Imputação múltipla de dados faltantes: exemplo de aplicação no Estudo Pró-Saúde

Dados faltantes são um problema comum em estudos epidemiológicos e, dependendo da forma como ocorrem, as estimativas dos parâmetros de interesse podem estar enviesadas. A literatura aponta algumas técnicas para se lidar com a questão, e, a imputação múltipla vem recebendo destaque nos últimos anos. Esta dissertação apresenta os resultados da utilização da imputação múltipla de dados no contexto do Estudo Pró-Saúde, um estudo longitudinal entre funcionários técnico-administrativos de uma universidade no Rio de Janeiro. No primeiro estudo, após simulação da ocorrência de dados faltantes, imputou-se a variável cor/raça das participantes, e aplicou-se um modelo de análise de sobrevivência previamente estabelecido, tendo como desfecho a história auto-relatada de miomas uterinos. Houve replicação do procedimento (100 vezes) para se determinar a distribuição dos coeficientes e erros-padrão das estimativas da variável de interesse. Apesar da natureza transversal dos dados aqui utilizados (informações da linha de base do Estudo Pró-Saúde, coletadas em 1999 e 2001), buscou-se resgatar a história do seguimento das participantes por meio de seus relatos, criando uma situação na qual a utilização do modelo de riscos proporcionais de Cox era possível. Nos cenários avaliados, a imputação demonstrou resultados satisfatórios, inclusive quando da avaliação de performance realizada. A técnica demonstrou um bom desempenho quando o mecanismo de ocorrência dos dados faltantes era do tipo MAR (Missing At Random) e o percentual de não-resposta era de 10%. Ao se imputar os dados e combinar as estimativas obtidas nos 10 bancos (m=10) gerados, o viés das estimativas era de 0,0011 para a categoria preta e 0,0015 para pardas, corroborando a eficiência da imputação neste cenário. Demais configurações também apresentaram resultados semelhantes. No segundo artigo, desenvolve-se um tutorial para aplicação da imputação múltipla em estudos epidemiológicos, que deverá facilitar a utilização da técnica por pesquisadores brasileiros ainda não familiarizados com o procedimento. São apresentados os passos básicos e decisões necessárias para se imputar um banco de dados, e um dos cenários utilizados no primeiro estudo é apresentado como exemplo de aplicação da técnica. Todas as análises foram conduzidas no programa estatístico R, versão 2.15 e os scripts utilizados são apresentados ao final do texto.

A (des)naturalização da pessoa jurídica: subjetividade, titularidade e atividade

O presente trabalho, a partir da revisão do conceito de personificação, pretende investigar como se desenvolve o processo de naturalização da pessoa jurídica e os eventuais prejuízos decorrentes para a tutela do ser humano nas organizações sociais e para a descrição do fenômeno empresarial. Sob o prisma da filosofia da linguagem, realiza-se uma revisão bibliográfica sobre a utilização do termo pessoa jurídica no discurso do Direito, destacando, principalmente, a desconstrução promovida pelo chamado nominalismo. São, ainda, propostos critérios para a identificação da naturalização, a partir de uma gradação que procura segregar os diversos grupos de casos que lhe são correlatos. A tese foi estruturada em três etapas: subjetividade, titularidade e atividade. Ao cotejar a pessoa natural com a pessoa jurídica, em cada um desses planos, espera-se revelar a assimetria de razões que separam a personificação do ser humano daquela presente nas sociedades, associações e fundações. Do questionamento do individualismo metodológico presente na noção de pessoa jurídica resulta a reconstrução do próprio sistema analítico de conceitos do discurso jurídico, com a revisão das ideias de imputação, relação jurídica, titularidade e autonomia patrimonial.

