Search

Compositional data are common in many fields, both as outcomes and predictor variables. The inventory of models for the case when both the outcome and predictor variables are compositional is limited, and the existing models are often difficult to interpret in the compositional space, due to their use of complex log‐ratio transformations. We develop a transformation‐free linear regression model where the expected value of the compositional outcome is expressed as a single Markov transition from the compositional predictor. Our approach is based on estimating equations thereby not requiring complete specification of data likelihood and is robust to different data‐generating mechanisms. Our model is simple to interpret, allows for 0s and 1s in both the compositional outcome and covariates, and subsumes several interesting subcases of interest. We also develop permutation tests for linear independence and equality of effect sizes of two components of the predictor. Finally, we show that despite its simplicity, our model accurately captures the relationship between compositional data using two datasets from education and medical research. [ABSTRACT FROM AUTHOR]

Abstract Background We sought to determine whether gender disparities exist in the prehospital management of chest pain (CP) or out-of-hospital cardiac arrest (OHCA) among patients who accessed the emergency medical services (EMS) system. Methods We obtained 2010–2013 data from the National Emergency Medical Services Information System and identified all EMS activations for CP or OHCA by adults 40 years of age or older. We selected American Heart Association medications and procedures to manage cardiovascular events. We stratified women and men by age (<65 years vs. ≥65 years), race (White vs. Black), clinical condition (CP vs. OHCA), same EMS agency, and calendar year. We determined the gender-specific treatment proportions for each stratum and calculated the weighted percentage difference in treatment between women and men. Results Approximately 2.4 million CP and 284,000 OHCA activations were analyzed. Women with CP received a lower percentage of recommended treatments than men. For every 100 EMS activations by women with CP, 2.8 fewer received aspirin (95% CI, −4.8 to −0.8). The greatest gap in CP care was that women were significantly less likely to be transported using lights and sirens than men (−4.6%; 95% CI, −8.7% to −0.5%). More than 90% of OHCA activations were resuscitated; however, women were significantly less likely to be resuscitated compared with men (−1.3%; 95% CI, −2.4% to −0.2%). Conclusions Small to modest disparities between otherwise similar women and men in the EMS treatment of CP and OHCA suggest the need for further evaluation and research with detailed contextual and outcome data. [ABSTRACT FROM AUTHOR]

Objectives Ectopic calcification (calcinosis) is a common complication of SSc, but a subset of SSc patients has a heavy burden of calcinosis. We examined whether there are unique risk factors for a heavy burden of calcinosis, as compared with a light burden or no calcinosis. Methods We reviewed the medical records of all patients in the Johns Hopkins Scleroderma Center Research Registry with calcinosis to quantify calcinosis burden using pre-specified definitions. We performed latent class analysis to identify SSc phenotypic classes. We used multinomial logistic regression to determine whether latent phenotypic classes and autoantibodies were independent risk factors for calcinosis burden. Results Of all patients, 29.4% (997/3388) had calcinosis, and 13.5% (130/963) of those with calcinosis had a heavy burden. The latent phenotypic class with predominantly diffuse skin disease and higher disease severity (characterized by pulmonary hypertension, interstitial lung disease, cardiomyopathy, severe RP, gastrointestinal involvement, renal crisis, myopathy and/or tendon friction rubs) was associated with an increased risk of both a heavy burden [odds ratio (OR) 6.92, 95% CI 3.66, 13.08; P  < 0.001] and a light burden (OR 2.88, 95% CI 2.11, 3.95; P  < 0.001) of calcinosis compared with the phenotypic class with predominantly limited skin disease. Autoantibodies to PM/Scl were strongly associated with a heavy burden of calcinosis (OR 17.31, 95% CI 7.72, 38.81; P  < 0.001) and to a lesser degree a light burden of calcinosis (OR 3.59, 95% CI 1.84, 7.00; P  < 0.001). Conclusions Calcinosis burden is associated with cumulative SSc-related tissue damage. Independent of disease severity, autoantibodies to PM/Scl are also associated with a heavy burden of calcinosis. [ABSTRACT FROM AUTHOR]

Background: Despite growing interest in monitoring improvements in quality of care, data on service quality in low-income and middle-income countries (LMICs) is limited. While health systems researchers have hypothesized the relationship between facility readiness and provision of care, there have been few attempts to quantify this relationship in LMICs. This study assesses the association between facility readiness and provision of care for antenatal care at the client level and facility level. Methods: To assess the association between provision of care and various facility readiness indices for antenatal care, we used multilevel, multivariable random-effects linear regression models. We tested an inflection point on readiness scores by fitting linear spline models. To compare the coefficients between models, we used a bootstrapping approach and calculated the mean difference between all pairwise comparisons. Analyses were conducted at client and facility levels. Results: Our results showed a small, but significant association between facility readiness and provision of care across countries and most index constructions. The association was most evident in the client-level analyses that had a larger sample size and were adjusted for factors at the facility, health worker, and individual levels. In addition, spline models at a facility readiness score of 50 better fit the data, indicating a plausible threshold effect. Conclusions: The results of this study suggest that facility readiness is not a proxy for provision of care, but that there is an important association between facility readiness and provision of care. Data on facility readiness is necessary for understanding the foundations of health systems particularly in countries with the lowest levels of service quality. However, a comprehensive view of quality of care should include both facility readiness and provision of care measures. [ABSTRACT FROM AUTHOR]

Background Active surveillance (AS) is an alternative to curative intervention, but overtreatment persists. Imperfect alignment of prostate biopsy and Gleason score after radical prostatectomy (RP) may be a contributing factor. Objective To develop a statistical model that predicts the post-RP Gleason score (pathologic Gleason score [PGS]) using clinical observations made in the course of AS. Design, setting, and participants Repeated prostate-specific antigen measurements and biopsy Gleason scores from 964 very low-risk patients in the Johns Hopkins Active Surveillance cohort were used in the analysis. PGS observations from 191 patients who underwent RP were also included. Outcome measurements and statistical analysis A Bayesian joint model based on accumulated clinical data was used to predict PGS in these categories: 6 (grade group 1), 3 + 4 (grade group 2), 4 + 3 (grade group 3), and 8–10 (grade groups 4 and 5). The area under the receiver operating characteristic curve (AUC) and calibration of predictions was assessed in patients with post-RP Gleason score observations. Results and limitations The estimated probability of harboring a PGS >6 was <20% for most patients who had not experienced grade reclassification or elected surgery. Among patients with post-RP Gleason score observations, the AUC for predictions of PGS >6 was 0.74 (95% confidence interval, 0.66–0.81), and the mean absolute error was 0.022. Conclusions Although the model requires external validation prior to adoption, PGS predictions can be used in AS to inform decisions regarding follow-up biopsies and remaining on AS. Predictions can be updated as additional data are observed. The joint modeling framework also accommodates novel biomarkers as they are identified and measured on AS patients. Patient summary Measurements taken in the course of active surveillance can be used to accurately predict patients’ underlying prostate cancer status. Predictions can be communicated to patients via a decision support tool and used to guide clinical decision making and reduce patient anxiety. [ABSTRACT FROM AUTHOR]

