previously identified genetic variants that explain the variation in the normal-range birth weight were used to construct a genetic measure of birth weight for the non-Hispanic white sample from the Health and Retirement Study. Our results show that the genetic tendency toward higher birth weight predicts better self-rated health in mid-to-late life course net of various demographic, socioeconomic, and health behavioral factors. We also examine the heterogeneous effects of birth-weight genes across birth cohorts and age groups. Moreover, to clarify the paradox that higher birth weight can predict both better self-rated health and higher BMI, we show the positive association between birth weight genes and BMI can only hold within the normal-range BMI (18 ≤ BMI < 30). Overall, these findings suggest the genetic factors underlying the normal-range birth weight can have life-courseimpacts on health.

Maintaining the validity of inference in small-sample stepped wedge cluster randomized trials with binary outcomes when using generalized estimating equations

Stepped wedge cluster trials are an increasingly popular alternative to traditional parallel cluster randomized trials. Such trials often utilize a small number of clusters and numerous time intervals, and these components must be considered when choosing an analysis method. A generalized linear mixed model containing a random intercept and fixed time and intervention covariates is the most common analysis approach. However, the sole use of a random intercept applies a constant intraclass correlation coefficient structure, which is an assumption that is likely to be violated given stepped wedge trials (SWTs) have multiple time intervals. Alternatively, generalized estimating equations (GEE) are robust to the misspecification of the working correlation structure, although it has been shown that small-sample adjustments to standard error estimates and the use of appropriate degrees of freedom are required to maintain the validity of inference when the number of clusters is small. In this article, we show, using an extensive simulation study based on a motivating example and a more general design, the use of GEE can maintain the validity of inference in small-sample SWTs with binary outcomes. Furthermore, we show which combinations of bias corrections to standard error estimates and degrees of freedom work best in terms of attaining nominal type I error rates.

xtgeebcv: A command for bias-corrected sandwich variance estimation for GEE analyses of cluster randomized trials

Cluster randomized trials, where clusters (for example, schools or clinics) are randomized to comparison arms but measurements are taken on individuals, are commonly used to evaluate interventions in public health, education, and the social sciences. Analysis is often conducted on individual-level outcomes, and such analysis methods must consider that outcomes for members of the same cluster tend to be more similar than outcomes for members of other clusters. A popular individual-level analysis technique is generalized estimating equations (GEE). However, it is common to randomize a small number of clusters (for example, 30 or fewer), and in this case, the GEE standard errors obtained from the sandwich variance estimator will be biased, leading to inflated type I errors. Some bias-corrected standard errors have been proposed and studied to account for this finite-sample bias, but none has yet been implemented in Stata. In this article, we describe several popular bias corrections to the robust sandwich variance. We then introduce our newly created command, xtgeebcv, which will allow Stata users to easily apply finite-sample corrections to standard errors obtained from GEE models. We then provide examples to demonstrate the use of xtgeebcv. Finally, we discuss suggestions about which finite-sample corrections to use in which situations and consider areas of future research that may improve xtgeebcv.

The role of alimentary and biliopancreatic limb length in outcomes of Roux-en-Y gastric bypass

INTRODUCTION

Roux-en-Y gastric bypass (RYGB) is one of the safe and easily reproducible bariatric procedures.

AIM

To evaluate the effect of biliopancreatic limb (BPL) and alimentary limb (AL) length on weight loss outcomes after RYGB.

MATERIAL AND METHODS

This retrospective cohort study included 313 morbidly obese patients who underwent primary laparoscopic RYGB 2009-2015. Patients' BPL and AL lengths were categorized into three groups: group 1 (BPL: 50 cm and AL: 150 cm), group 2 (BPL: 150 cm and AL: 50 cm), and group 3 (BPL: 100 cm and AL: 100 cm). Data were provided from the Iranian National Obesity Surgery Database. The generalized estimating equations method was used to assess the effect of limbs length on %excess weight loss (%EWL).