一种基于动态自适应数据窗口的模糊k-均值聚类缺失数据估算算法

完整性是数据质量的一个重要维度,由于数据本身固有的不确定性、采集的随机性及不准确性,导致现实应用中产生了大量具有如下特点的数据集:1)数据规模庞大;2)数据往往是不完整、不准确的.因此将大规模数据集分段到不同的数据窗口中处理是数据处理的重要方法,但缺失数据估算的相关研究大都忽视了数据集的特点和窗口的应用,而且回定大小的数据窗17容易造成算法的准确性和性能受窗口大小及窗口内数据值分布的影响.假设数据满足一定的领域相关的约束,首先提出了一种新的基于时间的动态自适应数据窗口检测算法,并基于此窗口提出了一种改进的模糊k-均值聚类算法来进行不完整数据的缺失数据估算.实验表明较之其他算法,不仅能更适应数据集的特点,具有较好的性能,而且能够保证准确性.

Missing data in randomized clinical trials for weight loss: scope of the problem, state of the field, and performance of statistical methods.

BACKGROUND: Dropouts and missing data are nearly-ubiquitous in obesity randomized controlled trails, threatening validity and generalizability of conclusions. Herein, we meta-analytically evaluate the extent of missing data, the frequency with which various analytic methods are employed to accommodate dropouts, and the performance of multiple statistical methods. METHODOLOGY/PRINCIPAL FINDINGS: We searched PubMed and Cochrane databases (2000-2006) for articles published in English and manually searched bibliographic references. Articles of pharmaceutical randomized controlled trials with weight loss or weight gain prevention as major endpoints were included. Two authors independently reviewed each publication for inclusion. 121 articles met the inclusion criteria. Two authors independently extracted treatment, sample size, drop-out rates, study duration, and statistical method used to handle missing data from all articles and resolved disagreements by consensus. In the meta-analysis, drop-out rates were substantial with the survival (non-dropout) rates being approximated by an exponential decay curve (e(-lambdat)) where lambda was estimated to be .0088 (95% bootstrap confidence interval: .0076 to .0100) and t represents time in weeks. The estimated drop-out rate at 1 year was 37%. Most studies used last observation carried forward as the primary analytic method to handle missing data. We also obtained 12 raw obesity randomized controlled trial datasets for empirical analyses. Analyses of raw randomized controlled trial data suggested that both mixed models and multiple imputation performed well, but that multiple imputation may be more robust when missing data are extensive. CONCLUSION/SIGNIFICANCE: Our analysis offers an equation for predictions of dropout rates useful for future study planning. Our raw data analyses suggests that multiple imputation is better than other methods for handling missing data in obesity randomized controlled trials, followed closely by mixed models. We suggest these methods supplant last observation carried forward as the primary method of analysis.

Importance of prostate volume in the European Randomised Study of Screening for Prostate Cancer (ERSPC) risk calculators: results from the prostate biopsy collaborative group.

OBJECTIVES: To compare the predictive performance and potential clinical usefulness of risk calculators of the European Randomized Study of Screening for Prostate Cancer (ERSPC RC) with and without information on prostate volume. METHODS: We studied 6 cohorts (5 European and 1 US) with a total of 15,300 men, all biopsied and with pre-biopsy TRUS measurements of prostate volume. Volume was categorized into 3 categories (25, 40, and 60 cc), to reflect use of digital rectal examination (DRE) for volume assessment. Risks of prostate cancer were calculated according to a ERSPC DRE-based RC (including PSA, DRE, prior biopsy, and prostate volume) and a PSA + DRE model (including PSA, DRE, and prior biopsy). Missing data on prostate volume were completed by single imputation. Risk predictions were evaluated with respect to calibration (graphically), discrimination (AUC curve), and clinical usefulness (net benefit, graphically assessed in decision curves). RESULTS: The AUCs of the ERSPC DRE-based RC ranged from 0.61 to 0.77 and were substantially larger than the AUCs of a model based on only PSA + DRE (ranging from 0.56 to 0.72) in each of the 6 cohorts. The ERSPC DRE-based RC provided net benefit over performing a prostate biopsy on the basis of PSA and DRE outcome in five of the six cohorts. CONCLUSIONS: Identifying men at increased risk for having a biopsy detectable prostate cancer should consider multiple factors, including an estimate of prostate volume.