Seasonal influenza epidemics offer unique opportunities to study the invasion and re-invasion waves of a pathogen in a partially immune population. Detailed patterns of spread remain elusive, however, due to lack of granular disease data. Here we model high-volume city-level medical claims data and human mobility proxies to explore the drivers of influenza spread in the US during 2002–2010. Although the speed and pathways of spread varied across seasons, seven of eight epidemics likely originated in the Southern US. Each epidemic was associated with 1–5 early long-range transmission events, half of which sparked onward transmission. Gravity model estimates indicate a sharp decay in influenza transmission with the distance between infectious and susceptible cities, consistent with spread dominated by work commutes rather than air traffic. Two early-onset seasons associated with antigenic novelty had particularly localized modes of spread, suggesting that novel strains may spread in a more localized fashion than previously anticipated. [ABSTRACT FROM AUTHOR]

High concentrations of household air pollution (HAP) due to biomass fuel usage with unvented, insufficient combustion devices are thought to be an important health risk factor in South Asia population. To better characterize the indoor concentrations of particulate matter (PM2.5) and carbon monoxide (CO), and to understand their impact on health in rural southern Nepal, this study analyzed daily monitoring data collected with DataRAM pDR-1000 and LASCAR CO data logger in 2980 households using traditional biomass cookstove indoor through the Nepal Cookstove Intervention Trial–Phase I between March 2010 and October 2011. Daily average PM2.5 and CO concentrations collected in area near stove were 1,376 (95% CI, 1,331–1,423) μg/m3 and 10.9 (10.5–11.3) parts per million (ppm) among households with traditional cookstoves. The 95th percentile, hours above 100μg/m3 for PM2.5 or 6ppm for CO, and hours above 1000μg/m3 for PM2.5 or 9ppm for CO were also reported. An algorithm was developed to differentiate stove-influenced (SI) periods from non-stove-influenced (non-SI) periods in monitoring data. Average stove-influenced concentrations were 3,469 (3,350–3,588) μg/m3 for PM2.5 and 21.8 (21.1–22.6) ppm for CO. Dry season significantly increased PM2.5 concentration in all metrics; wood was the cleanest fuel for PM2.5 and CO, while adding dung into the fuel increased concentrations of both pollutants. For studies in rural southern Nepal, CO concentration is not a viable surrogate for PM2.5 concentrations based on the low correlation between these measures. In sum, this study filled a gap in knowledge on HAP in rural Nepal using traditional cookstoves and revealed very high concentrations in these households. [ABSTRACT FROM AUTHOR]

Epidemiology is concerned with determining the distribution and causes of disease. Throughout its history, epidemiology has drawn upon statistical ideas and methods to achieve its aims. Because of the exponential growth in our capacity to measure and analyze data on the underlying processes that define each person's state of health, there is an emerging opportunity for population-based epidemiologic studies to influence health decisions made by individuals in ways that take into account the individuals' characteristics, circumstances, and preferences. We refer to this endeavor as "individualized health." The present article comprises 2 sections. In the first, we describe how graphical, longitudinal, and hierarchical models can inform the project of individualized health. We propose a simple graphical model for informing individual health decisions using population-based data. In the second, we review selected topics in causal inference that we believe to be particularly useful for individualized health. Epidemiology and biostatistics were 2 of the 4 founding departments in the world's first graduate school of public health at Johns Hopkins University, the centennial of which we honor. This survey of a small part of the literature is intended to demonstrate that the 2 fields remain just as inextricably linked today as they were 100 years ago. [ABSTRACT FROM AUTHOR]

BACKGROUND: Prospective cohort studies constitute the major source of evidence about the mortality effects of chronic exposure to particulate air pollution. Additional studies are needed to provide evidence on the health effects of chronic exposure to particulate matter ≤ 2.5 µm in aerodynamic diameter (PM2.5) because few studies have been carried out and the cohorts have not been representative. OBJECTIVES: This study was designed to estimate the relative risk of death associated with long-term exposure to PM2.5 by region and age groups in a U.S. population of elderly, for the period 2000--2005. METHODS: By linking PM2.5 monitoring data to the Medicare billing claims by ZIP code of residence of the enrollees, we have developed a new retrospective cohort study, the Medicare Cohort Air Pollution Study. The study population comprises 13.2 million participants living in 4,568 ZIP codes having centroids within 6 miles of a PM2.5 monitor. We estimated relative risks adjusted by socioeconomic status and smoking by fitting log-linear regression models. RESULTS: In the eastern and central regions, a 10-µg/m3 increase in 6-year average of PM2.5 is associated with 6.8% [95% confidence interval (CI), 4.9--8.7%] and 13.2% (95% CI, 9.5--16.9) increases in mortality, respectively. We found no evidence of an association in the western region or for persons ≥ 85 years of age. CONCLUSIONS: We established a cohort of Medicare participants for investigating air pollution and mortality on longer-term time frames. Chronic exposure to PM2.5 was associated with mortality in the eastern and central regions, but not in the western United States. [ABSTRACT FROM AUTHOR]

Background: Little is known about the associations of previous standardized examination scores with scores on subsequent standardized examinations used to assess medical knowledge in internal medicine residencies.Objective: To examine associations of previous standardized test scores on subsequent standardized test scores.Design: Retrospective cohort study.Participants: One hundred ninety-five internal medicine residents.Methods: Bivariate associations of United States Medical Licensing Examination (USMLE) Steps and Internal Medicine In-Training Examination (IM-ITE) scores were determined. Random effects analysis adjusting for repeated administrations of the IM-ITE and other variables known or hypothesized to affect IM-ITE score allowed for discrimination of associations of individual USMLE Step scores on IM-ITE scores.Results: In bivariate associations, USMLE scores explained 17% to 27% of the variance in IME-ITE scores, and previous IM-ITE scores explained 66% of the variance in subsequent IM-ITE scores. Regression coefficients (95% CI) for adjusted associations of each USMLE Step with IM-ITE scores were USMLE-1 0.19 (0.12, 0.27), USMLE-2 0.23 (0.17, 0.30), and USMLE-3 0.19 (0.09, 0.29).Conclusions: No single USMLE Step is more strongly associated with IM-ITE scores than the others. Because previous IM-ITE scores are strongly associated with subsequent IM-ITE scores, appropriate modeling, such as random effects methods, should be used to account for previous IM-ITE administrations in studies for which IM-ITE score is an outcome. [ABSTRACT FROM AUTHOR]

