Analysis of repeated measures data with clumping at zero

Measurement error models with zero inflation and multiple sources of zeros, with applications to hard zeros

We consider measurement error models for two variables observed repeatedly and subject to measurement error. One variable is continuous, while the other variable is a mixture of continuous and zero measurements. This second variable has two sources of zeros. The first source is episodic zeros, wherein some of the measurements for an individual may be zero and others positive. The second source is hard zeros, i.e., some individuals will always report zero. An example is the consumption of alcohol from alcoholic beverages: some individuals consume alcoholic beverages episodically, while others never consume alcoholic beverages. However, with a small number of repeat measurements from individuals, it is not possible to determine those who are episodic zeros and those who are hard zeros. We develop a new measurement error model for this problem, and use Bayesian methods to fit it. Simulations and data analyses are used to illustrate our methods. Extensions to parametric models and survival analysis are discussed briefly.

Comparative validation of automated presurgical tractography based on constrained spherical deconvolution and diffusion tensor imaging with direct electrical stimulation

OBJECTIVES

Accurate presurgical brain mapping enables preoperative risk assessment and intraoperative guidance. This cross-sectional study investigated whether constrained spherical deconvolution (CSD) methods were more accurate than diffusion tensor imaging (DTI)-based methods for presurgical white matter mapping using intraoperative direct electrical stimulation (DES) as the ground truth.

METHODS

Five different tractography methods were compared (three DTI-based and two CSD-based) in 22 preoperative neurosurgical patients undergoing surgery with DES mapping. The corticospinal tract (CST, N = 20) and arcuate fasciculus (AF, N = 7) bundles were reconstructed, then minimum distances between tractograms and DES coordinates were compared between tractography methods. Receiver-operating characteristic (ROC) curves were used for both bundles. For the CST, binary agreement, linear modeling, and posthoc testing were used to compare tractography methods while correcting for relative lesion and bundle volumes.

RESULTS

Distance measures between 154 positive (functional response, pDES) and negative (no response, nDES) coordinates, and 134 tractograms resulted in 860 data points. Higher agreement was found between pDES coordinates and CSD-based compared to DTI-based tractograms. ROC curves showed overall higher sensitivity at shorter distance cutoffs for CSD (8.5 mm) compared to DTI (14.5 mm). CSD-based CST tractograms showed significantly higher agreement with pDES, which was confirmed by linear modeling and posthoc tests (PFWE < .05).

CONCLUSIONS

CSD-based CST tractograms were more accurate than DTI-based ones when validated using DES-based assessment of motor and sensory function. This demonstrates the potential benefits of structural mapping using CSD in clinical practice.

First-interview response patterns of intensive longitudinal psychological and health data

Self-report data are essential in health psychology research where an individual's perception is critical to understanding one's health and psychological status. Intensive data collection over time, including daily diary assessments, is necessary in understanding within- and between-person variability in health and psychological processes over time. An "initial elevation or latent decline" (IELD) effect, inherent of self-report data, is increasingly acknowledged in the social psychology literature, but awareness of this effect in health psychology research is lacking, particularly in studies that emphasize within- and between-person variability in self-reports. The IELD effect is a pattern in which responses tend to be more extreme at the initial interview relative to subsequent responses. This paper illustrates the impact of IELD in applications of mixed-effects models based on observational self-reports and concludes that researchers take such effects into account in data analysis or in the research designing phase to help mitigate such effects.

Diagnostics for regression models with semicontinuous outcomes

Semicontinuous outcomes commonly arise in a wide variety of fields, such as insurance claims, healthcare expenditures, rainfall amounts, and alcohol consumption. Regression models, including Tobit, Tweedie, and two-part models, are widely employed to understand the relationship between semicontinuous outcomes and covariates. Given the potential detrimental consequences of model misspecification, after fitting a regression model, it is of prime importance to check the adequacy of the model. However, due to the point mass at zero, standard diagnostic tools for regression models (eg, deviance and Pearson residuals) are not informative for semicontinuous data. To bridge this gap, we propose a new type of residuals for semicontinuous outcomes that is applicable to general regression models. Under the correctly specified model, the proposed residuals converge to being uniformly distributed, and when the model is misspecified, they significantly depart from this pattern. In addition to in-sample validation, the proposed methodology can also be employed to evaluate predictive distributions. We demonstrate the effectiveness of the proposed tool using health expenditure data from the US Medical Expenditure Panel Survey.

Generalized Linear Models with Covariate Measurement Error and Zero-Inflated Surrogates

Epidemiological studies often encounter a challenge due to exposure measurement error when estimating an exposure-disease association. A surrogate variable may be available for the true unobserved exposure variable. However, zero-inflated data are encountered frequently in the surrogate variables. For example, many nutrient or physical activity measures may have a zero value (or a low detectable value) among a group of individuals. In this paper, we investigate regression analysis when the observed surrogates may have zero values among some individuals of the whole study cohort. A naive regression calibration without taking into account a probability mass of the surrogate variable at 0 (or a low detectable value) will be biased. We developed a regression calibration estimator which typically can have smaller biases than the naive regression calibration estimator. We propose an expected estimating equation estimator which is consistent under the zero-inflated surrogate regression model. Extensive simulations show that the proposed estimator performs well in terms of bias correction. These methods are applied to a physical activity intervention study.

Assessing Repeated Urinary Proline Betaine Measures as a Biomarker of Usual Citrus Intake during Pregnancy: Sources of Within-Person Variation and Correlation with Reported Intake

Proline betaine (Pro-B) has been identified as a biomarker of dietary citrus intake, yet gaps remain in its validation as a quantitative predictor of intake during various physiological states. This study quantified sources of within-individual variation (WIV) in urinary Pro-B concentration during pregnancy and assessed its correlation with the reported usual intake of citrus fruit and juice. Pro-B concentrations were determined by 1H-NMR spectroscopy in spot and 24-h urine specimens (n = 255) collected throughout pregnancy from women participating in the MARBLES cohort study. Adjusted linear or log mixed effects models quantified WIV and tested potential temporal predictors of continuous or elevated Pro-B concentration. Pearson or Spearman correlations assessed the relationship between averaged repeated biomarker measures and usual citrus intake reported by food frequency questionnaires. The proportion of variance in urinary Pro-B attributable to WIV ranged from 0.69 to 0.74 in unadjusted and adjusted models. Citrus season was a significant predictor of Pro-B in most analyses (e.g., adjusted β [95% CI]: 0.52 [0.16, 0.88] for non-normalized Pro-B), while gestational age predicted only non-normalized Pro-B (adjusted β [95% CI]: -0.093 [-0.18, -0.0038]). Moderate correlations (rs of 0.40 to 0.42) were found between reported usual citrus intake and averaged repeated biomarker measurements, which were stronger compared to using a single measurement. Given the high degree of WIV observed in urinary Pro-B, multiple samples per participant are likely needed to assess associations between citrus consumption and health outcomes.

Cystoisospora suis in Portugal: an observational study of prevalence, management, and risk factors

BACKGROUND

Neonatal coccidiosis is a common and important disease of suckling piglets in modern farming caused by Cystoisospora suis. Prevalence rates are high, namely, in Portugal, although no recent data are available. The metaphylactic administration of a single dose of toltrazuril and hygienic measures are the backbone of control strategies on positive farms. However, several studies have shown that these programs are not always effective, underlining the need to revise the risk factors and control strategies currently applied. The present study evaluated C. suis prevalence on Portuguese farms and assessed the risk factors associated with facilities and farm rearing practices.