The validity of a latent class typology of adolescent drinking patterns

Objectives: This study examined the validity of a latent class typology of adolescent drinking based on four alcohol dimensions; frequency of drinking, quantity consumed, frequency of binge drinking and the number of alcohol related problems encountered. Method: Data used were from the 1970 British Cohort Study sixteen-year-old follow-up. Partial or complete responses to the selected alcohol measures were provided by 6,516 cohort members. The data were collected via a series of postal questionnaires. Results: A five class LCA typology was constructed. Around 12% of the sample were classified as �hazardous drinkers� reporting frequent drinking, high levels of alcohol consumed, frequent binge drinking and multiple alcohol related problems. Multinomial logistic regression, with multiple imputation for missing data, was used to assess the covariates of adolescent drinking patterns. Hazardous drinking was associated with being white, being male, having heavy drinking parents (in particular fathers), smoking, illicit drug use, and minor and violent offending behaviour. Non-significant associations were found between drinking patterns and general mental health and attention deficient disorder. Conclusion: The latent class typology exhibited concurrent validity in terms of its ability to distinguish respondents across a number of alcohol and non-alcohol indicators. Notwithstanding a number of limitations, latent class analysis offers an alternative data reduction method for the construction of drinking typologies that addresses known weaknesses inherent in more tradition classification methods.

A genome-wide association study provides evidence for association of chromosome 8p23 (MYP10) and 10q21.1 (MYP15) with high myopia in the French population.

PURPOSE. Myopia is a complex trait affected by both genetic and environmental factors. High myopia is associated with increased risk of sight-threatening eye disorders such as retinal detachment. The purpose of this genome-wide association study was to identify susceptibility genes contributing to high myopia in the French population. METHODS. High myopic cases were genotyped using Affymetrix SNP 6.0 chips and population controls were selected from the GABRIEL French dataset in which samples were genotyped by Illumina Human610 quad array. The association study was conducted using 152,234 single nucleotide polymorphisms that were present on both manufacturers' chips in 192 high myopic cases and 1064 controls to identify associated regions. Imputation was performed on peak regions. RESULTS. Associations were found at known myopia locus MYP10 on chromosome 8p23 and MYP15 on chromosome 10q21.1. Rs189798 (8p23) and rs10825992 (10q21.1) showed the strongest associations in these regions (P=6.32x10-7 and P=2.17x10-5, respectively). The imputed results at 8p23 showed 2 peaks of interest. The first spanned 30kb including rs189798 between MIR4660 and PPP1R3B with the most significant association at rs17155227 (P=1.07x10-10). The second novel peak was 4kb in length, encompassing MIR124-1 and the MSRA gene, with the strongest association at rs55864141 (P=1.30x10-7). The peak of imputed data at 10q21.1 was 70kb in length between ZWINT and MIR3924, with rs3107503 having the lowest P value (P=1.54x10-7). CONCLUSION. We provide evidence for the association of MYP10 at 8p23 and MYP15 at 10p21.1 with high myopia in the French population and refine these regions of association.

Prevalence and risk factors of depressive symptoms in a Canadian palliative home care population: a cross-sectional study

Background: Depression in palliative care patients is important because of its intrinsic burden and association with elevated physical symptoms, reduced immunity and increased mortality risk. Identifying risk factors associated with depression can enable clinicians to more readily diagnose it, which is important since depression is treatable. The purpose of this cross-sectional study was to determine the prevalence of depressive symptoms and risk factors associated with them in a large sample of palliative home care patients.

Methods: The data come from interRAI Palliative Care assessments completed between 2006 and 2012. The sample (n = 5144) consists of adults residing in Ontario (Canada), receiving home care services, classified as palliative, and not experiencing significant cognitive impairment. Logistic regression identified the risk factors associated with depressive symptoms. The dependent variable was the Depression Rating Scale (DRS) and the independent variables were functional indicators from the interRAI assessment and other variables identified in the literature. We examined the results of the complete case and multiple imputation analyses, and found them to be similar.