RESULTS

Mean ± standard deviation age and body mass index (BMI) of 252 patients were 38.55 ±10.24 years and 45.8 ±4.77 kg/m2, respectively. Totally, 172 (68.3%, BMI of 46 ±5 kg/m2), 48 (19%, BMI of 45.12 ±4.26 kg/m2), and 32 (12.7%, BMI of 45.43 ±4.23 kg/m2) were in group 1, 2, and 3, respectively (p = 0.44). The results showed that the choice of different limb lengths had no significant effect on %EWL over 12 months follow-up (p = 0.625) adjusted for baseline BMI (p = 0.25). Mean %EWL in the patients with longer BPL and shorter AL was 5.43% (1.91, 8.95) higher in comparison to the patients with shorter BPL and longer AL during 36 months postoperatively adjusted for baseline BMI (p = 0.002).

CONCLUSIONS

During 12 months after RYGB, %EWL was not associated with BPL or AL length. However, during 36 months postoperatively, the patients with longer BPL had a significantly higher %EWL in comparison to the patients with shorter BPL.

Bivariate traits association analysis using generalized estimating equations in family data

Genome wide association study (GWAS) is becoming fundamental in the arduous task of deciphering the etiology of complex diseases. The majority of the statistical models used to address the genes-disease association consider a single response variable. However, it is common for certain diseases to have correlated phenotypes such as in cardiovascular diseases. Usually, GWAS typically sample unrelated individuals from a population and the shared familial risk factors are not investigated. In this paper, we propose to apply a bivariate model using family data that associates two phenotypes with a genetic region. Using generalized estimation equations (GEE), we model two phenotypes, either discrete, continuous or a mixture of them, as a function of genetic variables and other important covariates. We incorporate the kinship relationships into the working matrix extended to a bivariate analysis. The estimation method and the joint gene-set effect in both phenotypes are developed in this work. We also evaluate the proposed methodology with a simulation study and an application to real data.

Longitudinal Analysis of Ventilation Perfusion Mismatch in Congenital Diaphragmatic Hernia Survivors

OBJECTIVE

To determine the natural history of pulmonary function for survivors of congenital diaphragmatic hernia (CDH).

STUDY DESIGN

This was a retrospective cohort study of survivors of CDH born during 1991-2016 and followed at our institution. A generalized linear model was fitted to assess the longitudinal trends of ventilation (V), perfusion (Q), and V/Q mismatch. The association between V/Q ratio and body mass index percentile as well as functional status was also assessed with a generalized linear model.

RESULTS

During the study period, 212 patients had at least one V/Q study. The average ipsilateral V/Q of the cohort increased over time (P < .01), an effect driven by progressive reduction in relative perfusion (P = .012). A higher V/Q ratio was correlated with lower body mass index percentile (P < .001) and higher probability of poor functional status (New York Heart Association class III or IV) (P = .045).

CONCLUSIONS

In this cohort of survivors of CDH with more severe disease characteristics, V/Q mismatch worsens over time, primarily because of progressive perfusion deficit of the ipsilateral side. V/Q scans may be useful in identifying patients with CDH who are at risk for poor growth and functional status.

Marginal analysis of multiple outcomes with informative cluster size

In surveillance studies of periodontal disease, the relationship between disease and other health and socioeconomic conditions is of key interest. To determine whether a patient has periodontal disease, multiple clinical measurements (eg, clinical attachment loss, alveolar bone loss, and tooth mobility) are taken at the tooth-level. Researchers often create a composite outcome from these measurements or analyze each outcome separately. Moreover, patients have varying number of teeth, with those who are more prone to the disease having fewer teeth compared to those with good oral health. Such dependence between the outcome of interest and cluster size (number of teeth) is called informative cluster size and results obtained from fitting conventional marginal models can be biased. We propose a novel method to jointly analyze multiple correlated binary outcomes for clustered data with informative cluster size using the class of generalized estimating equations (GEE) with cluster-specific weights. We compare our proposed multivariate outcome cluster-weighted GEE results to those from the convectional GEE using the baseline data from Veterans Affairs Dental Longitudinal Study. In an extensive simulation study, we show that our proposed method yields estimates with minimal relative biases and excellent coverage probabilities.