RESULTS

From the 27 tested farms, 23 were positive to Cystoisopora suis (85.2%). In total, 258 litters were sampled (accounting for 516 samples-2 samples per litter), with an average of 59.7% of positive litters per positive farm. Faecal pools from litters, in which liquid faeces predominated had a higher probability of containing oocysts than litter pools with mainly solid (Odds Ratio: 9.87; p < 0.0001) or pasty faeces (OR: 7.05; p = 0.001), and samples obtained from younger animals had higher oocyst counts (coefficient: - 0.0720; 95% CI - 0.125; - 0.019). No significant effect of toltrazuril administration was observed on the positivity rate, and none of the tested farms used disinfectants with official claims against parasites and known anticoccidial effects (e.g., cresol-based products).

CONCLUSIONS

The C. suis prevalence on Portuguese swine farms appears to be similar to the prevalence found in other European countries. Repeated sampling of the same litter and the use of autofluorescence microscopy after a modified Ritchie technique seems to have increased sensitivity and consequently the detection rate of positive litters. Finally, despite the common use of oral toltrazuril, C. suis control programs appear to not always be effective (based on the detection of oocysts in faecal samples), suggesting the need to revise the control strategies applied in the field, including management factors and choices of disinfectant products.

Examining workweek variations in computer usage patterns: An application of ergonomic monitoring software

Alternative work arrangements have emerged as potential solutions to enhance productivity and work-life balance. However, accurate and objective measurement of work patterns is essential to make decisions about adjusting work arrangements. This study aimed at evaluating objective computer usage metrics as a proxy for productivity using RSIGuard, an ergonomics monitoring software. Data were collected from 789 office-based employees over a two-year period between January 1, 2017 and December 31, 2018 at a large energy company in Texas. A generalized mixed-effects model was utilized to compare computer usage patterns across different days of the week and times of the day. Our findings demonstrate that computer output metrics significantly decrease on Fridays compared to other weekdays, even after controlling for total active hours. Additionally, we found that workers' output varied depending on the time of day, with reduced computer usage observed in the afternoons and a significant decrease on Friday afternoons. The decrease in the number of typos was much less than that in the number of words typed, indicating reduced work efficiency on Friday afternoons. These objective indicators provide a novel approach to evaluating the productivity during the workweek and can help optimize work arrangements to promote sustainability for the benefit of employers, employees, and the environment.

Parasternal intercostal plane block catheters for cardiac surgery: a retrospective, propensity weighted, cohort study

Aim: Anesthesia for cardiac surgery has evolved toward fast-track recovery strategies incorporating non opioid analgesics and regional anesthesia. Materials & methods: This retrospective cohort study compared opioid consumption, pain scores and length of stay in patients who underwent cardiac surgery via median sternotomy and did or did not receive preoperative parasternal intercostal plane block catheters with postoperative ropivacaine infusions. Results: Postoperative opioid consumption and postoperative pain scores did not differ. Blocks were associated with decreased intraoperative opioids and reduced length of stay in the intensive care unit and hospital. Conclusion: Parasternal intercostal plane block catheters were not associated with decreased postoperative opioid consumption or pain scores, but were associated with reduced intraoperative opioids and length of stay.

Characterization of Arsenic and Atrazine Contaminations in Drinking Water in Iowa: A Public Health Concern

Arsenic and atrazine are two water contaminants of high public health concern in Iowa. The occurrence of arsenic and atrazine in drinking water from Iowa's private wells and public water systems was investigated over several decades. In this study, the percentages of detection and violation of regulations were compared over region, season, and water source, and factors affecting the detection and concentration of arsenic and atrazine were analyzed using a mixed-effects model. Atrazine contamination in drinking water was found to vary by region, depending on agricultural usage patterns and hydrogeological features. The annual median atrazine levels of all public water systems were below the drinking water standard of 3 ppb in 2001-2014. Around 40% of public water systems contained arsenic at levels > 1 ppb in 2014, with 13.8% containing arsenic at levels of 5-10 ppb and 2.6% exceeding 10 ppb. This unexpected result highlights the ongoing public health threat posed by arsenic in drinking water in Iowa, emphasizing the need for continued monitoring and mitigation efforts to reduce exposure and associated health risks. Additionally, an atrazine metabolite, desethylatrazine, should be monitored to obtain a complete account of atrazine exposure and possible health effects.

Bayesian Analysis of Tweedie Compound Poisson Partial Linear Mixed Models with Nonignorable Missing Response and Covariates

Under the Bayesian framework, this study proposes a Tweedie compound Poisson partial linear mixed model on the basis of Bayesian P-spline approximation to nonparametric function for longitudinal semicontinuous data in the presence of nonignorable missing covariates and responses. The logistic regression model is simultaneously used to specify the missing response and covariate mechanisms. A hybrid algorithm combining the Gibbs sampler and the Metropolis-Hastings algorithm is employed to produce the joint Bayesian estimates of unknown parameters and random effects as well as nonparametric function. Several simulation studies and a real example relating to the osteoarthritis initiative data are presented to illustrate the proposed methodologies.

A Randomized Intervention of Supplemental Nutrition Assistance Program-Education Did Not Improve Dietary Outcomes Except for Vitamin D Among Lower-Income Women in Indiana

BACKGROUND

The goal of US Department of Agriculture Supplemental Nutrition Assistance Program-Education (SNAP-Ed) is to improve the likelihood that those eligible for SNAP will make healthy choices aligned with the Dietary Guidelines for Americans, 2020-2025.

OBJECTIVE

The objective of the study was to evaluate the long-term effects of a direct SNAP-Ed intervention in which participants actively engage in learning with educator instruction about dietary quality and usual intake of key nutrient and food groups among Indiana SNAP-Ed-eligible women participants as an example sample in the context of no similar existing evaluation.

DESIGN

The study design was a parallel-arm, randomized controlled, nutrition education intervention, with follow-up at 1 year.

PARTICIPANTS/SETTING

Participants (18 years and older; n = 97 women) eligible for SNAP-Ed and interested in receiving nutrition education lessons were recruited from 31 Indiana counties from August 2015 to May 2016 and randomized to an intervention (n = 53) or control (n = 44) group.

INTERVENTION

The intervention comprised core lessons of Indiana SNAP-Ed delivered between 4 and 10 weeks after baseline assessment. Each participant completed a baseline and 1-year follow-up assessment. Dietary intake was assessed using repeated 24-hour dietary recalls (up to 2).

MAIN OUTCOME MEASURES

Mean usual nutrient, food group intake, diet quality (ie, Healthy Eating Index-2010 scores), and proportion of intervention and control groups meeting Dietary Guidelines for Americans, 2020-2025 recommendations and Dietary Reference Intake indicators of requirement or adequacy, were determined using the National Cancer Institute method and the simple Healthy Eating Index-2010 scoring algorithm method. Dietary changes between intervention and control groups were examined over time using mixed linear models.

STATISTICAL ANALYSES PERFORMED

Bonferroni-corrected significance levels were applied to the results of the mixed linear models for comparisons of usual intake of nutrients and foods.

RESULTS

No differences in diet quality, intake of food group components, food group intake, or nutrients were observed at 1-year follow-up, except that vitamin D intake was higher among those who received SNAP-Ed compared with the control group.

CONCLUSIONS

A direct SNAP-Ed intervention did not improve diet quality, food group intake, or key nutrient intake, except for vitamin D, among Indiana SNAP-Ed-eligible women up to 1 year after the nutrition education.

Effectiveness of multi-modal cognitive behavioural therapy in improving mental well-being among caregivers of children with disabilities in urban Uganda: A cluster-randomized controlled trial

Background

In Sub-Saharan Africa, 41 to 58% of the caregivers of children with disabilities experience psychological distress and have poor mental well-being. Cognitive behavioural therapy (CBT) has a moderate effect on improving mental well-being. However, no study has examined its effects among caregivers of children with disabilities at home and in schools. This study evaluated the effectiveness of CBT in improving mental well-being among caregivers of children with disabilities in urban Uganda.