OBJECTIVE: To examine the association of medical knowledge acquisition with attendance at specific conference types during internal medicine residency. PARTICIPANTS AND METHODS: Attendance at residency core curriculum, morbidity and mortality, and medical grand rounds conferences was tracked for 195 residents who took the internal Medicine in-Training Examination (IM-ITE) 421 times while attending the Internal Medicine Residency Program at Mayo Clinic's site in Rochester, MN, between October 1, 1999, and October 1, 2003. Random effects modeling was used to adjust for variables known or hypothesized to be associated with IM-ITE scores and allowed discrimination of effects of individual conferences on IM-ITE scores. RESULTS: Total conference attendance was significantly associated with increased IM-ITE scores, with cohort mean increase of 2.30% (95% confidence interval [Cl], 1.24% to 3.36%; P<.001). Core curriculum conferences accounted for much more of this association than either medical grand rounds or morbidity and mortality, with cohort mean increases of 2.05% (95% Cl, 0.13% to 3.90%; P=.04), 0.24% (95% Cl, -0.56% to 1.03%; P=.61), and 0.03% (95% Cl, -1.69% to 1.69%; P=.97), respectively. CONCLUSION: Conference attendance is associated with improved knowledge acquisition as measured by improved performance on IM-ITE. This finding does not appear to apply to all conferences at our institution but rather is specifically attributable to attendance at the core curriculum series. [ABSTRACT FROM AUTHOR]

BACKGROUND: Knowledge acquisition is a goal of residency and is measurable by in-training exams. Little is known about factors associated with medical knowledge acquisition. OBJECTIVE: To examine associations of learning habits on medical knowledge acquisition. DESIGN, PARTICIPANTS: Cohort study of all 195 residents who took the Internal Medicine In-Training Examination (IM-ITE) 421 times over 4 years while enrolled in the Internal Medicine Residency, Mayo Clinic, Rochester, MN. MEASUREMENTS: Score (percent questions correct) on the IM-ITE adjusted for variables known or hypothesized to be associated with score using a random effects model. RESULTS: When adjusting for demographic, training, and prior achievement variables, yearly advancement within residency was associated with an IM-ITE score increase of 5.1% per year (95%CI 4.1%, 6.2%; p<.001). In the year before examination, comparable increases in IM-ITE score were associated with attendance at two curricular conferences per week, score increase of 3.9% (95%CI 2.1%, 5.7%: p<.001), or self-directed reading of an electronic knowledge resource 20 minutes each day, score increase of 4.5% (95%CI 1.2%, 7.8%; p=.008). Other factors significantly associated with IM-ITE performance included: age at start of residency, score decrease per year of increasing age, -0.2% (95%CI -0.36%, -0.042%; p=.01), and graduation from a US medical school, score decrease compared to international medical school graduation, -3.4% (95%CI -6.5%, -0.36%; p=.03). CONCLUSIONS: Conference attendance and self-directed reading of an electronic knowledge resource had statistically and educationally significant independent associations with knowledge acquisition that were comparable to the benefit of a year in residency training. [ABSTRACT FROM AUTHOR]

Procedures for analyzing and comparing health care providers' effects on health services delivery and outcomes have been referred to as provider profiling. In a typical profiling procedure, patient-level responses are measured for clusters of patients treated by providers that in turn can be considered statistically exchangeable. Thus a hierarchical model naturally represents the structure of the data. When provider effects on multiple responses are profiled, a multivariate model rather than a series of univariate models can capture associations among responses at both the provider and patient levels. When responses are in the form of charges for health care services and sampled patients include nonusers of services, charge variables are a mix of O's and highly skewed positive values that present a modeling challenge. For analysis of covariate effects on charges for a single service, a frequently used approach is a two-part model that combines logistic or probit regression on any use of the service and linear regression on log-positive charges given use of the service. Here we extend the two- part model to the case of charges for multiple services, using a log-linear model and a general multivariate lognormal model, and use the resultant multivariate two-part model as the within-provider component of a hierarchical model. The log-linear likelihood is reparameterized as proposed by Fitzmaurice and Laird, so that covariate effects on any use of each service are marginal with respect to any use of other services. The general multivariate lognormal likelihood is structured in such a way that the variance of log-positive charges for each service is provider-specific but correlations among logs of positive charges for different services are uniform across providers. A data augmentation step is included in the Gibbs sampler used to fit the hierarchical model to accommodate the fact that values of log-positive charges are undefined for unused services. We apply this hierarc [ABSTRACT FROM AUTHOR]

This paper gives an overview of time series ideas and methods used in public health and biomedical research. A time series is a sequence of observations made over time. Examples in public health include daily ozone concentrations, weekly admissions to an emergency department, or annual expenditures on health care in the United States. Time series models are most commonly used in regression analysis to describe the dependence of the response at each time on predictor variables including covariates and possibly previous values in the series. For example, Bell et al. (2) use time series methods to regress daily mortality in U.S. cities on concentrations of particulate air pollution. Time series methods are necessary to make valid inferences from data by accounting for the correlation among repeated responses over time. [ABSTRACT FROM AUTHOR]

This article presents a novel approach to analyzing a complex dataset from a prevention trial, where outcomes comprise multiple repeated mental health items and times to initiation of alcohol and tobacco use. The dataset has a nonnegligible portion of missing values and interval or left censored events. The substantive interest of the trial suggests a psychiatric distress latent variable that is reflected in the mental health items and potentially affects initiation of alcohol and tobacco use. We describe the data with a combination of three types of component model: a marginal model for the longitudinal latent process for psychiatric distress given study interventions and covariates; logistic regression models for the repeated mental health items given the latent process; and hazard models for times to initiation of alcohol and tobacco use given the latent process, study interventions, and covariates. To aid in fitting these models simultaneously, we use automatic differentiation to find the first two derivatives of the total log-likelihood function, thus speeding up convergence relative to the regular expectation-maximization algorithm with a direct calculation of valid variance estimates. [ABSTRACT FROM AUTHOR]