Sample size estimation for stratified individual and cluster randomized trials with binary outcomes

Individual randomized trials (IRTs) and cluster randomized trials (CRTs) with binary outcomes arise in a variety of settings and are often analyzed by logistic regression (fitted using generalized estimating equations for CRTs). The effect of stratification on the required sample size is less well understood for trials with binary outcomes than for continuous outcomes. We propose easy-to-use methods for sample size estimation for stratified IRTs and CRTs and demonstrate the use of these methods for a tuberculosis prevention CRT currently being planned. For both IRTs and CRTs, we also identify the ratio of the sample size for a stratified trial vs a comparably powered unstratified trial, allowing investigators to evaluate how stratification will affect the required sample size when planning a trial. For CRTs, these can be used when the investigator has estimates of the within-stratum intracluster correlation coefficients (ICCs) or by assuming a common within-stratum ICC. Using these methods, we describe scenarios where stratification may have a practically important impact on the required sample size. We find that in the two-stratum case, for both IRTs and for CRTs with very small cluster sizes, there are unlikely to be plausible scenarios in which an important sample size reduction is achieved when the overall probability of a subject experiencing the event of interest is low. When the probability of events is not small, or when cluster sizes are large, however, there are scenarios where practically important reductions in sample size result from stratification.

Variable selection via penalized generalized estimating equations for a marginal survival model

Clustered and multivariate survival times, such as times to recurrent events, commonly arise in biomedical and health research, and marginal survival models are often used to model such data. When a large number of predictors are available, variable selection is always an important issue when modeling such data with a survival model. We consider a Cox's proportional hazards model for a marginal survival model. Under the sparsity assumption, we propose a penalized generalized estimating equation approach to select important variables and to estimate regression coefficients simultaneously in the marginal model. The proposed method explicitly models the correlation structure within clusters or correlated variables by using a prespecified working correlation matrix. The asymptotic properties of the estimators from the penalized generalized estimating equations are established and the number of candidate covariates is allowed to increase in the same order as the number of clusters does. We evaluate the performance of the proposed method through a simulation study and analyze two real datasets for the application.

On the analysis of two-phase designs in cluster-correlated data settings

In public health research, information that is readily available may be insufficient to address the primary question(s) of interest. One cost-efficient way forward, especially in resource-limited settings, is to conduct a two-phase study in which the population is initially stratified, at phase I, by the outcome and/or some categorical risk factor(s). At phase II detailed covariate data is ascertained on a subsample within each phase I strata. While analysis methods for two-phase designs are well established, they have focused exclusively on settings in which participants are assumed to be independent. As such, when participants are naturally clustered (eg, patients within clinics) these methods may yield invalid inference. To address this, we develop a novel analysis approach based on inverse-probability weighting that permits researchers to specify some working covariance structure and appropriately accounts for the sampling design and ensures valid inference via a robust sandwich estimator for which a closed-form expression is provided. To enhance statistical efficiency, we propose a calibrated inverse-probability weighting estimator that makes use of information available at phase I but not used in the design. In addition to describing the technique, practical guidance is provided for the cluster-correlated data settings that we consider. A comprehensive simulation study is conducted to evaluate small-sample operating characteristics, including the impact of using naïve methods that ignore correlation due to clustering, as well as to investigate design considerations. Finally, the methods are illustrated using data from a one-time survey of the national antiretroviral treatment program in Malawi.

Sequential adaptive variables and subject selection for GEE methods

Modeling correlated or highly stratified multiple-response data is a common data analysis task in many applications, such as those in large epidemiological studies or multisite cohort studies. The generalized estimating equations method is a popular statistical method used to analyze these kinds of data, because it can manage many types of unmeasured dependence among outcomes. Collecting large amounts of highly stratified or correlated response data is time-consuming; thus, the use of a more aggressive sampling strategy that can accelerate this process-such as the active-learning methods found in the machine-learning literature-will always be beneficial. In this study, we integrate adaptive sampling and variable selection features into a sequential procedure for modeling correlated response data. Besides reporting the statistical properties of the proposed procedure, we also use both synthesized and real data sets to demonstrate the usefulness of our method.

The Influence of Inpatient Physician Continuity on Hospital Discharge

BACKGROUND

Inpatient attending physicians may change during a patient's hospital stay. This study measured the association of attending physician continuity and discharge probability.

METHODS

All patients admitted to general medicine service at a tertiary care teaching hospital in 2015 were included. Attending inpatient physician continuity was measured as the consecutive number of days each patient was treated by the same staff-person. Generalized estimating equation methods were used to model the adjusted association of attending inpatient physician continuity with daily discharge probability.