Methods

We conducted a two-arm cluster-randomized controlled trial in 11 schools across the Kampala district of Uganda. The intervention was a multi-modal CBT training program conducted for six months among 392 home and school caregivers of children with disabilities. In the first three months, caregivers received group-based CBT, and in the next three months, they received phone-based CBT. We used generalized linear mixed-effects regression to examine the differences in the mental well-being of caregivers in the control group vs those in the intervention group.

Results

Home caregivers' mental well-being was significantly higher after phone-based CBT (unstandardized coefficient of the estimate (B) = 4.31, 95% CI = 1.18-6.82; P < 0.001, Cohen's D (d) = 0.27). School caregivers' mental well-being was significantly higher after group-based CBT (B = 3.98, 95% CI = 0.22-7.47; P = 0.038, d = 0.25).

Conclusions

Group-based CBT improved mental well-being among school caregivers, and phone-based CBT improved mental well-being among home caregivers. Interventions targeting school caregivers of children with disabilities should employ group settings and those targeting home caregivers should utilize peer-to-peer networks to enhance the caregivers' mental well-being.

Registration

The study protocol was registered with UMIN Clinical Trials Registry (UMIN-CTR). Trial ID: UMIN000040912.

Zero-augmented beta-prime model for multilevel semi-continuous data: a Bayesian inference

Semi-continuous data characterized by an excessive proportion of zeros and right-skewed continuous positive values appear frequently in medical research. One example would be the pharmaceutical expenditure (PE) data for which a substantial proportion of subjects investigated may report zero. Two-part mixed-effects models have been developed to analyse clustered measures of semi-continuous data from multilevel studies. In this study, we propose a new flexible two-part mixed-effects model with skew distributions for nested semi-continuous cost data under the framework of a Bayesian approach. The proposed model specification consists of two mixed-effects models linked by the correlated random effects: Part I) a model on the occurrence of positive values using a generalized logistic mixed model; and Part II) a model on the magnitude of positive values using a linear mixed model where the model errors follow skew distributions including beta-prime (BP). The proposed method is illustrated with pharmaceutical expenditure data from a multilevel observational study and the analytic results are reported by comparing potential models under different skew distributions. Simulation studies are conducted to assess the performance of the proposed model. The DIC₃, LPML, WAIC, and LOO as the Bayesian model selection criteria and measures of divergence used to compare the models.

Patient-Reported Outcome Dashboards Within the Electronic Health Record to Support Shared Decision-making: Protocol for Co-design and Clinical Evaluation With Patients With Advanced Cancer and Chronic Kidney Disease

BACKGROUND

Patient-reported outcomes-symptoms, treatment side effects, and health-related quality of life-are important to consider in chronic illness care. The increasing availability of health IT to collect patient-reported outcomes and integrate results within the electronic health record provides an unprecedented opportunity to support patients' symptom monitoring, shared decision-making, and effective use of the health care system.

OBJECTIVE

The objectives of this study are to co-design a dashboard that displays patient-reported outcomes along with other clinical data (eg, laboratory tests, medications, and appointments) within an electronic health record and conduct a longitudinal demonstration trial to evaluate whether the dashboard is associated with improved shared decision-making and disease management outcomes.

METHODS

Co-design teams comprising study investigators, patients with advanced cancer or chronic kidney disease, their care partners, and their clinicians will collaborate to develop the dashboard. Investigators will work with clinic staff to implement the co-designed dashboard for clinical testing during a demonstration trial. The primary outcome of the demonstration trial is whether the quality of shared decision-making increases from baseline to the 3-month follow-up. Secondary outcomes include longitudinal changes in satisfaction with care, self-efficacy in managing treatments and symptoms, health-related quality of life, and use of costly and potentially avoidable health care services. Implementation outcomes (ie, fidelity, appropriateness, acceptability, feasibility, reach, adoption, and sustainability) during the co-design process and demonstration trial will also be collected and summarized.

RESULTS

The dashboard co-design process was completed in May 2020, and data collection for the demonstration trial is anticipated to be completed by the end of July 2022. The results will be disseminated in at least one manuscript per study objective.

CONCLUSIONS

This protocol combines stakeholder engagement, health care coproduction frameworks, and health IT to develop a clinically feasible model of person-centered care delivery. The results will inform our current understanding of how best to integrate patient-reported outcome measures into clinical workflows to improve outcomes and reduce the burden of chronic disease on patients and health care systems.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/38461.

Individual differences in the dietary response to stress in ecological momentary assessment: Does the individual-difference model need expansion?

According to the individual-difference model, individuals differ in the way stress changes their eating behaviour. Research shows that some increase, some decrease, and others show no change in food intake. Despite numerous efforts to identify moderating variables that explain these individual (i.e., between-person) differences, evidence remains inconclusive. The present study aims at deepening the understanding of the stress and eating relationship by applying ecological momentary assessment to study (1) the influence of stress on whether and how much individuals eat and (2) the moderating role of gender, age, BMI, trait stress-eating, and eating styles. The APPetite-mobile-app was used for 3 days to capture actual food intake (event-contingent) and perceived stress (signal-contingent). Data of 154 healthy adults suggest that stress is not associated with whether but how much individuals eat. Only gender moderated the relationship between stress and the amount of food intake. Individual differences were small indicating that an individual's dietary response to stress might not be as stable as yet assumed. Moreover, a study suggests that time-varying factors (e.g., food availability) moderate the stress and eating relationship. Hence, intraindividual (i.e., within-person) variability may be relevant. Therefore, we propose an expansion of the individual-difference model, which accounts for time-varying factors.

Estradiol during (analogue-)trauma: Risk- or protective factor for intrusive re-experiencing?

Intrusions, a key symptom of posttraumatic stress disorder (PTSD), can occur in the form of images but also as pain sensations. Similar to audiovisual intrusions, the frequency and persistence of pain intrusions varies greatly between individuals. In the current study, we examined whether peritraumatic circulating 17β-estradiol (E2) levels are a biologic factor associated with subsequent audiovisual (i.e., film) and pain intrusion development, and whether peritraumatic stress levels modulate this relationship. Forty-one free-cycling women participated in an ecologically informed trauma-pain-conditioning (TPC) paradigm, using trauma-films and pain as unconditioned stimuli. Independent variables were salivary peritraumatic E2 levels and stress indexed by salivary cortisol and self-reported state-anxiety during TPC. Outcomes were film- and pain-intrusions occurring during daily-life in the week following TPC and a Memory-Triggering-Task in response to conditioned stimuli 24 h after TPC. In the week after analogue-trauma, higher peritraumatic E2 levels were associated with a greater probability of experiencing film-intrusions in the beginning of the week, which switched to a lower probability toward the end of the week. This time-dependent relationship between E2 and film-intrusions only held for higher state-anxious women. In contrast, results indicated a consistent inverse relationship between peritraumatic E2 levels and pain-intrusions during daily-life and Memory-Triggering-Task. Together, these data suggest that higher peritraumatic E2 levels could be associated with lower long-term visual trauma intrusions, as well as lower pain-intrusions, and thereby possibly constitute a protective biologic factor for PTSD and potentially also for chronic pain.

Overnight fasting affects avoidance learning and relief

OBJECTIVES

prolonged fasting influences threat and reward processing, two fundamental systems underpinning adaptive behaviors. In animals, overnight fasting sensitizes the mesolimbic-dopaminergic activity governing avoidance, reward, and fearextinction learning. Despite evidence that overnight fasting may also affect reward and fear learning in humans, effects on human avoidance learning have not been studied yet. Here, we examined the effects of 16 h-overnight fasting on instrumental avoidance and relief from threat omission.

METHODS

to this end, 50 healthy women were randomly assigned to a Fasting (N = 25) or a Re-feeding group (N = 25) and performed an Avoidance-Relief Task.

