RESUMEN

BACKGROUND: Missing data are common in observational studies and often occur in several of the variables required when estimating a causal effect, i.e. the exposure, outcome and/or variables used to control for confounding. Analyses involving multiple incomplete variables are not as straightforward as analyses with a single incomplete variable. For example, in the context of multivariable missingness, the standard missing data assumptions ("missing completely at random", "missing at random" [MAR], "missing not at random") are difficult to interpret and assess. It is not clear how the complexities that arise due to multivariable missingness are being addressed in practice. The aim of this study was to review how missing data are managed and reported in observational studies that use multiple imputation (MI) for causal effect estimation, with a particular focus on missing data summaries, missing data assumptions, primary and sensitivity analyses, and MI implementation. METHODS: We searched five top general epidemiology journals for observational studies that aimed to answer a causal research question and used MI, published between January 2019 and December 2021. Article screening and data extraction were performed systematically. RESULTS: Of the 130 studies included in this review, 108 (83%) derived an analysis sample by excluding individuals with missing data in specific variables (e.g., outcome) and 114 (88%) had multivariable missingness within the analysis sample. Forty-four (34%) studies provided a statement about missing data assumptions, 35 of which stated the MAR assumption, but only 11/44 (25%) studies provided a justification for these assumptions. The number of imputations, MI method and MI software were generally well-reported (71%, 75% and 88% of studies, respectively), while aspects of the imputation model specification were not clear for more than half of the studies. A secondary analysis that used a different approach to handle the missing data was conducted in 69/130 (53%) studies. Of these 69 studies, 68 (99%) lacked a clear justification for the secondary analysis. CONCLUSION: Effort is needed to clarify the rationale for and improve the reporting of MI for estimation of causal effects from observational data. We encourage greater transparency in making and reporting analytical decisions related to missing data.

Asunto(s)

RESUMEN

Integrating multiple observational studies to make unconfounded causal or descriptive comparisons of group potential outcomes in a large natural population is challenging. Moreover, retrospective cohorts, being convenience samples, are usually unrepresentative of the natural population of interest and have groups with unbalanced covariates. We propose a general covariate-balancing framework based on pseudo-populations that extends established weighting methods to the meta-analysis of multiple retrospective cohorts with multiple groups. Additionally, by maximizing the effective sample sizes of the cohorts, we propose a FLEXible, Optimized, and Realistic (FLEXOR) weighting method appropriate for integrative analyses. We develop new weighted estimators for unconfounded inferences on wide-ranging population-level features and estimands relevant to group comparisons of quantitative, categorical, or multivariate outcomes. Asymptotic properties of these estimators are examined. Through simulation studies and meta-analyses of TCGA datasets, we demonstrate the versatility and reliability of the proposed weighting strategy, especially for the FLEXOR pseudo-population.

Asunto(s)

RESUMEN

Electronic health records and other sources of observational data are increasingly used for drawing causal inferences. The estimation of a causal effect using these data not meant for research purposes is subject to confounding and irregularly-spaced covariate-driven observation times affecting the inference. A doubly-weighted estimator accounting for these features has previously been proposed that relies on the correct specification of two nuisance models used for the weights. In this work, we propose a novel consistent multiply robust estimator and demonstrate analytically and in comprehensive simulation studies that it is more flexible and more efficient than the only alternative estimator proposed for the same setting. It is further applied to data from the Add Health study in the United States to estimate the causal effect of therapy counseling on alcohol consumption in American adolescents.

Asunto(s)

RESUMEN

The test-negative design (TND) is an observational study design to evaluate vaccine effectiveness (VE) that enrolls individuals receiving diagnostic testing for a target disease as part of routine care. VE is estimated as one minus the adjusted odds ratio of testing positive versus negative comparing vaccinated and unvaccinated patients. Although the TND is related to case-control studies, it is distinct in that the ratio of test-positive cases to test-negative controls is not typically pre-specified. For both types of studies, sparse cells are common when vaccines are highly effective. We consider the implications of these features on power for the TND. We use simulation studies to explore three hypothesis-testing procedures and associated sample size calculations for case-control and TND studies. These tests, all based on a simple logistic regression model, are a standard Wald test, a continuity-corrected Wald test, and a score test. The Wald test performs poorly in both case-control and TND when VE is high because the number of vaccinated test-positive cases can be low or zero. Continuity corrections help to stabilize the variance but induce bias. We observe superior performance with the score test as the variance is pooled under the null hypothesis of no group differences. We recommend using a score-based approach to design and analyze both case-control and TND. We propose a modification to the TND score sample size to account for additional variability in the ratio of controls over cases. This work enhances our understanding of the data generating mechanism in a test-negative design (TND) and how it is distinct from that of a case-control study due to its passive recruitment of controls.