Results: The prevalence of depressive symptoms was 9.8%. The risk factors associated with depressive symptoms were (pooled estimates, multiple imputation): low life satisfaction (OR = 3.01 [CI = 2.37-3.82]), severe and moderate sleep disorders (2.56 [2.05-3.19] and 1.56 [1.18-2.06]), health instability (2.12 [1.42-3.18]), caregiver distress 2.01 [1.62-2.51]), daily pain (1.73 [1.35-2.22]), cognitive impairment (1.45 [1.13-1.87]), being female (1.37 [1.11-1.68]), and gastrointestinal symptoms (1.27 [1.03-1.55]). Life satisfaction mediated the effect of prognostic awareness on depressive symptoms.

Conclusions: The prevalence of depressive symptoms in our study was close to the median of 10-20% reported in the palliative care literature, suggesting they are present but by no means inevitable in palliative patients. Most of the factors associated with depressive symptoms in our study are amenable to clinical intervention and often targeted in palliative care programs. Designing interventions to address them can be challenging, however, requiring careful attention to patient preferences, the spectrum of comorbid conditions they face, and their social supports. Life satisfaction was one of the strongest factors associated with depressive symptoms in our study, and is likely to be among the most challenging to address.

SORBS1 gene, a new candidate for diabetic nephropathy: results from a multi-stage genome-wide association study in patients with type 1 diabetes

Aims/hypothesis

Effect of a Web-Based Behavior Change Program on Weight Loss and Cardiovascular Risk Factors in Overweight and Obese Adults at High Risk of Developing Cardiovascular Disease:Randomized Controlled Trial

BACKGROUND: Web-based programs are a potential medium for supporting weight loss because of their accessibility and wide reach. Research is warranted to determine the shorter- and longer-term effects of these programs in relation to weight loss and other health outcomes.

OBJECTIVE: The aim was to evaluate the effects of a Web-based component of a weight loss service (Imperative Health) in an overweight/obese population at risk of cardiovascular disease (CVD) using a randomized controlled design and a true control group.

METHODS: A total of 65 overweight/obese adults at high risk of CVD were randomly allocated to 1 of 2 groups. Group 1 (n=32) was provided with the Web-based program, which supported positive dietary and physical activity changes and assisted in managing weight. Group 2 continued with their usual self-care (n=33). Assessments were conducted face-to-face. The primary outcome was between-group change in weight at 3 months. Secondary outcomes included between-group change in anthropometric measurements, blood pressure, lipid measurements, physical activity, and energy intake at 3, 6, and 12 months. Interviews were conducted to explore participants' views of the Web-based program.

RESULTS: Retention rates for the intervention and control groups at 3 months were 78% (25/32) vs 97% (32/33), at 6 months were 66% (21/32) vs 94% (31/33), and at 12 months were 53% (17/32) vs 88% (29/33). Intention-to-treat analysis, using baseline observation carried forward imputation method, revealed that the intervention group lost more weight relative to the control group at 3 months (mean -3.41, 95% CI -4.70 to -2.13 kg vs mean -0.52, 95% CI -1.55 to 0.52 kg, P<.001), at 6 months (mean -3.47, 95% CI -4.95 to -1.98 kg vs mean -0.81, 95% CI -2.23 to 0.61 kg, P=.02), but not at 12 months (mean -2.38, 95% CI -3.48 to -0.97 kg vs mean -1.80, 95% CI -3.15 to -0.44 kg, P=.77). More intervention group participants lost ≥5% of their baseline body weight at 3 months (34%, 11/32 vs 3%, 1/33, P<.001) and 6 months (41%, 13/32 vs 18%, 6/33, P=.047), but not at 12 months (22%, 7/32 vs 21%, 7/33, P=.95) versus control group. The intervention group showed improvements in total cholesterol, triglycerides, and adopted more positive dietary and physical activity behaviors for up to 3 months verus control; however, these improvements were not sustained.