RESULTS

we found that fasting decreases unnecessary avoidance during signaled safety; this effect was mediated via a reduction in relief pleasantness during signaled absence of threat. A fasting-induced reduction in relief was also found during fear extinction learning.

DISCUSSION

we conclude that fasting optimizes avoidance and safety learning. Future studies should test whether these effects also hold for anxious individuals.

Assessing adult physical activity and compliance with 2008 CDC guidelines using a Bayesian two-part measurement error model

While there is wide agreement that physical activity is an important component of a healthy lifestyle, it is unclear how many people adhere to public health recommendations on physical activity. The Physical Activity Guidelines (PAG), published by the CDC, provides guidelines to American adults, but it is difficult to assess compliance with these guidelines. The PAG further complicates adherence assessment by recommending activity to occur in at least 10 min bouts. To better understand the measurement capabilities of various instruments to quantify activity, and to propose an approach to evaluate activity relative to the PAG, researchers at Iowa State University administered the Physical Activity Measurement Survey (PAMS) to over 1000 participants in four different Iowa counties. In this paper, we develop a two-part Bayesian measurement error model and apply it to the PAMS data in order to assess compliance with the PAG in the Iowa adult population. The model accurately accounts for the 10 min bout requirement put forth in the PAG. The measurement error model corrects biased estimates and accounts for day-to-day variation in activity. The model is also applied to the nationally representative National Health and Nutrition Examination Survey.

The relationship between moderate to vigorous physical activity and metabolic syndrome: a Bayesian measurement error approach

Metabolic Syndrome (MetS) is a serious condition that can be an early warning sign of heart disease and Type 2 diabetes. MetS is characterized by having elevated levels of blood pressure, cholesterol, waist circumference, and fasting glucose. There are many articles in the literature exploring the relationship between physical activity and MetS, but most do not consider the measurement error in the physical activity measurements nor the correlations among the MetS risk factors. Furthermore, previous work has generally treated MetS as binary, rather than directly modeling the risk factors on their measured, continuous space. Using data from the National Health and Nutrition Examination Survey (NHANES), we explore the relationship between minutes of moderate to vigorous physical activity (MVPA) and MetS risk factors. We construct a measurement error model for the accelerometry data, and then model its relationship between MetS risk factors with nonlinear seemingly unrelated regressions, incorporating dependence among MetS risk factors. The novel features of this model give the medical research community a new way to understand relationships between MVPA and MetS. The results of this approach present the field with a different modeling perspective than previously taken and suggest future avenues of scientific discovery.

Low Meat Consumption in the Netherlands Is Associated With Higher Intake of Fish, Nuts, Seeds, Cheese, Sweets, and Snacks: Results From a Two-Part Model

Studies on sustainable diets show a need for replacement of animal-based foods by plant-based foods, which is also called "the protein transition." To gain insight into the acceptability of such diet shifts, this study evaluated which current food sources people consume at varying amounts of meat consumption. The study population consisted of 4,313 participants aged 1-79 years of the Dutch National Food Consumption Survey 2012-2016, which assessed diet using two nonconsecutive 24-h dietary recalls. A two-part statistical model was used that accounts for both repeated measures and the correlation between probability and amount of consumption. Results are presented for quartiles of low to high meat consumption, by age and sex. Depending on age and sex, a higher consumption of fish (>100%), nuts and seeds (73-156%), cheese (34-111%), and sweets and snacks (28-81%) is observed in the lowest quartile of meat consumption compared to the highest. For fish, nuts, seeds, and cheese, this increase is mainly due to probability of consumption (>100%, 61-93%, and 16-64%, respectively). For sweets and snacks, the increase is mainly due to the amount of consumption (26-72%). Probability of potato consumption is 29-51% lower at low meat consumption. Vegetable consumption is lower mainly due to amount of consumption (6-29%). The results from the two-part model suggest that shifting away from a traditional Dutch high meat-vegetable-potatoes pattern is associated with higher probability of consuming fish, nuts and seeds, and cheese, but also increased amounts of sweets and snacks. This illustrates that analyzing the probability and amount part separately in relation to behavioral or physiological determinants extends our understanding of the diet according to meat consumption. These insights are important when developing realistic and acceptable food-based dietary guidelines for meat reduction.

Two-part joint model for a longitudinal semicontinuous marker and a terminal event with application to metastatic colorectal cancer data

Joint models for a longitudinal biomarker and a terminal event have gained interests for evaluating cancer clinical trials because the tumor evolution reflects directly the state of the disease. A biomarker characterizing the tumor size evolution over time can be highly informative for assessing treatment options and could be taken into account in addition to the survival time. The biomarker often has a semicontinuous distribution, i.e., it is zero inflated and right skewed. An appropriate model is needed for the longitudinal biomarker as well as an association structure with the survival outcome. In this article, we propose a joint model for a longitudinal semicontinuous biomarker and a survival time. The semicontinuous nature of the longitudinal biomarker is specified by a two-part model, which splits its distribution into a binary outcome (first part) represented by the positive versus zero values and a continuous outcome (second part) with the positive values only. Survival times are modeled with a proportional hazards model for which we propose three association structures with the biomarker. Our simulation studies show some bias can arise in the parameter estimates when the semicontinuous nature of the biomarker is ignored, assuming the true model is a two-part model. An application to advanced metastatic colorectal cancer data from the GERCOR study is performed where our two-part model is compared to one-part joint models. Our results show that treatment arm B (FOLFOX6/FOLFIRI) is associated to higher SLD values over time and its positive association with the terminal event leads to an increased risk of death compared to treatment arm A (FOLFIRI/FOLFOX6).

A mixed-effects two-part model for twin-data and an application on identifying important factors associated with extremely preterm children's health disorders

Our recent studies identifying factors significantly associated with the positive child health index (PCHI) in a mixed cohort of preterm-born singletons, twins, and triplets posed some analytic and modeling challenges. The PCHI transforms the total number of health disorders experienced (of the eleven ascertained) to a scale from 0 to 100%. While some of the children had none of the eleven health disorders (i.e., PCHI = 1), others experienced a subset or all (i.e., 0 ≤PCHI< 1). This indicates the existence of two distinct data processes-one for the healthy children, and another for those with at least one health disorder, necessitating a two-part model to accommodate both. Further, the scores for twins and triplets are potentially correlated since these children share similar genetics and early environments. The existing approach for analyzing PCHI data dichotomizes the data (i.e., number of health disorders) and uses a mixed-effects logistic or multiple logistic regression to model the binary feature of the PCHI (1 vs. < 1). To provide an alternate analytic framework, in this study we jointly model the two data processes under a mixed-effects two-part model framework that accounts for the sample correlations between and within the two data processes. The proposed method increases power to detect factors associated with disorders. Extensive numerical studies demonstrate that the proposed joint-test procedure consistently outperforms the existing method when the type I error is controlled at the same level. Our numerical studies also show that the proposed method is robust to model misspecifications and it is applicable to a set of correlated semi-continuous data.

Bayesian Copula Density Deconvolution for Zero-Inflated Data in Nutritional Epidemiology

Estimating the marginal and joint densities of the long-term average intakes of different dietary components is an important problem in nutritional epidemiology. Since these variables cannot be directly measured, data are usually collected in the form of 24-hour recalls of the intakes, which show marked patterns of conditional heteroscedasticity. Significantly compounding the challenges, the recalls for episodically consumed dietary components also include exact zeros. The problem of estimating the density of the latent long-time intakes from their observed measurement error contaminated proxies is then a problem of deconvolution of densities with zero-inflated data. We propose a Bayesian semiparametric solution to the problem, building on a novel hierarchical latent variable framework that translates the problem to one involving continuous surrogates only. Crucial to accommodating important aspects of the problem, we then design a copula based approach to model the involved joint distributions, adopting different modeling strategies for the marginals of the different dietary components. We design efficient Markov chain Monte Carlo algorithms for posterior inference and illustrate the efficacy of the proposed method through simulation experiments. Applied to our motivating nutritional epidemiology problems, compared to other approaches, our method provides more realistic estimates of the consumption patterns of episodically consumed dietary components.