Asunto(s)

RESUMEN

Observational studies are frequently used to estimate the effect of an exposure or treatment on an outcome. To obtain an unbiased estimate of the treatment effect, it is crucial to measure the exposure accurately. A common type of exposure misclassification is recall bias, which occurs in retrospective cohort studies when study subjects may inaccurately recall their past exposure. Particularly challenging is differential recall bias in the context of self-reported binary exposures, where the bias may be directional rather than random and its extent varies according to the outcomes experienced. This paper makes several contributions: (1) it establishes bounds for the average treatment effect even when a validation study is not available; (2) it proposes multiple estimation methods across various strategies predicated on different assumptions; and (3) it suggests a sensitivity analysis technique to assess the robustness of the causal conclusion, incorporating insights from prior research. The effectiveness of these methods is demonstrated through simulation studies that explore various model misspecification scenarios. These approaches are then applied to investigate the effect of childhood physical abuse on mental health in adulthood.

Asunto(s)

RESUMEN

Researchers often estimate the association between the hazard of a time-to-event outcome and the characteristics of individuals and the clusters in which individuals are nested. Lin and Wei's robust variance estimator is often used with a Cox regression model fit to clustered data. Recently, alternative variance estimators have been proposed: the Fay-Graubard estimator, the Kauermann-Carroll estimator, and the Mancl-DeRouen estimator. Using Monte Carlo simulations, we found that, when fitting a marginal Cox regression model with both individual-level and cluster-level covariates: (i) in the presence of weak to moderate within-cluster homogeneity of outcomes, the Lin-Wei variance estimator can result in estimates of the SE with moderate bias when the number of clusters is fewer than 20-30, while in the presence of strong within-cluster homogeneity, it can result in biased estimation even when the number of clusters is as large as 100; (ii) when the number of clusters was less than approximately 20, the Fay-Graubard variance estimator tended to result in estimates of SE with the lowest bias; (iii) when the number of clusters exceeded approximately 20, the Mancl-DeRouen estimator tended to result in estimated standard errors with the lowest bias; (iv) the Mancl-DeRouen estimator used with a t-distribution tended to result in 95% confidence that had the best performance of the estimators; (v) when the magnitude of within-cluster homogeneity in outcomes was strong or very strong, all methods resulted in confidence intervals with lower than advertised coverage rates even when the number of clusters was very large.

Asunto(s)

RESUMEN

Propensity score matching is commonly used to draw causal inference from observational survival data. However, its asymptotic properties have yet to be established, and variance estimation is still open to debate. We derive the statistical properties of the propensity score matching estimator of the marginal causal hazard ratio based on matching with replacement and a fixed number of matches. We also propose a double-resampling technique for variance estimation that takes into account the uncertainty due to propensity score estimation prior to matching.

Asunto(s)

RESUMEN

Sequential multiple assignment randomized trials (SMARTs) are the gold standard for estimating optimal dynamic treatment regimes (DTRs), but are costly and require a large sample size. We introduce the multi-stage augmented Q-learning estimator (MAQE) to improve efficiency of estimation of optimal DTRs by augmenting SMART data with observational data. Our motivating example comes from the Back Pain Consortium, where one of the overarching aims is to learn how to tailor treatments for chronic low back pain to individual patient phenotypes, knowledge which is lacking clinically. The Consortium-wide collaborative SMART and observational studies within the Consortium collect data on the same participant phenotypes, treatments, and outcomes at multiple time points, which can easily be integrated. Previously published single-stage augmentation methods for integration of trial and observational study (OS) data were adapted to estimate optimal DTRs from SMARTs using Q-learning. Simulation studies show the MAQE, which integrates phenotype, treatment, and outcome information from multiple studies over multiple time points, more accurately estimates the optimal DTR, and has a higher average value than a comparable Q-learning estimator without augmentation. We demonstrate this improvement is robust to a wide range of trial and OS sample sizes, addition of noise variables, and effect sizes.