CONCLUSIONS: Although the intervention group had high attrition levels, this study provides evidence that this Web-based program can be used to initiate clinically relevant weight loss and lower CVD risk up to 3-6 months based on the proportion of intervention group participants losing ≥5% of their body weight versus control group. It also highlights a need for augmenting Web-based programs with further interventions, such as in-person support to enhance engagement and maintain these changes.

Using interviewer random effects to remove selection bias from HIV prevalence estimates

Background: Selection bias in HIV prevalence estimates occurs if non-participation in testing is correlated with HIV status. Longitudinal data suggests that individuals who know or suspect they are HIV positive are less likely to participate in testing in HIV surveys, in which case methods to correct for missing data which are based on imputation and observed characteristics will produce biased results. Methods: The identity of the HIV survey interviewer is typically associated with HIV testing participation, but is unlikely to be correlated with HIV status. Interviewer identity can thus be used as a selection variable allowing estimation of Heckman-type selection models. These models produce asymptotically unbiased HIV prevalence estimates, even when non-participation is correlated with unobserved characteristics, such as knowledge of HIV status. We introduce a new random effects method to these selection models which overcomes non-convergence caused by collinearity, small sample bias, and incorrect inference in existing approaches. Our method is easy to implement in standard statistical software, and allows the construction of bootstrapped standard errors which adjust for the fact that the relationship between testing and HIV status is uncertain and needs to be estimated. Results: Using nationally representative data from the Demographic and Health Surveys, we illustrate our approach with new point estimates and confidence intervals (CI) for HIV prevalence among men in Ghana (2003) and Zambia (2007). In Ghana, we find little evidence of selection bias as our selection model gives an HIV prevalence estimate of 1.4% (95% CI 1.2% – 1.6%), compared to 1.6% among those with a valid HIV test. In Zambia, our selection model gives an HIV prevalence estimate of 16.3% (95% CI 11.0% - 18.4%), compared to 12.1% among those with a valid HIV test. Therefore, those who decline to test in Zambia are found to be more likely to be HIV positive. Conclusions: Our approach corrects for selection bias in HIV prevalence estimates, is possible to implement even when HIV prevalence or non-participation is very high or very low, and provides a practical solution to account for both sampling and parameter uncertainty in the estimation of confidence intervals. The wide confidence intervals estimated in an example with high HIV prevalence indicate that it is difficult to correct statistically for the bias that may occur when a large proportion of people refuse to test.

Adjusting HIV Prevalence Estimates for Non-participation: an Application to Demographic Surveillance

Introduction: HIV testing is a cornerstone of efforts to combat the HIV epidemic, and testing conducted as part of surveillance provides invaluable data on the spread of infection and the effectiveness of campaigns to reduce the transmission of HIV. However, participation in HIV testing can be low, and if respondents systematically select not to be tested because they know or suspect they are HIV positive (and fear disclosure), standard approaches to deal with missing data will fail to remove selection bias. We implemented Heckman-type selection models, which can be used to adjust for missing data that are not missing at random, and established the extent of selection bias in a population-based HIV survey in an HIV hyperendemic community in rural South Africa.

Methods: We used data from a population-based HIV survey carried out in 2009 in rural KwaZulu-Natal, South Africa. In this survey, 5565 women (35%) and 2567 men (27%) provided blood for an HIV test. We accounted for missing data using interviewer identity as a selection variable which predicted consent to HIV testing but was unlikely to be independently associated with HIV status. Our approach involved using this selection variable to examine the HIV status of residents who would ordinarily refuse to test, except that they were allocated a persuasive interviewer. Our copula model allows for flexibility when modelling the dependence structure between HIV survey participation and HIV status.