Background Estimates of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) seroprevalence in young children and risk factors for seropositivity are scarce. Using data from a prospective cohort study of households during the pre-coronavirus disease 2019 (COVID-19) vaccine period, we estimated SARS-CoV-2 seroprevalence by age and evaluated risk factors for SARS-CoV-2 seropositivity. Methods The SARS-CoV-2 Epidemiology and Response in Children (SEARCh) study enrolled 175 Maryland households (690 participants) with ≥1 child aged 0–4 years during November 2020–March 2021; individuals vaccinated against COVID-19 were ineligible. At enrollment, participants completed questionnaires about sociodemographic and health status and work, school, and daycare attendance. Participants were tested for SARS-CoV-2 antibodies in sera. Logistic regression models with generalized estimating equations (GEE) to account for correlation within households assessed predictors of individual- and household-level SARS-CoV-2 seropositivity. Results Of 681 (98.7%) participants with enrollment serology results, 55 (8.1%; 95% confidence interval [CI], 6.3%–10.4%) participants from 21 (12.0%) households were seropositive for SARS-CoV-2. Among seropositive participants, fewer children than adults reported being tested for SARS-CoV-2 infection before enrollment (odds ratio [OR] = 0.23; 95% CI,.06–.73). Seropositivity was similar by age (GEE OR vs 0–4 years: 1.19 for 5–17 years, 1.36 for adults; P =.16) and was significantly higher among adults working outside the home (GEE adjusted OR = 2.2; 95% CI, 1.1–4.4) but not among children attending daycare or school. Conclusions Before study enrollment, children and adults in this cohort had similar rates of SARS-CoV-2 infection as measured by serology. An adult household member working outside the home increased a household's odds of SARS-CoV-2 infection, whereas a child attending daycare or school in person did not. [ABSTRACT FROM AUTHOR]

Background: Data that capture implementation strength can be combined in multiple ways across content and health system levels to create a summary measure that can help us to explore and compare program implementation across facility catchment areas. Summary indices can make it easier for national policymakers to understand and address variation in strength of program implementation across jurisdictions. In this paper, we describe the development of an index that we used to describe the district-level strength of implementation of Malawi's national family planning program. Methods: To develop the index, we used data collected during a 2017 national, health facility and community health worker Implementation Strength Assessment survey in Malawi to test different methods to combine indicators within and then across domains (4 methods—simple additive, weighted additive, principal components analysis, exploratory factor analysis) and combine scores across health facility and community health worker levels (2 methods—simple average and mixed effects model) to create a catchment area-level summary score for each health facility in Malawi. We explored how well each model captures variation and predicts couple-years protection and how feasible it is to conduct each type of analysis and the resulting interpretability. Results: We found little difference in how the four methods combined indicator data at the individual and combined levels of the health system. However, there were major differences when combining scores across health system levels to obtain a score at the health facility catchment area level. The scores resulting from the mixed effects model were able to better discriminate differences between catchment area scores compared to the simple average method. The scores using the mixed effects combination method also demonstrated more of a dose–response relationship with couple-years protection. Conclusions: The summary measure that was calculated from the mixed effects combination method captured the variation of strength of implementation of Malawi's national family planning program at the health facility catchment area level. However, the best method for creating an index should be based on the pros and cons listed, not least, analyst capacity and ease of interpretability of findings. Ultimately, the resulting summary measure can aid decision-makers in understanding the combined effect of multiple aspects of programs being implemented in their health system and comparing the strengths of programs across geographies. [ABSTRACT FROM AUTHOR]

Background: In South Asia, a third of babies are born small-for-gestational age (SGA). The risk factors are well described in the literature, but many studies are in high-and-middle income countries or measure SGA on facility births only. There are fewer studies that describe the prevalence of risk factors for large-for-gestational age (LGA) in low-income countries. We aim to describe the factors associated with SGA and LGA in a population-based cohort of pregnant women in rural Nepal.Methods: This is a secondary data analysis of community-based trial on neonatal oil massage (22,545 women contributing 39,479 pregnancies). Demographic, socio-economic status (SES), medical/obstetric history, and timing of last menstruation were collected at enrollment. Vital signs, illness symptoms, and antenatal care (ANC) attendance were collected throughout the pregnancy and neonatal weight was measured for live births. We conducted multivariate analysis using multinomial, multilevel logistic regression, reporting the odds ratio (OR) with 95% confidence intervals (CIs). Outcomes were SGA, LGA compared to appropriate-for-gestational age (AGA) and were multiply imputed using birthweight recalibrated to time at delivery.Results: SGA was associated with nulligravida (OR: 2.12 95% CI: 1.93-2.34), gravida/nulliparous (OR: 1.86, 95% CI: 1.26-2.74), interpregnancy intervals less than 18 months (OR: 1.16, 95% CI: 1.07-1.27), and poor appetite/vomiting in the second trimester, (OR: 1.27, 95% CI: 1.19-1.35). Greater wealth (OR: 0.78, 95% CI: 0.69-0.88), swelling of hands/face in the third trimester (OR: 0.81, 95% CI: 0.69-0.94) parity greater than five (OR: 0.77, 95% CI: 0.65-0.92), male fetal sex (OR: 0.91, 95% CI: 0.86-0.98), and increased weight gain (OR: 0.93 per weight kilogram difference between 2nd and 3rd trimester, 95% CI: 0.92-0.95) were protective for SGA. Four or more ANC visits (OR: 0.53, 95% CI: 0.41-0.68) and respiratory symptoms in the third trimester (OR: 0.67, 95% CI: 0.54-0.84) were negatively associated with LGA, and maternal age < 18 years (OR: 1.39, 95% CI: 1.03-1.87) and respiratory symptoms in the second trimester (OR: 1.27, 95% CI: 1.07-1.51) were positively associated with LGA.Conclusions: Our findings are in line with known risk factors for SGA. Because the prevalence and mortality risk of LGA babies is low in this population, it is likely LGA status does not indicate underlaying illness. Improved and equitable access to high quality antenatal care, monitoring for appropriate gestational weight gain and increased monitoring of women with high-risk pregnancies may reduce prevalence and improve outcomes of SGA babies.Trial Registration: The study used in this secondary data analysis was registered at Clinicaltrials.gov NCT01177111. [ABSTRACT FROM AUTHOR]

Compares the rate of progression to acquired immunodeficiency syndrome (AIDS) in human immunodeficiency virus type 1 (HIV)-1 seropositive homosexual men receiving and not receiving zidovudine and `Pneumocystis carinii' pneumonia prophylaxis between 1987 and 1990 in the multicenter AIDS cohort study. Patients and methods; Results; Discussion.