A multiplicity of environmental, economic and social factor analyses to understand COVID-19 diffusion

Research on the impact of the environment on COVID-19 diffusion lacks a full-comprehensive perspective, and neglecting the multiplicity of the human-environment system can lead to misleading conclusions. We attempted to reveal all pre-existing environmental-to-human and human-to-human determinants that influence the transmission of COVID-19. As such, We estimated the daily case incidence ratios (CIR) of COVID-19 for prefectures across mainland China, and used a mixed-effects mixed-distribution model to study the association between the CIR and 114 factors related to climate, atmospheric environmental quality, terrain, population, economic, human mobility as well as non-pharmaceutical interventions (NPIs). Not only the changes in determinants over time as the pandemic progresses but also their lag and interaction effects were examined. CO, O3, PM10 and PM2.5 were found positively linked with CIR, but the effect of NO2 was negative. The temperature had no significant association with CIR, and the daily minimum humidity was a significant negatively predictor. NPIs' level was negatively associated with CIR until with a lag of 15 days. Higher accumulated destination migration scale flow from the epicenter and lower distance to the epicenter (DisWH) were associated with a higher CIR, however, the interaction between DisWH and the time was positive. The more economically developed and more densely populated cities have a higher probability of CIR occurrence, but they may not have a higher CIR intensity.The COVID-19 diffusion are caused by a multiplicity of environmental, economic, social factors as well as NPIs. First, multiple pollutants carried simultaneously on particulate matter affect COVID-19 transmission. Second, the temperature has a limited impact on the spread of the epidemic. Third, NPIs must last for at least 15 days or longer before the effect has been apparent. Fourth, the impact of population movement from the epicenter on COVID-19 gradually diminished over time and intraregional migration deserves more attention.

Bayesian analysis of two-part nonlinear latent variable model: Semiparametric method

Two-part model (TPM) is a widely appreciated statistical method for analyzing semi-continuous data. Semi-continuous data can be viewed as arising from two distinct stochastic processes: one governs the occurrence or binary part of data and the other determines the intensity or continuous part. In the regression setting with the semi-continuous outcome as functions of covariates, the binary part is commonly modelled via logistic regression and the continuous component via a log-normal model. The conventional TPM, still imposes assumptions such as log-normal distribution of the continuous part, with no unobserved heterogeneity among the response, and no collinearity among covariates, which are quite often unrealistic in practical applications. In this article, we develop a two-part nonlinear latent variable model (TPNLVM) with mixed multiple semi-continuous and continuous variables. The semi-continuous variables are treated as indicators of the latent factor analysis along with other manifest variables. This reduces the dimensionality of the regression model and alleviates the potential multicollinearity problems. Our TPNLVM can accommodate the nonlinear relationships among latent variables extracted from the factor analysis. To downweight the influence of distribution deviations and extreme observations, we develop a Bayesian semiparametric analysis procedure. The conventional parametric assumptions on the related distributions are relaxed and the Dirichlet process (DP) prior is used to improve model fitting. By taking advantage of the discreteness of DP, our method is effective in capturing the heterogeneity underlying population. Within the Bayesian paradigm, posterior inferences including parameters estimates and model assessment are carried out through Markov Chains Monte Carlo (MCMC) sampling method. To facilitate posterior sampling, we adapt the Polya-Gamma stochastic representation for the logistic model. Using simulation studies, we examine properties and merits of our proposed methods and illustrate our approach by evaluating the effect of treatment on cocaine use and examining whether the treatment effect is moderated by psychiatric problems.

Simultaneous modeling of detection rate and exposure concentration using semi-continuous models to identify exposure determinants when left-censored data may be a true zero

BACKGROUND

Most methods for treating left-censored data assume the analyte is present but not quantified. Biased estimates may result if the analyte is absent such that the unobserved data represents a mixed exposure distribution with an unknown proportion clustered at zero.

OBJECTIVE

We used semi-continuous models to identify time and industry trends in 52,457 OSHA inspection lead sample results.

METHOD

The first component of the semi-continuous model predicted the probability of detecting concentrations ≥ 0.007 mg/m³ (highest estimated detection limit, 62% of measurements). The second component predicted the median concentration of measurements ≥ 0.007 mg/m³. Both components included a random-effect for industry and fixed-effects for year, industry group, analytical method, and other variables. We used the two components together to predict median industry- and time-specific lead concentrations.

RESULTS

The probabilities of detectable concentrations and the median detected concentrations decreased with year; both were also lower for measurements analyzed for multiple (vs. one) metals and for those analyzed by inductively-coupled plasma (vs. atomic absorption spectroscopy). The covariance was 0.30 (standard error = 0.06), confirming the two components were correlated.

SIGNIFICANCE

We identified determinants of exposure in data with over 60% left-censored, while accounting for correlated relationships and without assuming a distribution for the censored data.

Studying dietary intake in daily life through multilevel two-part modelling: a novel analytical approach and its practical application

BACKGROUND

Understanding which factors influence dietary intake, particularly in daily life, is crucial given the impact diet has on physical as well as mental health. However, a factor might influence whether but not how much an individual eats and vice versa or a factor's importance may differ across these two facets. Distinguishing between these two facets, hence, studying dietary intake as a dual process is conceptually promising and not only allows further insights, but also solves a statistical issue. When assessing the association between a predictor (e.g. momentary affect) and subsequent dietary intake in daily life through ecological momentary assessment (EMA), the outcome variable (e.g. energy intake within a predefined time-interval) is semicontinuous. That is, one part is equal to zero (i.e. no dietary intake occurred) and the other contains right-skewed positive values (i.e. dietary intake occurred, but often only small amounts are consumed). However, linear multilevel modelling which is commonly used for EMA data to account for repeated measures within individuals cannot be applied to semicontinuous outcomes. A highly informative statistical approach for semicontinuous outcomes is multilevel two-part modelling which treats the outcome as generated by a dual process, combining a multilevel logistic/probit regression for zeros and a multilevel (generalized) linear regression for nonzero values.

METHODS

A multilevel two-part model combining a multilevel logistic regression to predict whether an individual eats and a multilevel gamma regression to predict how much is eaten, if an individual eats, is proposed. Its general implementation in R, a widely used and freely available statistical software, using the R-package brms is described. To illustrate its practical application, the analytical approach is applied exemplary to data from the Eat2beNICE-APPetite-study.

RESULTS

Results highlight that the proposed multilevel two-part model reveals process-specific associations which cannot be detected through traditional multilevel modelling.

CONCLUSIONS

This paper is the first to introduce multilevel two-part modelling as a novel analytical approach to study dietary intake in daily life. Studying dietary intake through multilevel two-part modelling is conceptually as well as methodologically promising. Findings can be translated to tailored nutritional interventions targeting either the occurrence or the amount of dietary intake.

Joint modeling of longitudinal data with informative cluster size adjusted for zero-inflation and a dependent terminal event

Repeated measures are often collected in longitudinal follow-up from clinical trials and observational studies. In many situations, these measures are adherent to some specific event and are only available when it occurs; an example is serum creatinine from laboratory tests for hospitalized acute kidney injuries. The frequency of event recurrences is potentially correlated with overall health condition and hence may influence the distribution of the outcome measure of interest, leading to informative cluster size. In particular, there may be a large portion of subjects without any events, thus no longitudinal measures are available, which may be due to insusceptibility to such events or censoring before any events, and this zero-inflation nature of the data needs to be taken into account. On the other hand, there often exists a terminal event that may be correlated with the recurrent events. Previous work in this area suffered from the limitation that not all these issues were handled simultaneously. To address this deficiency, we propose a novel joint modeling approach for longitudinal data adjusting for zero-inflated and informative cluster size as well as a terminal event. A three-stage semiparametric likelihood-based approach is applied for parameter estimation and inference. Extensive simulations are conducted to evaluate the performance of our proposal. Finally, we utilize the Assessment, Serial Evaluation, and Subsequent Sequelae of Acute Kidney Injury (ASSESS-AKI) study for illustration.