Asunto(s)

RESUMEN

Estimating causal effects from large experimental and observational data has become increasingly prevalent in both industry and research. The bootstrap is an intuitive and powerful technique used to construct standard errors and confidence intervals of estimators. Its application however can be prohibitively demanding in settings involving large data. In addition, modern causal inference estimators based on machine learning and optimization techniques exacerbate the computational burden of the bootstrap. The bag of little bootstraps has been proposed in non-causal settings for large data but has not yet been applied to evaluate the properties of estimators of causal effects. In this article, we introduce a new bootstrap algorithm called causal bag of little bootstraps for causal inference with large data. The new algorithm significantly improves the computational efficiency of the traditional bootstrap while providing consistent estimates and desirable confidence interval coverage. We describe its properties, provide practical considerations, and evaluate the performance of the proposed algorithm in terms of bias, coverage of the true 95% confidence intervals, and computational time in a simulation study. We apply it in the evaluation of the effect of hormone therapy on the average time to coronary heart disease using a large observational data set from the Women's Health Initiative.

Asunto(s)

Asunto(s)

RESUMEN

Most persons living with HIV (PLWH) experience a significant restoration of their immunity associated with successful inhibition of viral replication after antiretroviral therapy (ART) initiation. Nevertheless, with the robust quantitative and qualitative restoration of CD4+ T-lymphocytes, a fraction of patients co-infected with tuberculosis develop immune reconstitution inflammatory syndrome (TB-IRIS), a dysregulated inflammatory response that can be associated with significant tissue damage. Several studies underscored the role of adaptive immune cells in IRIS pathogenesis, but to what degree T lymphocyte activation contributes to TB-IRIS development remains largely elusive. Here, we sought to dissect the phenotypic landscape of T lymphocyte activation in PLWH coinfected with TB inititating ART, focusing on characterization of the profiles linked to development of TB-IRIS. We confirmed previous observations demonstrating that TB-IRIS individuals display pronounced CD4+ lymphopenia prior to ART initiation. Additionally, we found an ART-induced increase in T lymphocyte activation, proliferation and cytotoxicity among TB-IRIS patients. Importantly, we demonstrate that TB-IRIS subjects display higher frequencies of cytotoxic CD8+ T lymphocytes which is not affected by ART. Moreover, These patients exhibit higher levels of activated (HLA-DR+) and profilerative (Ki-67+) CD4+ T cells after ART commencenment than their Non-IRIS counterparts. Our network analysis reveal significant negative correlations between Total CD4+ T cells counts and the frequencies of Cytotoxic CD8+ T cells in our study population which could suggest the existance of compensatory mechanisms for Mtb-infected cells elimination in the face of severe CD4+ T cell lymphopenia. We also investigated the correlation between T lymphocyte activation profiles and the abundance of several inflammatory molecules in plasma. We applied unsupervised machine learning techniques to predict and diagnose TB-IRIS before and during ART. Our analyses suggest that CD4+ T cell activation markers are good TB-IRIS predictors, whereas the combination of CD4+ and CD8+ T cells markers are better at diagnosing TB-IRIS patients during IRIS events Overall, our findings contribute to a more refined understanding of immunological mechanisms in TB-IRIS pathogenesis that may assist in new diagnostic tools and more targeted patient management.

Asunto(s)

RESUMEN

Hypothesis generation in observational, biomedical data science often starts with computing an association or identifying the statistical relationship between a dependent and an independent variable. However, the outcome of this process depends fundamentally on modeling strategy, with differing strategies generating what can be called "vibration of effects" (VoE). VoE is defined by variation in associations that often lead to contradictory results. Here, we present a computational tool capable of modeling VoE in biomedical data by fitting millions of different models and comparing their output. We execute a VoE analysis on a series of widely reported associations (e.g., carrot intake associated with eyesight) with an extended additional focus on lifestyle exposures (e.g., physical activity) and components of the Framingham Risk Score for cardiovascular health (e.g., blood pressure). We leveraged our tool for potential confounder identification, investigating what adjusting variables are responsible for conflicting models. We propose modeling VoE as a critical step in navigating discovery in observational data, discerning robust associations, and cataloging adjusting variables that impact model output.