Presents lorelogram function, a regression estimator of the marginal pairwise log-odds ratio measure of association for longitudinal categorical responses. Properties of lorelogram; Estimation of lorelogram; Example using lorelogram methodology.

Proposes a method of estimating mixing distributions using maximum likelihood over the class of arbitrary mixtures of Gaussians. Constraint that the component variances be greater than or equal to some minimum value h; Extension of the estimate to include multivariate mixing distributions.

Constructs statistical models for clustered ordinal measurements. Specification of two regression models; Presentation of first-order estimating equations (GEE1) as an alternative estimation strategy; Examination of the efficiency of GEE! and ALR relative to full maximum likelihood.

Focuses on the random effects model in a Bayesian framework and use a Monte Carlo method, the Gibbs sampler, to overcome the computational limitations. Highlight of the random effects generalized linear model (GLM); Bayesian formulation; Application of the Gibbs sampler to the random effects GLM; Necessary conditional distributions for use of the Gibbs sampler; Methodology with a brief simulation study and an application to infectious disease data.

We consider the regression model yt = ηt + εt, t = 0, 1,...n - 1, where yt are scalar observations, ηt, is the unknown regression function, and εt, are unobservable errors generated by a zero-mean weakly stationary process, independent of ηt, and with completely unknown autocorrelation structure. We propose a data-driven method for selecting a parametric or nonparametric estimator of ηt. The method is based on cross-validation in the frequency domain and requires no assumptions about the form of the estimator or the error correlations. It does, however, require the discrete Fourier transform (DFT) of the signal ηt, to be a smooth complex function of frequency, as is the case, for example, with transient signals or growth and decay curves. After giving some general motivations for the method, we focus on the special case of linear estimators of a nonparametric regression function, including both kernel and spline estimators. For these estimators, we develop efficient methods of evaluating the frequency domain cross-validation (FDCV) function. The standard time domain cross-validation (TDCV) method, which leaves out data points one at a time, is sensible only when the errors arc independent. Autocorrelation among the errors can cause severe biases in the TDCV function, leading to poor selections. FDCV leaves out discrete Fourier transform values one at a time. These values are approximately independent regardless of the error correlation structure, and hence FDCV remains valid even for correlated errors, as long as the DFT of ηt, at the omitted frequency can be predicted from those remaining. Asymptotic properties of FDCV are given for a class of transient signals. Then the usefulness of FDCV for transient and other signals is demonstrated in a Monte Carlo study comparing the performances of TDCV and FDCV for selecting a kernel estimator of a nonparametric regression function. The use of FDCV is illustrated with data on international airline travel. [ABSTRACT FROM AUTHOR]

A logistic model for multivariate binary time series is proposed. First, we establish the equivalence between a log-linear model for the marginal distribution of a multivariate binary random vector and logistic models for the conditional distributions of each component given the others. The logistic formulation is used to describe a Markov chain for each series, which implies a Markov model for the vector of time series. A pseudolikelihood estimation procedure is presented. The methods are illustrated with data on psychosomatic and psychological diagnoses for families in a health-maintenance plan. [ABSTRACT FROM AUTHOR]

A non-Gaussian autoregressive-like model is presented for time series that exhibit occasional large increases in value, termed pulses, and exponential decay between pulses. The model differs from a first-order autoregressive process in its incorporation of feedback between the distribution of the current innovation and the history of the process. Likelihood-based methods of inference for the model are developed, and an application to endocrinological data is given. [ABSTRACT FROM AUTHOR]

This article discusses the median of a batch of time series. We focus on the frequency-domain median (FDM) series (Zeger 1985), which is calculated from the "mediancenters" (Gower 1974) of the discrete Fourier transforms. Like the univariate median, it has a breakdown value of 50%. Like the mean, the FDM time series of independent realizations from a stationary Ganssian process has a spectrum proportional to that of the component series. Analogs of the univariate median have been described for multivariate (e.g., Brown 1983), survival (Brookmeyer and Crowley 1982), and spherical (Fisher 1985) data. As in the multivariate case, there is not a unique definition of a median time series. One possibility is the median value at each time or time-domain median (TDM). A drawback of the TDM is that it can be qualitatively dissimilar in appearance to its component series because of discontinuities when the median value switches from one realization to another. This is particularly disturbing for smooth time series. Our alternative, the FDM, avoids this problem for nearly Gaussian processes. We show that the breakdown value of the mediancenter of spherically symmetric random variables is 50%. The result for the FDM then follows. We consider a set of time series in which each is composed of a common signal and an iid stationary error series. Two asymptotic scenarios are discussed--the number of iid series of finite length getting large and the length increasing for a finite number of realizations. In the former case, the FDM is asymptotically a Ganssian process with a spectrum similar to that of the components. In the latter, we show that the FDM of stationary Gaussian processes is unbiased and has a spectrum proportional to the spectrum of a single realization. An example illustrates the FDM. [ABSTRACT FROM AUTHOR]

For many studies in which data are collected sequentially in time, the sensitivity of the measurement is limited and an exact value can be recorded only if it falls within a specified range. This gives rise to a censored time series. In this article, we present a methodology for regression analysis of censored time series data. We fit autoregressive models to account for the time dependence. Two numerical methods for full likelihood estimation and an approximate method are discussed. The methods are illustrated with air pollution data subject to lower limits of detection. [ABSTRACT FROM AUTHOR]

The criterion of second-order efficiency is used to distinguish among estimators, which have the same asymptotic variance, of the mean of a stationary autoregressive process. The best linear unbiased estimator is typically unknown, since it depends on the parameters of the process. It is demonstrated by second-order efficiency that the sample mean performs poorly under certain conditions, whereas some weighted averages maintain a more consistent performance as the parameters of the underlying process are allowed to vary. Numerical examples are shown for second-and third-order autoregressive processes. [ABSTRACT FROM AUTHOR]

In 1974, atmospheric scientists (Molina and Rowland; Cicerone et al.) first postulated that man-made chemicals known as CFC's (e.g., freon) deplete the earth's ozone when released into the atmosphere. This article presents an exploratory data analysis (EDA) of a spatial time series of ozone measurements. Frequency domain techniques for the EDA are introduced and used to graphically display global, long-term trends relevant to the CFC issue. My intention is to illustrate the effectiveness of a frequency domain approach to exploring a spatial time series. [ABSTRACT FROM AUTHOR]

The article offers information on several aspects associated with the precision medicine comprising its associated discovery of clinically relevant and mechanistically anchored disease subgroups at scale. The topics addressed include details on the technology revolutions which are reshaping medicine comprising improved measurements, increased computational power, and better connectivity.