Desensitization to Fear-Inducing COVID-19 Health News on Twitter: Observational Study

Background

As of May 9, 2021, the United States had 32.7 million confirmed cases of COVID-19 (20.7% of confirmed cases worldwide) and 580,000 deaths (17.7% of deaths worldwide). Early on in the pandemic, widespread social, financial, and mental insecurities led to extreme and irrational coping behaviors, such as panic buying. However, despite the consistent spread of COVID-19 transmission, the public began to violate public safety measures as the pandemic got worse.

Objective

In this work, we examine the effect of fear-inducing news articles on people’s expression of anxiety on Twitter. Additionally, we investigate desensitization to fear-inducing health news over time, despite the steadily rising COVID-19 death toll.

Methods

This study examined the anxiety levels in news articles (n=1465) and corresponding user tweets containing “COVID,” “COVID-19,” “pandemic,” and “coronavirus” over 11 months, then correlated that information with the death toll of COVID-19 in the United States.

Results

Overall, tweets that shared links to anxious articles were more likely to be anxious (odds ratio [OR] 2.65, 95% CI 1.58-4.43, P<.001). These odds decreased (OR 0.41, 95% CI 0.2-0.83, P=.01) when the death toll reached the third quartile and fourth quartile (OR 0.42, 95% CI 0.21-0.85, P=.01). However, user tweet anxiety rose rapidly with articles when the death toll was low and then decreased in the third quartile of deaths (OR 0.61, 95% CI 0.37-1.01, P=.06). As predicted, in addition to the increasing death toll being matched by a lower level of article anxiety, the extent to which article anxiety elicited user tweet anxiety decreased when the death count reached the second quartile.

Conclusions

The level of anxiety in users’ tweets increased sharply in response to article anxiety early on in the COVID-19 pandemic, but as the casualty count climbed, news articles seemingly lost their ability to elicit anxiety among readers. Desensitization offers an explanation for why the increased threat is not eliciting widespread behavioral compliance with guidance from public health officials. This work investigated how individuals' emotional reactions to news of the COVID-19 pandemic manifest as the death toll increases. Findings suggest individuals became desensitized to the increased COVID-19 threat and their emotional responses were blunted over time.

Intrusive memories as conditioned responses to trauma cues: An empirically supported concept?

Intrusions in posttraumatic stress disorder (PTSD) are clinically understood as conditioned responses (CRs) to trauma-cues; however, experimental evidence for this is limited. We subjected 84 healthy participants to a differential conditioned-intrusion paradigm, where neutral faces served as conditioned stimuli (CSs) and aversive film clips as unconditioned stimuli (USs). While one group only completed acquisition, another group additionally received extinction. Subsequently, participants provided detailed e-diary intrusion reports. Several key findings emerged: First, participants in both groups re-experienced not only USs but also CSs as content of their intrusions. Second, intrusions were elicited by cues resembling CSs, USs, and experimental context. Third, extinction reduced probability and severity of US intrusions, and accelerated their decay, and this was particularly the case in participants showing greater cognitive (US-expectancy) and physiological (SCR) differential responding to CS+ vs. CS- at end of acquisition (i.e., conditionability). Similarly, extinction reduced CS-intrusion probability and severity, but only in participants with greater cognitive conditionability. These results support conditioning's role in re-experiencing in two critical ways: (1) Conditioning during trauma provides cues that not only function as reminder cues, but also as content of intrusions; (2) After strong conditioning, weakening the original CS-US relationship via extinction reduces intrusion formation after analogue-trauma.

Nonparametric Bayesian functional two-part random effects model for longitudinal semicontinuous data analysis

Longitudinal semicontinuous data, characterized by repeated measures of a large portion of zeros and continuous positive values, are frequently encountered in many applications including biomedical, epidemiological, and social science studies. Two-part random effects models (TPREM) have been used to investigate the association between such longitudinal semicontinuous data and covariates accounting for the within-subject correlation. The existing TPREM is, however, limited to incorporate a functional covariate, which is often available in a longitudinal study. Moreover, the existing TPREM typically assumes the normality of subject-specific random effects, which can be easily violated when there exists a subgroup structure. In this article, we propose a nonparametric Bayesian functional TPREM to assess the relationship between the longitudinal semicontinuous outcome and various types of covariates including a functional covariate. The proposed model also relaxes the normality assumption for the random effects through a Dirichlet process mixture of normals, which allows for identifying an underlying subgroup structure. The methodology is illustrated through an application to social insurance expenditure data collected by the Korean Welfare Panel Study and a simulation study.

Diet, Nutrition, Obesity, and Their Implications for COVID-19 Mortality: Development of a Marginalized Two-Part Model for Semicontinuous Data

Background

Nutrition is not a treatment for COVID-19, but it is a modifiable contributor to the development of chronic disease, which is highly associated with COVID-19 severe illness and deaths. A well-balanced diet and healthy patterns of eating strengthen the immune system, improve immunometabolism, and reduce the risk of chronic disease and infectious diseases.

Objective

This study aims to assess the effect of diet, nutrition, obesity, and their implications for COVID-19 mortality among 188 countries by using new statistical marginalized two-part models.

Methods

We globally evaluated the distribution of diet and nutrition at the national level while considering the variations between different World Health Organization regions. The effects of food supply categories and obesity on (as well as associations with) the number of deaths and the number of recoveries were reported globally by estimating coefficients and conducting color maps.

Results

The findings show that a 1% increase in supplementation of pulses reduced the odds of having a zero death by 4-fold (OR 4.12, 95% CI 11.97-1.42). In addition, a 1% increase in supplementation of animal products and meat increased the odds of having a zero death by 1.076-fold (OR 1.076, 95% CI 1.01-1.15) and 1.13-fold (OR 1.13, 95% CI 1.0-1.28), respectively. Tree nuts reduced the odds of having a zero death, and vegetables increased the number of deaths. Globally, the results also showed that populations (countries) who consume more eggs, cereals excluding beer, spices, and stimulants had the greatest impact on the recovery of patients with COVID-19. In addition, populations that consume more meat, vegetal products, sugar and sweeteners, sugar crops, animal fats, and animal products were associated with more death and less recoveries in patients. The effect of consuming sugar products on mortality was considerable, and obesity has affected increased death rates and reduced recovery rates.

Conclusions

Although there are differences in dietary patterns, overall, unbalanced diets are a health threat across the world and not only affect death rates but also the quality of life. To achieve the best results in preventing nutrition-related pandemic diseases, strategies and policies should fully recognize the essential role of both diet and obesity in determining good nutrition and optimal health. Policies and programs must address the need for change at the individual level and make modifications in society and the environment to make healthier choices accessible and preferable.

An imputation approach for fitting two-part mixed effects models for longitudinal semi-continuous data

Two-part mixed effects models are often used for analyzing longitudinal data with many zeros. Typically, these models are formulated with binary and continuous components separately with random effects that are correlated between the two components. Researchers have developed maximum-likelihood and Bayesian approaches for fitting these models that often require using particular software packages or very specialized software. We propose an imputation approach that will allow practitioners to separately use standard linear and generalized linear mixed models to estimate the fixed effects for two-part mixed effects models with complex random effects structures. An approximation to the conditional distribution of positive measurements given an individual's pattern of non-zero measurements is proposed that can be easily estimated and then imputed from. We show that for a wide range of parameter values, the imputation approach results in nearly unbiased estimation and can be implemented with standard software. We illustrate the proposed imputation approach for the analysis of longitudinal clinical trial data with many zeros.