RESULTS

6301 admissions involving 41 internists, 5134 patients, and 38,242 patient-days were studied. The final model had moderate discrimination (c-statistic = 0.70) but excellent calibration (Hosmer-Lemeshow statistic 11.5, 18 df, p value 0.89). Daily discharge probability decreased significantly with greater severity of illness, higher patient death risk, and longer length of stay, on admission day, for elective admissions, and on the weekend. Discharge likelihood increased significantly with attending inpatient physician continuity; daily discharge probability increased for the average patient from 15.3 to 20.9% when the consecutive number of days the patient was treated by the same attending inpatient physician increased from 1 to 7 days.

CONCLUSIONS

Inpatient attending physician continuity is significantly associated with the likelihood of patient discharge. This finding could be considered if resource utilization is a factor when scheduling attending inpatient physician coverage.

A GEE approach to estimating accuracy and its confidence intervals for correlated data

In this paper, we provide a method for constructing confidence interval for accuracy in correlated observations, where one sample of patients is being rated by two or more diagnostic tests. Confidence intervals for other measures of diagnostic tests, such as sensitivity, specificity, positive predictive value, and negative predictive value, have already been developed for clustered or correlated observations using the generalized estimating equations (GEE) method. Here, we use the GEE and delta-method to construct confidence intervals for accuracy, the proportion of patients who are correctly classified. Simulation results verify that the estimated confidence intervals exhibit consistent/appropriate coverage rates.

Domain-specific and total sedentary behaviors associated with psychological distress in older adults

Purpose: Time spent in sedentary behaviors has become a major public health problem, affecting both physical and mental conditions, which is regularly evident in older adults. The aim of this study was to explore the association between each domain-specific sedentary behavior (screen-time, leisure-time sedentary behavior and transport) and total sedentary behavior (sum of all indicators) with "high" psychological distress among older individuals. Patients and methods: In this cross-sectional study, we recruited 810 participants aged ≥85 (16% men) from 6 neighborhoods in the city of Zagreb. We used Measure of Older Adults' Sedentary Time sedentary behavior questionnaire to assess the time spent in a specific domain of sedentary behavior and Kessler K6 scale to assess the level of psychological distress. Participants who had a score ≥13 points were treated as those with "high" psychological distress. Generalized estimating equations with Poisson regression models and risk ratios were used to calculate the association. Results: After adjusting for sex, body mass index, sleep quality, self-rated health, material status, physical activity, diet and chronic diseases, participants categorized in the second, third and fourth quartile of screen-time, in the fourth quartile of leisure-time sedentary behavior and in the third and fourth quartile of total sedentary behavior were less likely to have "high" psychological distress. However, participants categorized in the fourth quartile of transport were more likely to have "high" psychological distress. Conclusion: Our study shows that more time spent in front of screens, leisure and in total sedentary behavior is associated with lower levels, while more time spent in transport is associated with higher levels of psychological distress, pointing out that the aforementioned associations remained even after adjusting for variables describing "general" physical health. Thus, strategies aiming to reduce the time spent in passive transport and enhance active transport in a sample of older adults are warranted.

Marginal analysis of ordinal clustered longitudinal data with informative cluster size

The issue of informative cluster size (ICS) often arises in the analysis of dental data. ICS describes a situation where the outcome of interest is related to cluster size. Much of the work on modeling marginal inference in longitudinal studies with potential ICS has focused on continuous outcomes. However, periodontal disease outcomes, including clinical attachment loss, are often assessed using ordinal scoring systems. In addition, participants may lose teeth over the course of the study due to advancing disease status. Here we develop longitudinal cluster-weighted generalized estimating equations (CWGEE) to model the association of ordinal clustered longitudinal outcomes with participant-level health-related covariates, including metabolic syndrome and smoking status, and potentially decreasing cluster size due to tooth-loss, by fitting a proportional odds logistic regression model. The within-teeth correlation coefficient over time is estimated using the two-stage quasi-least squares method. The motivation for our work stems from the Department of Veterans Affairs Dental Longitudinal Study in which participants regularly received general and oral health examinations. In an extensive simulation study, we compare results obtained from CWGEE with various working correlation structures to those obtained from conventional GEE which does not account for ICS. Our proposed method yields results with very low bias and excellent coverage probability in contrast to a conventional generalized estimating equations approach.