In this issue of the Journal, two different articles present epidemiologic evidence supporting the hypotheses that environmental exposures to particulate air pollution or higher temperatures modestly increase the risk of preterm birth. In this commentary, the author discusses environmental epidemiologic methods through the lens of these two papers with respect to the causal question, measurements, and quantification and interpretation of the evidence. Both groups of investigators present results from exploratory analyses that are at the hypothesis-generating end of the research spectrum as opposed to the confirmatory end. The present author describes in qualitative terms a method for decomposing evidence about the association of environmental exposures with prematurity into components representing different temporal and spatial scales. Finally, reproducible epidemiologic research methodology for studies like these is offered as one way to speed the transition from exploratory studies to confirmatory studies. [ABSTRACT FROM AUTHOR]

We evaluated the effect of state cigarette tax increases on cigarette sales in the 50 states for the years 1955 to 1988. State cigarette tax increases were associated with an average decline in cigarette consumption of three cigarette packs per capita (about 2.4%). Larger tax increases were associated with larger declines in consumption. Raising state cigarette taxed appears to be an effective public health intervention that can reduce cigarette consumption and its associated health consequences. [ABSTRACT FROM AUTHOR]

Objectives: We examined whether an array of scleroderma autoantibodies associates with risk of cancer and could be useful tools for risk stratification. Methods: Scleroderma cancer cases and scleroderma controls without cancer from the Johns Hopkins Scleroderma Center and the University of Pittsburgh Scleroderma Center were studied. Sera were assayed by Lineblot and enzyme‐linked immunosorbent assay (ELISA) for autoantibodies against centromere, topoisomerase 1, RNA polymerase (POLR) 3, PM/Scl, Th/To, NOR90, U3 RNP, Ku, Ro52, U1RNP, and RNPC3. Logistic regression models were constructed to examine whether distinct autoantibodies associated with overall cancer at any time and cancer‐associated scleroderma (cancer occurring three years before and after scleroderma onset). The effects of having more than one autoantibody on cancer were further examined using random forest analysis. Results: A total of 676 cases and 687 controls were studied. After adjusting for relevant covariates, anti‐POLR3 (odds ratio [OR] 1.47, 95% confidence interval [CI] 1.03–2.11) and monospecific anti‐Ro52 (OR 2.19, 95% CI 1.29–3.74) were associated with an increased overall cancer risk, whereas anticentromere (OR 0.69, 95% CI 0.51–0.93) and anti‐U1RNP (OR 0.63, 95% CI 0.43–0.93) were associated with lower risk. When examining risk of cancer‐associated scleroderma, these immune responses remained associated with increased or decreased risk: anti‐POLR3 (OR 2.28, 95% CI 1.33–3.91), monospecific anti‐Ro52 (OR 2.58, 95% CI 1.05–6.30), anticentromere (OR 0.39, 95% CI 0.20–0.74), and anti‐U1RNP (OR 0.32, 95% CI 0.11–0.93). Anti‐Ro52 plus anti‐U1RNP or anti‐Th/To was associated with decreased cancer risk compared with anti‐Ro52 alone. Conclusions: These data suggest that five distinct scleroderma immune responses, alone or in combination, may be useful tools to stratify the risk of cancer for scleroderma patients. Further study examining cancer risk in autoantibody subgroups relative to the general population is warranted. [ABSTRACT FROM AUTHOR]

Age-related memory deficits are correlated with neural hyperactivity in the CA3 region of the hippocampus. Abnormal CA3 hyperactivity in aged rats has been proposed to contribute to an imbalance between pattern separation and pattern completion, resulting in overly rigid representations. Recent evidence of functional heterogeneity along the CA3 transverse axis suggests that proximal CA3 supports pattern separation while distal CA3 supports pattern completion. It is not known whether age-related CA3 hyperactivity is uniformly represented along the CA3 transverse axis. We examined the firing rates of CA3 neurons from young and aged, male, Long–Evans rats along the CA3 transverse axis. Consistent with prior studies, young CA3 cells showed an increasing gradient in mean firing rate from proximal to distal CA3. However, aged CA3 cells showed an opposite, decreasing trend, in that CA3 cells in aged rats were hyperactive in proximal CA3, but possibly hypoactive in distal CA3, compared with young (Y) rats. We suggest that, in combination with altered inputs from the entorhinal cortex and dentate gyrus (DG), the proximal CA3 region of aged rats may switch from its normal function that reflects the pattern separation output of the DG and instead performs a computation that reflects an abnormal bias toward pattern completion. In parallel, distal CA3 of aged rats may create weaker attractor basins that promote abnormal, bistable representations under certain conditions. [ABSTRACT FROM AUTHOR]

Purpose: Numerous randomized trials have demonstrated noninferiority of single- versus multiple-fraction palliative radiation therapy (RT) in the management of uncomplicated bone metastases; yet there is neither a clear definition of what constitutes a complicated lesion, nor substantial data regarding the prevalence of such complicating features in clinical practice. Thus, we identify a range of evidence-based operational definitions of complicated symptomatic bone metastases and characterize the frequency of such complicating features at a high-volume, tertiary care center.Methods and Materials: A retrospective review of patients seen in consultation for symptomatic bone metastases between March 1, 2007, and July 31, 2013, at Johns Hopkins Hospital identified patient and disease characteristics. Descriptive statistics characterized the frequency of the following complicating features: prior RT, prior surgery, neuraxis compromise, pathologic fracture, and soft tissue component at the symptomatic site. A range of definitions for complicated bone metastases was evaluated based on combinations of these features. Uni- and multivariable logistic regressions evaluated the odds of complicated bone metastases as a function of site of primary cancer and of the symptomatic target lesion.Results: A total of 686 symptomatic bone metastases in 401 patients were evaluated. Percent of target sites complicated by prior RT was 4.4%, prior surgery was 8.9%, pathologic fracture was 20.6%, neuraxis compromise was 52.0% among spine and medial pelvis sites, and soft tissue component was 38.6%. More than 96 possible definitions of complicated bone metastases were identified. The presence of such complicated lesions ranged from 2.3% to 67.3%, depending on the operational definition used. Odds of a complicated lesion were significantly higher for spine sites and select nonbreast histologies.Conclusions: In this retrospective study, we found complicated symptomatic bone metastases may be present in up to two-thirds of patients. Literature review also demonstrates no clear standard definition of complicated bone metastases, potentially explaining underutilization of single-fraction palliative RT in this setting. [ABSTRACT FROM AUTHOR]