Best (but oft-forgotten) practices: sample size and power calculation for a dietary intervention trial with episodically consumed foods

Dietary interventions often target foods that are underconsumed relative to dietary guidelines, such as vegetables, fruits, and whole grains. Because these foods are only consumed episodically for some participants, data from such a study often contains a disproportionally large number of zeros due to study participants who do not consume any of the target foods on the days that dietary intake is assessed, thus generating semicontinuous data. These zeros need to be properly accounted for when calculating sample sizes to ensure that the study is adequately powered to detect a meaningful intervention effect size. Nonetheless, this issue has not been well addressed in the literature. Instead, methods that are common for continuous outcomes are typically used to compute the sample sizes, resulting in a substantially under- or overpowered study. We propose proper approaches to calculating the sample size needed for dietary intervention studies that target episodically consumed foods. Sample size formulae are derived for detecting the mean difference in the amount of intake of an episodically consumed food between an intervention and a control group. Numerical studies are conducted to investigate the accuracy of the sample size formulae as compared with the ad hoc methods. The simulation results show that the proposed formulae are appropriate for estimating the sample sizes needed to achieve the desired power for the study. The proposed method for sample size is recommended for designing dietary intervention studies targeting episodically consumed foods.

Evaluating the effect of Coriandrum sativum syrup on being migraine-free using mixture models

Background:Coriandrum sativum (coriander) is prescribed as a treatment for headache in traditional Persian medicine. Several investigations have been carried out to find the medicinal properties of this plant. However, no study has evaluated the effectiveness of this plant on becoming migraine-free.

Methods: Sixty-eight migraineurs were randomly allocated to two equal groups of intervention and control . Each received 500 mg of sodium valproate in addition to 15 mL of coriander or placebo syrup three times a day. We followed subjects and recorded their migraine duration in the 1^st, 2^nd, 3^rd, and 4^th weeks. We applied an appropriate statistical model so as to consider special features of the data, which led to more accurate results using SAS 9.4

Results: Our findings showed that the probability of being migraine-free was not only considerably higher in final weeks of the study (p<0.001) in all patients of the intervention group than placebo group, but it was also significantly higher in patients less than 30 years of age compared to patients older than 30 years old. Migraine duration in migraineurs using coriander syrup reduced considerably during the study (p<0.001).

Conclusion: The finding of this study revealed that coriander has a significant effect both on the probability of being migraine free and the duration of migraine attacks. Its effects were more significant during the final weeks of study.

Intravenous vs Oral Acetaminophen for Analgesia After Cesarean Delivery: A Randomized Trial

OBJECTIVE

Examination of postoperative analgesia with intravenous and oral acetaminophen.

DESIGN

Prospective, three-arm, nonblinded, randomized clinical trial.

SETTING

A single academic medical center.

SUBJECTS

Parturients scheduled for elective cesarean delivery.

METHODS

This trial randomized 141 parturients to receive intravenous acetaminophen (1 g every eight hours, three doses), oral acetaminophen (1 g every eight hours, three doses), or no acetaminophen. All patients received a standardized neuraxial anesthetic with intrathecal opioids and scheduled postoperative ketorolac. The primary outcome, 24-hour opioid consumption, was evaluated using the Kruskal-Wallace test and Tukey-Kramer adjustment for multiple comparisons. Secondary outcomes included 48-hour opioid consumption, first opioid rescue, pain scores, patient satisfaction, times to ambulation and discharge, and side effects.

RESULTS

Over 18 months, 141 parturients with similar demographic variables completed the study. Median (interquartile range) opioid consumption in intravenous morphine milligram equivalents at 24 hours was 0 (5), 0 (7), and 5 (7) for the intravenous, oral, and no groups, respectively, and differed between groups (global P = 0.017). Opioid consumption and other secondary outcomes did not differ between the intravenous vs oral or oral vs no groups. Opioid consumption was reduced at 24 hours with intravenous vs no acetaminophen (P = 0.015). Patients receiving no acetaminophen had 5.8 times the odds of consuming opioids (P = 0.036), consumed 40% more opioids controlling for time (P = 0.041), and had higher pain scores with ambulation (P = 0.004) compared with the intravenous group.

CONCLUSIONS

Intravenous acetaminophen did not reduce 24-hour opioid consumption or other outcomes compared with oral acetaminophen. Intravenous acetaminophen did decrease opioid consumption and pain scores compared with no acetaminophen.

Semiparametric Estimation of the Distribution of Episodically Consumed Foods Measured With Error

Dietary data collected from 24-hour dietary recalls are observed with significant measurement errors. In the nonparametric curve estimation literature, much of the effort has been devoted to designing methods that are consistent under contamination by noise, and which have been traditionally applied for analyzing those data. However, some foods such as alcohol or fruits are consumed only episodically, and may not be consumed during the day when the 24-hour recall is administered. These so-called excess zeros make existing nonparametric estimators break down, and new techniques need to be developed for such data. We develop two new consistent semiparametric estimators of the distribution of such episodically consumed food data, making parametric assumptions only on some less important parts of the model. We establish its theoretical properties and illustrate the good performance of our fully data-driven method in simulated and real data. Supplementary materials for this article are available online.

Diet Quality and Associations with Food Security among Women Eligible for Indiana Supplemental Nutrition Assistance Program-Education

BACKGROUND

The diet quality among adults receiving nutrition education lessons through Supplemental Nutrition Assistance Program-Education (SNAP-Ed) is currently unknown.

OBJECTIVES

The objectives of this study were to characterize the diet quality of Indiana SNAP-Ed-eligible women; estimate their mean usual intake of fruits, vegetables, dairy, and whole grains compared to Dietary Guidelines for Americans (DGA) recommendations; and determine if these dietary outcomes differed by food security status.

METHODS

SNAP-Ed paraprofessionals recruited participants from August 2015 to May 2016 for this secondary analysis of cross-sectional data collected as the baseline assessment for a randomized controlled trial. Participants were SNAP-Ed-eligible women aged ≥18 y interested in nutrition education lessons. Dietary outcomes were assessed by one or two 24-h dietary recalls. The Healthy Eating Index (HEI)-2010 was used to characterize diet quality. Mean usual intake of food groups was estimated using the National Cancer Institute Method. Food security status was classified using the US Household Food Security Survey Module. Data were analyzed in October 2019.

RESULTS

Mean ± SEM HEI-2010 total score was 42 ± 0.9 for the study sample. Mean ± SE usual intake of servings of fruits (0.61 ± 0.08 cups [144.32 ± 18.93 mL]), vegetables [1.4 ± 0.10 cups (331.2 ± 23.66 mL)], dairy [1.5 ± 0.11 cups (354.88 ± 26.02 mL)], and whole grains [0.48 ± 0.06 ounces (13.61 ± 1.70 g)] did not differ by food security subgroup. Mean HEI-2010 total score was significantly higher by 4.8 ± 2.0 points for the food-secure than for the food-insecure subgroup (P = 0.01). Mean HEI-2010 component scores were 1.1 ± 0.5 points higher for whole grain (P = 0.01) and 1.0 ± 0.5 points higher for dairy (P = 0.05) in the food-secure than in the food-insecure subgroup. The proportions of the study sample not meeting the DGA recommendations for food group intake were ≥85% for both food-secure and -insecure subgroups.

CONCLUSIONS

Indiana SNAP-Ed-eligible women reported poor diet quality, highlighting their need for nutrition interventions aiming to improve food security and diet as per DGA recommendations in low-income populations.