Asunto(s)

RESUMEN

Informações sobre protocolos de pesquisas científicas que envolvem seres humanos relativas ao coronavírus e/ou à Covid-19, aprovadas na Conep.

Asunto(s)

RESUMEN

Informações sobre protocolos de pesquisa científicas que envolvem seres humanos relativas ao Coronavírus e/ou Covid-19, aprovadas pela Conep.

Asunto(s)

RESUMEN

Informações sobre protocolos de pesquisa científicas que envolvem seres humanos relativas ao coronavírus e/ou Covid-19, aprovadas pela Conep.

Asunto(s)

RESUMEN

The main systemic therapy for the management of hormone-sensitive prostate cancer (PC) is androgen deprivation therapy (ADT), with the use of long-acting luteinizing hormone releasing-hormone (LHRH) agonists considered the main form of ADT used in clinical practice to obtain castration in PC. The concomitant administration of antiandrogens for the first weeks could reduce the incidence of clinical effects related to the testosterone flare-up in the first injection of LHRH. On the contrary, Gonadotropin Rh (GnRH) antagonists produce a rapid decrease of testosterone levels without the initial flare-up, with degarelix commonly used in clinical practice to induce castration in PC patients. Even if no long-term data are reported in terms of survival to define a superiority of GnRH or LHRH, for oncological efficacy and PC control, data from randomized clinical trials and from real-life experiences, suggest a difference in cardiovascular risk of patients starting ADT. The age-related decline in testosterone levels may represent a factor connected to the increase of cardiovascular disease risk, however, the role of ADT in increasing CV events remains controversial. For these reasons, the aim of the paper is to synthesize the difference in cardiovascular risk between LHRH and degarelix in patients undergoing ADT. A difference in cardiovascular risk could be indeed an important parameter in the evaluation of these two forms of castration therapy. The Randomized trials analyzed in this paper sustain a possible protective role for degarelix versus LHRH agonists in reducing the rate of new CV events and interventions in the short-term period. On the contrary, real-word data are contradictory in different national experiences and are strongly conditioned by huge differences between the LHRH agonists group and the degarelix group.

Asunto(s)

RESUMEN

Fundamentos: Las prácticas alimentarias veg(etari)anas son cada vez más frecuentes a nivel global y estimaciones recientes indican que 9% de la población de Argentina adhiere a las mismas. En esta investigación nos propusimos analizar características sociodemográficas, estado nutricional antropométrico y alimentación habitual de población ovo-lacto-vegetariana(OLV) y vegana (VGN) residente en los tres principales centros urbanos del país. Métodos: Para este estudio observacional, exploratorio y de corte transversal, se diseñó un cuestionario de encuesta que fue completado online por 282 personas. Para el análisis de datos se utilizó el programa estadístico STATA 14.0. Resultados: Los participantes presentan un peso dentro de los parámetros recomendados y llevan una dieta saludable, con mayor presencia de verduras, frutas, cereales integrales y pseudocereales, semillas y frutos secos entre la población VGN. No obstante, menos de un tercio cubre los requerimientos en cuanto al consumo diario de agua y, entre la población OLV, se observó un bajo uso de suplementos de vitamina B12. Conclusiones: Estos hallazgos coinciden con los de investigaciones desarrolladas previamente, a la vez que indican la necesidad de difundir las recomendaciones para este grupopoblacional que se encuentra en franco crecimiento tanto a nivel nacional como global. (AU)

Background: Veg(etari)an eating practices are increasingly frequent globally, and recent estimates indicate that9% of the Argentinian population adheres to such diets. In this research, we aimed to analyze sociodemographic characteristics, anthropometric nutritional status, and usual diet of ovo-lacto-vegetarian (OLV) and vegan (VGN) population of the three main urban centers of the country. Methods: For this observational, exploratory, cross-sectional study, a survey questionnaire was designed and completed online by 282 respondents. The statistical program STATA 14.0 was used for the analysis of data. Results: Participants present a weight within the recommended parameters and have a healthy diet, with a greater presence of vegetables, fruits, whole grains and pseudocereals, seeds and nuts among the VGN population. However, less than a third covers the requirements of daily water consumption, and a low use of vitamin B12 supplements was observed among the OLV population. Conclusions: These findings are in line with previous research and indicate the need to disseminate recommendationsfor this population group, which is growing rapidly both nationally and globally. (AU)