Background: Clinical research and medical practice can be advanced through the prediction of an individual's health state, trajectory, and responses to treatments. However, the majority of current clinical risk prediction models are based on regression approaches or machine learning algorithms that are static, rather than dynamic. To benefit from the increasing emergence of large, heterogeneous data sets, such as electronic health records (EHRs), novel tools to support improved clinical decision making through methods for individual-level risk prediction that can handle multiple variables, their interactions, and time-varying values are necessary.Methods: We introduce a novel dynamic approach to clinical risk prediction for survival, longitudinal, and multivariate (SLAM) outcomes, called random forest for SLAM data analysis (RF-SLAM). RF-SLAM is a continuous-time, random forest method for survival analysis that combines the strengths of existing statistical and machine learning methods to produce individualized Bayes estimates of piecewise-constant hazard rates. We also present a method-agnostic approach for time-varying evaluation of model performance.Results: We derive and illustrate the method by predicting sudden cardiac arrest (SCA) in the Left Ventricular Structural (LV) Predictors of Sudden Cardiac Death (SCD) Registry. We demonstrate superior performance relative to standard random forest methods for survival data. We illustrate the importance of the number of preceding heart failure hospitalizations as a time-dependent predictor in SCA risk assessment.Conclusions: RF-SLAM is a novel statistical and machine learning method that improves risk prediction by incorporating time-varying information and accommodating a large number of predictors, their interactions, and missing values. RF-SLAM is designed to easily extend to simultaneous predictions of multiple, possibly competing, events and/or repeated measurements of discrete or continuous variables over time.Trial Registration: LV Structural Predictors of SCD Registry (clinicaltrials.gov, NCT01076660), retrospectively registered 25 February 2010. [ABSTRACT FROM AUTHOR]

Addresses a commentary on an article about latent class model (LCM) diagnosis. Application of goodness of fit tests to LCM diagnosis; Approaches to LCM parameterization; Comment on the use of graphical methods in LCM diagnosis.

Background Prior observation has shown differences in COVID-19 hospitalization risk between SARS-CoV-2 variants, but limited information describes hospitalization outcomes. Methods Inpatients with COVID-19 at 5 hospitals in the eastern United States were included if they had hypoxia, tachypnea, tachycardia, or fever, and SARS-CoV-2 variant data, determined from whole-genome sequencing or local surveillance inference. Analyses were stratified by history of SARS-CoV-2 vaccination or infection. The average effect of SARS-CoV-2 variant on 28-day risk of severe disease, defined by advanced respiratory support needs, or death was evaluated using models weighted on propensity scores derived from baseline clinical features. Results Severe disease or death within 28 days occurred for 977 (29%) of 3369 unvaccinated patients and 269 (22%) of 1230 patients with history of vaccination or prior SARS-CoV-2 infection. Among unvaccinated patients, the relative risk of severe disease or death for Delta variant compared with ancestral lineages was 1.30 (95% confidence interval [CI]: 1.11–1.49). Compared with Delta, the risk for Omicron patients was.72 (95% CI:.59–.88) and compared with ancestral lineages was.94 (.78–1.1). Among Omicron and Delta infections, patients with history of vaccination or prior SARS-CoV-2 infection had half the risk of severe disease or death (adjusted hazard ratio:.40; 95% CI:.30–.54), but no significant outcome difference by variant. Conclusions Although risk of severe disease or death for unvaccinated inpatients with Omicron was lower than with Delta, it was similar to ancestral lineages. Severe outcomes were less common in vaccinated inpatients, with no difference between Delta and Omicron infections. [ABSTRACT FROM AUTHOR]

The author comments on an article by James M. Robins and colleagues published in this issue about methods for causal inference from longitudinal, observational data. He organized his opinion into four topics including the role of statistical modeling in science, causal inferences as extrapolations from the observed data, generalized estimating equation as a method of inference and defining causal parameters.

Two letters to the editor are presented concerning the article "How Effective Are Excise Tax Increases in Reducing Cigarette Smoking?," by J. Wasserman, published in a 1992 issue of the "American Journal of Public Health."

Opinion. Presents the authors' view on historical preference for randomization inference and the regulatory benefit of a standardized approach to the analysis of clinical trial data, and focus in more detail on bias, proposing an alternative to E&F's estimate of treatment. Their objection related to the regulatory objective for a clinical trial to dictate a decision about a proposed therapy; Most important objection to controlling for compliance.

Key Points: Question: Can DNA sequencing of blood from adults with acute myeloid leukemia (AML) in first remission prior to allogeneic hematopoietic cell transplant identify patients at increased risk of subsequent relapse and death? Findings: In patients with AML in first complete remission who received a transplant from March 1, 2013, through December 31, 2017 (discovery, n = 371) or from January 1, 2018, through February 14, 2019 (validation, n = 451), the presence of residual FLT3 internal tandem duplication (FLT3-ITD) and/or NPM1 DNA variants before transplant were associated with significantly increased rates of relapse (validation cohort difference, 47%; 95% CI, 26% to 69%) and significantly worse survival (validation cohort difference, −24%; 95% CI, −39 to −9%) at 3 years, compared with those without these markers. Meaning: Among patients with AML in first remission prior to allogeneic hematopoietic cell transplant, the persistence of FLT3-ITD or NPM1 variants in the blood at an allele fraction of 0.01% or higher was associated with increased relapse and worse survival compared with those without variants detected. Importance: Preventing relapse for adults with acute myeloid leukemia (AML) in first remission is the most common indication for allogeneic hematopoietic cell transplant. The presence of AML measurable residual disease (MRD) has been associated with higher relapse rates, but testing is not standardized. Objective: To determine whether DNA sequencing to identify residual variants in the blood of adults with AML in first remission before allogeneic hematopoietic cell transplant identifies patients at increased risk of relapse and poorer overall survival compared with those without these DNA variants. Design, Setting, and Participants: In this retrospective observational study, DNA sequencing was performed on pretransplant blood from patients aged 18 years or older who had undergone their first allogeneic hematopoietic cell transplant during first remission for AML associated with variants in FLT3, NPM1, IDH1, IDH2, or KIT at 1 of 111 treatment sites from 2013 through 2019. Clinical data were collected, through May 2022, by the Center for International Blood and Marrow Transplant Research. Exposure: Centralized DNA sequencing of banked pretransplant remission blood samples. Main Outcomes and Measures: The primary outcomes were overall survival and relapse. Day of transplant was considered day 0. Hazard ratios were reported using Cox proportional hazards regression models. Results: Of 1075 patients tested, 822 had FLT3 internal tandem duplication (FLT3-ITD) and/or NPM1 mutated AML (median age, 57.1 years, 54% female). Among 371 patients in the discovery cohort, the persistence of NPM1 and/or FLT3-ITD variants in the blood of 64 patients (17.3%) in remission before undergoing transplant was associated with worse outcomes after transplant (2013-2017). Similarly, of the 451 patients in the validation cohort who had undergone transplant in 2018-2019, 78 patients (17.3%) with residual NPM1 and/or FLT3-ITD variants had higher rates of relapse at 3 years (68% vs 21%; difference, 47% [95% CI, 26% to 69%]; HR, 4.32 [95% CI, 2.98 to 6.26]; P <.001) and decreased survival at 3 years (39% vs 63%; difference, −24% [2-sided 95% CI, −39% to −9%]; HR, 2.43 [95% CI, 1.71 to 3.45]; P <.001). Conclusions and Relevance: Among patients with acute myeloid leukemia in first remission prior to allogeneic hematopoietic cell transplant, the persistence of FLT3 internal tandem duplication or NPM1 variants in the blood at an allele fraction of 0.01% or higher was associated with increased relapse and worse survival compared with those without these variants. Further study is needed to determine whether routine DNA-sequencing testing for residual variants can improve outcomes for patients with acute myeloid leukemia. In this observational study, targeted deep DNA sequencing was performed to test the hypothesis that detection of specific residual AML-associated variants in the blood of patients in first remission prior to allogeneic hematopoietic cell transplant would be associated with higher rates of relapse and mortality after transplant [ABSTRACT FROM AUTHOR]