Bayesian profiling for cost with zeros to decompose total cost into probability of cost and mean nonzero cost

Cost of health care can vary substantially across hospitals, centers, or providers. Data from electronic health records provide information for studying patterns of cost variation and identifying high or low cost centers. Cost data often include zero values when patients receive no care, and joint two-part models have been developed for clustered cost data with zeros. Standard methods for center comparisons, sometimes called profiling, can use these methods to incorporate zero values into total cost. However, zero costs also provide opportunities to further examine sources of cost variation and outliers. For example, a hospital may have high (or low) cost due to frequency of nonzero cost, amount of nonzero cost, or a combination of those. We give methods for decomposing hospital differences in total cost with zeros into components for probability of use (i.e., of nonzero cost) and for cost of use (mean of nonzero cost). The components multiply to total cost and quantify components on the same easily interpreted multiplicative scales. The methods are based on Bayesian hierarchical models and counterfactual arguments, with Markov chain Monte Carlo estimation. We used simulated data to illustrate use, interpretation, and visualization of the methods in diverse situations, and applied the methods to 30,024 patients at 57 US Veterans Administration hospitals to characterize outlier hospitals in one year cost of inpatient care following a cardiac procedure. Twenty eight percent of patients had zero cost. These methods are useful in providing insight into cost variation and outliers for planning future studies or interventions.

Association Between Supplemental Private Health Insurance and Burden of Out-of-Pocket Healthcare Expenditure in China: A Novel Approach to Estimate Two-Part Model with Random Effects Using Panel Data

Introduction

Private health insurance (PHI) is an important supplement to the basic health insurance schemes in the Chinese healthcare system. However, there is an absence of evidence on whether the strategy of engaging PHI to reduce burden is effective in China. As such, we aimed to investigate the association between supplemental PHI and the out-of-pocket (OOP) burden of household healthcare expenditure in China.

Methods

We conducted a panel data analysis using data from three waves of China Health and Retirement Longitudinal Study (CHARLS). Specifically, a two-part model (TPM) with a first-stage probit and second-stage generalized linear model (GLM) framework was used to analyze the data. To account for individual-level random effects in both stages and their correlation in the TPM analysis, we proposed a generalized structural equation modeling (GSEM) approach to implement the estimation. The proposed approach allowed us to simultaneously analyze the association of PHI with the probability of having any healthcare and the OOP burden conditional on having any healthcare expenditure.

Results

Using the GSEM estimates, we found that supplemental PHI was significantly associated with a higher probability (4.29 percentage points) of having any OOP healthcare expenditure but a lower OOP burden conditional on having any expenditure (−2.37 percentage points). Overall, supplemental PHI was insignificantly associated with a lower OOP burden (−1.05 percentage points).

Discussion

Our findings suggested that supplemental PHI in China may be able to effectively improve access to healthcare while keeping the OOP healthcare expenditure burden flat. Also, GSEM is a feasible method to estimate random-effect TPMs.

A two-part mixed-effects model for analyzing clustered time-to-event data with clumping at zero

BACKGROUND AND OBJECTIVE

In longitudinal epidemiological studies consisting of a baseline stage and a follow-up stage, observations at the baseline stage may contain a countable proportion of negative responses. The time-to-event outcomes of those observations corresponding to negative responses at baseline can be denoted as zeros, which are excluded from standard survival analysis. Consequently, some important information on these subjects is therefore lost in the analysis. Furthermore, subjects are often clustered within hospitals, communities or health service centers, resulting in correlated observations. The framework of the two-part model has been developed and utilized widely to analyze semi-continuous data or count data with excess zeros, but its application to clustered time-to-event data with clumping at zero remains sparse.

METHODS

A two-part mixed-effects modeling approach was proposed. A logistic mixed-effects regression model was used in the first part to determine factors associated with the prevalence of the baseline event of interest. Parametric frailty models (including Weibull, exponential, log-logistic and log-normal) were used in the second part to assess associations between exposures and time-to-event outcomes. Correlated random effects were incorporated within the two regression models to accommodate the inherent correlation within each clustering unit and the correlation between the two parts. As an illustrative example, the method was applied to exclusive breastfeeding data from a community-based prospective cohort study in Nepal.

RESULTS

A significantly positive correlation between the baseline prevalence of exclusive breastfeeding and exclusive breastfeeding duration was confirmed (ρ = 0.67, P < 0.001). The correlated two-part model outperformed the independent two-part model (likelihood ratio test statistic = 8.6, df = 1, P = 0.003).

CONCLUSIONS

The proposed approach makes full use of all available information at baseline and during the follow-up, compared to the conventional survival analysis. In addition to breastfeeding studies, the method can be applied to other research areas where clustered time-to-event data with clumping at zero arise.

Two-part mixed-effects location scale models

Longitudinal time use data afford the opportunity to study within- and between-individual differences, but can present challenges in data analysis. Often the response set includes a large number of zeros representing those who did not engage in the target behavior. Coupled with this is a continuous measure of time use for those who did engage. The latter is strictly positive and skewed to the right if relatively few individuals engage in the behavior to a greater extent. Data analysis is further complicated for repeated measures, because within-individual responses are typically correlated, and some respondents may have missing data. This combination of zeros and positive responses is characteristic of a type of semicontinuous data in which the response is equal to a discrete value and is otherwise continuous. Two-part models have been successfully applied to cross-sectional time use data when the research goals distinguish between a respondent's likelihood to engage in a behavior and the time spent conditional on any time being spent, as these models allow different covariates to relate to each distinct aspect of a behavior. Two-part mixed-effects models extend two-part models for analysis of longitudinal semicontinuous data to simultaneously address longitudinal decisions to engage in a behavior and time spent conditional on any time spent. Heterogeneity between and within individuals can be studied in unique ways. This paper presents applications of these models to daily diary data to study individual differences in time spent relaxing or engaged in leisure activities for an adult sample.

Does point-of-sale nutrition information improve the nutritional quality of food choices?

Point-of-sale nutrition information has been adopted by numerous grocery stores to respond to the demand for easy-to-understand nutrition labeling by consumers. Although there is conflicting evidence regarding the effectiveness of providing nutrition information, previous research indicates simplified shelf nutrition labels may lead to healthier choices. However, these studies have not examined how different consumer segments respond to these labels, nor the differential impacts across foods. Using household purchase data from a store that voluntarily adopted the (now defunct) NuVal shelf nutrition labels (a 1-100 numeric score derived from a nutrition-profiling algorithm), we assess NuVal impacts across different consumers and foods. NuVal scores potentially influence not only purchase quantity but also likelihood of buying. Thus, the effect of NuVal was measured by estimating a two-part model and predicting consumers' unconditional purchase responses. We found evidence of heterogeneous impacts of NuVal across consumers and foods. High-income households and households with children shifted their yogurt and frozen dinner purchases to more healthful items. In contrast, households with children and households headed by heads with college education slightly shifted their canned soup purchases to less healthful options. Our findings suggest that specific foods and consumer segments are influenced by simplified shelf nutrition information and further research is necessary to better understand its effect on consumer dietary quality.

The use of stimulus perception to account for variability in skin conductance responses to interoceptive stimuli

Activity of the electrodermal response system is customarily expressed in relation to physical stimulus properties and not to perceived features. In situations where the delivery of physically identical stimuli can be challenging, such as in interoception research, this variability might pose a challenge for contemporary SCR analyses. Therefore, we investigated the extent to which activity in the electrodermal response system triggered by the delivery of interoceptive stimuli is better predicted by perceived intensity rather than physical input. For this purpose, we reanalyzed data from the baseline phase of a previous study (n = 60) in which skin conductance responses (SCRs) to innocuous esophageal stimulations of high and low intensities were recorded in addition to categorizations based on their perceived intensity (high or low). Using both peak scoring and model inversion methods, we found that the inclusion of stimulus perception as a predictor of the magnitude of the SCR increased model fit. These findings suggest that the inclusion of perception is a promising avenue to better model variability in psychophysiological responses to interoceptive stimuli.