Asunto(s)

RESUMEN

OBJECTIVE: To date, no systematic reviews and meta-analysis on the global epidemiology of acromegaly are available in the literature. The aims of this study are to provide a systematic review and a meta-analysis of the global epidemiology of acromegaly and to evaluate the quality of study reporting for the identified studies. METHODS: MEDLINE, EMBASE and The Cochrane Library databases were searched for studies assessing the epidemiology of acromegaly from inception until 31 January 2020. We included original observational studies written in English, reporting acromegaly prevalence and/or incidence for a well-defined geographic area. Two reviewers independently extracted data and performed quality assessments. Prevalence and incidence pooled estimates were derived by performing a random-effects meta-analysis. RESULTS: A total of 32 studies were included in the systematic review, and 22 of them were included in the meta-analysis. The pooled prevalence of acromegaly was 5.9 (95% CI: 4.4-7.9) per 100 000 persons, while the incidence rate (IR) was 0.38 (95% CI: 0.32-0.44) cases per 100 000 person-years. For both prevalence and IR, considerable between-study heterogeneity was found (I2 = 99.3 and 86.0%, respectively). The quality of study reporting was rated as the medium for 20 studies and low for 12 studies. CONCLUSIONS: Although the largest amount of heterogeneity was due to the high precision of the studies' estimates, data source and geographic area could represent relevant study-level factors which could explain about 50% of the total between-study variability. Large-scale high-quality studies on the epidemiology of acromegaly are warranted to help the public health system in making decisions.

Asunto(s)

RESUMEN

Importance: General health checks, also known as general medical examinations, periodic health evaluations, checkups, routine visits, or wellness visits, are commonly performed in adult primary care to identify and prevent disease. Although general health checks are often expected and advocated by patients, clinicians, insurers, and health systems, others question their value. Observations: Randomized trials and observational studies with control groups reported in prior systematic reviews and an updated literature review through March 2021 were included. Among 19 randomized trials (906 to 59 616 participants; follow-up, 1 to 30 years), 5 evaluated a single general health check, 7 evaluated annual health checks, 1 evaluated biannual checks, and 6 evaluated health checks delivered at other frequencies. Twelve of 13 observational studies (240 to 471 415 participants; follow-up, cross-sectional to 5 years) evaluated a single general health check. General health checks were generally not associated with decreased mortality, cardiovascular events, or cardiovascular disease incidence. For example, in the South-East London Screening Study (n = 7229), adults aged 40 to 64 years who were invited to 2 health checks over 2 years, compared with adults not invited to screening, experienced no 8-year mortality benefit (6% vs 5%). General health checks were associated with increased detection of chronic diseases, such as depression and hypertension; moderate improvements in controlling risk factors, such as blood pressure and cholesterol; increased clinical preventive service uptake, such as colorectal and cervical cancer screening; and improvements in patient-reported outcomes, such as quality of life and self-rated health. In the Danish Check-In Study (n = 1104), more patients randomized to receive to a single health check, compared with those randomized to receive usual care, received a new antidepressant prescription over 1 year (5% vs 2%; P = .007). In a propensity score-matched analysis (n = 8917), a higher percentage of patients who attended a Medicare Annual Wellness Visit, compared with those who did not, underwent colorectal cancer screening (69% vs 60%; P < .01). General health checks were sometimes associated with modest improvements in health behaviors such as physical activity and diet. In the OXCHECK trial (n = 4121), fewer patients randomized to receive annual health checks, compared with those not randomized to receive health checks, exercised less than once per month (68% vs 71%; difference, 3.3% [95% CI, 0.5%-6.1%]). Potential adverse effects in individual studies included an increased risk of stroke and increased mortality attributed to increased completion of advance directives. Conclusions and Relevance: General health checks were not associated with reduced mortality or cardiovascular events, but were associated with increased chronic disease recognition and treatment, risk factor control, preventive service uptake, and improved patient-reported outcomes. Primary care teams may reasonably offer general health checks, especially for groups at high risk of overdue preventive services, uncontrolled risk factors, low self-rated health, or poor connection or inadequate access to primary care.

Asunto(s)

RESUMEN

Informações sobre protocolos de pesquisa científicas que envolvem seres humanos relativas ao coronavírus e/ou Covid-19, aprovadas pela Conep.

Asunto(s)