As clinicians are faced with a deluge of clinical data, data science can play an important role in highlighting key features driving patient outcomes, aiding in the development of new clinical hypotheses. Insight derived from machine learning can serve as a clinical support tool by connecting care providers with reliable results from big data analysis that identify previously undetected clinical patterns. In this work, we show an example of collaboration between clinicians and data scientists during the COVID-19 pandemic, identifying sub-groups of COVID-19 patients with unanticipated outcomes or who are high-risk for severe disease or death. We apply a random forest classifier model to predict adverse patient outcomes early in the disease course, and we connect our classification results to unsupervised clustering of patient features that may underpin patient risk. The paradigm for using data science for hypothesis generation and clinical decision support, as well as our triaged classification approach and unsupervised clustering methods to determine patient cohorts, are applicable to driving rapid hypothesis generation and iteration in a variety of clinical challenges, including future public health crises. [ABSTRACT FROM AUTHOR]

The Pneumonia Etiology Research for Child Health (PERCH) study seeks to use modern measurement technology to infer the causes of pneumonia for which gold-standard evidence is unavailable. Based on case-control data, the article describes a latent variable model designed to infer the etiology distribution for the population of cases, and for an individual case given her measurements. We assume each observation is drawn from a mixture model for which each component represents one disease class. The model conisidered here addresses a major limitation of the traditional latent class approach by taking account of residual dependence among multivariate binary outcomes given disease class, hence reducing estimation bias, retaining efficiency and offering more valid inference. Such "local dependence" on each subject is induced in the model by nesting latent subclasses within each disease class. Measurement precision and covariation can be estimated using the control sample for whom the class is known. In a Bayesian framework, we use stick-breaking priors on the subclass indicators for model-averaged inference across different numbers of subclasses. Assessment of model fit and individual diagnosis are done using posterior samples drawn by Gibbs sampling. We demonstrate the utility of the method on simulated and on the motivating PERCH data. [ABSTRACT FROM AUTHOR]

Associations of mean glucose and time in range (70-180 mg/dL) from continuous glucose monitoring (CGM) with HbA1c in adults with type 2 diabetes are not well characterized. We conducted a secondary analysis of 186 participants from the Hyperglycemic Profiles in Obstructive Sleep Apnea (HYPNOS) trial. Participants simultaneously wore Dexcom G4 and Abbott Libre Pro CGM sensors up to 4 weeks. Mean HbA1c was 7.7% (SD, 1.3). There were strong negative Pearson's correlations of HbA1c with CGM time in range (-0.79, Abbott; -0.81, Dexcom) and strong positive correlations with CGM mean glucose (Dexcom, 0.84; Abbott, 0.82). However, there were large differences in CGM mean glucose (±20 mg/dL) and time in range (±14%) at any given HbA1c value. Mean glucose and HbA1c are strongly correlated in type 2 diabetes patients not taking insulin but discordance is evident at the individual level. Clinicians should expect discordance and use HbA1c and CGM in a complementary manner. ClinicalTrials.gov Identifier: NCT02454153. [ABSTRACT FROM AUTHOR]

Quantification learning is the task of prevalence estimation for a test population using predictions from a classifier trained on a different population. Quantification methods assume that the sensitivities and specificities of the classifier are either perfect or transportable from the training to the test population. These assumptions are inappropriate in the presence of dataset shift, when the misclassification rates in the training population are not representative of those for the test population. Quantification under dataset shift has been addressed only for single-class (categorical) predictions and assuming perfect knowledge of the true labels on a small subset of the test population. We propose generalized Bayes quantification learning (GBQL) that uses the entire compositional predictions from probabilistic classifiers and allows for uncertainty in true class labels for the limited labeled test data. Instead of positing a full model, we use a model-free Bayesian estimating equation approach to compositional data using Kullback–Leibler loss-functions based only on a first-moment assumption. The idea will be useful in Bayesian compositional data analysis in general as it is robust to different generating mechanisms for compositional data and allows 0's and 1's in the compositional outputs thereby including categorical outputs as a special case. We show how our method yields existing quantification approaches as special cases. Extension to an ensemble GBQL that uses predictions from multiple classifiers yielding inference robust to inclusion of a poor classifier is discussed. We outline a fast and efficient Gibbs sampler using a rounding and coarsening approximation to the loss functions. We establish posterior consistency, asymptotic normality and valid coverage of interval estimates from GBQL, which to our knowledge are the first theoretical results for a quantification approach in the presence of local labeled data. We also establish finite sample posterior concentration rate. Empirical performance of GBQL is demonstrated through simulations and analysis of real data with evident dataset shift. for this article are available online. [ABSTRACT FROM AUTHOR]