Results: For women, our selection model generated an HIV prevalence estimate of 33% (95% CI 27–40) for all people eligible to consent to HIV testing in the survey. This estimate is higher than the estimate of 24% generated when only information from respondents who participated in testing is used in the analysis, and the estimate of 27% when imputation analysis is used to predict missing data on HIV status. For men, we found an HIV prevalence of 25% (95% CI 15–35) using the selection model, compared to 16% among those who participated in testing, and 18% estimated with imputation. We provide new confidence intervals that correct for the fact that the relationship between testing and HIV status is unknown and requires estimation.

Conclusions: We confirm the feasibility and value of adopting selection models to account for missing data in population-based HIV surveys and surveillance systems. Elements of survey design, such as interviewer identity, present the opportunity to adopt this approach in routine applications. Where non-participation is high, true confidence intervals are much wider than those generated by standard approaches to dealing with missing data suggest.

Pleiotropic analysis of cancer risk loci on esophageal adenocarcinoma risk

Background: Several cancer-associated loci identified from genome-wide association studies (GWAS) have been associated with risks of multiple cancer sites, suggesting pleiotropic effects. We investigated whether GWAS-identified risk variants for other common cancers are associated with risk of esophageal adenocarcinoma (EA) or its precursor, Barrett's esophagus. 

Methods: We examined the associations between risks of EA and Barrett's esophagus and 387 SNPs that have been associated with risks of other cancers, by using genotype imputation data on 2,163 control participants and 3,885 (1,501 EA and 2,384 Barrett's esophagus) case patients from the Barrett's and Esophageal Adenocarcinoma Genetic Susceptibility Study, and investigated effect modification by smoking history, body mass index (BMI), and reflux/heartburn. 

Results: After correcting for multiple testing, none of the tested 387 SNPs were statistically significantly associated with risk of EA or Barrett's esophagus. No evidence of effect modification by smoking, BMI, or reflux/heartburn was observed. 

Conclusions: Genetic risk variants for common cancers identified from GWAS appear not to be associated with risks of EA or Barrett's esophagus. 

Impact: To our knowledge, this is the first investigation of pleiotropic genetic associations with risks of EA and Barrett's esophagus.

Impaired orthostatic blood pressure recovery and cognitive performance at two-year follow up in older adults: The Irish Longitudinal Study on Ageing

Background: Prospective investigations of the association between impaired orthostatic blood pressure (BP) regulation and cognitive decline in older adults are limited, and findings to-date have been mixed. The aim of this study was to determine whether impaired recovery of orthostatic BP was associated with change in cognitive function over a 2-year period, in a population based sample of community dwelling older adults. 

Methods: Data from the first two waves of the Irish Longitudinal Study on Ageing were analysed. Orthostatic BP was measured during a lying to standing orthostatic stress protocol at wave 1 using beat-to-beat digital plethysmography, and impaired recovery of BP at 40 s post stand was investigated. Cognitive function was assessed at wave 1 and wave 2 (2 years later) using the Mini-Mental State Exam (MMSE), verbal fluency and word recall tasks. 

Results: After adjustment for measured, potential confounders, and multiple imputation for missing data, the change in the number of errors between waves on the MMSE was 10 % higher [IRR (95 % CI) = 1.10 (0.96, 1.26)] in those with impaired recovery at 40 s. However, this was not statistically significant (p = 0.17). Impaired BP recovery was not associated with change in performance on any of the other cognitive measures. 

Conclusions: There was no clear evidence for an association between impaired recovery of orthostatic BP and change in cognition over a 2-year period in this nationally representative cohort of older adults. Longer follow-up and more detailed cognitive testing would be advantageous to further investigate the relationship between orthostatic BP and cognitive decline.

Statin use after diagnosis of breast cancer and survival: a population-based cohort study

BACKGROUND: Preclinical studies have shown that statins, particularly simvastatin, can prevent growth in breast cancer cell lines and animal models. We investigated whether statins used after breast cancer diagnosis reduced the risk of breast cancer-specific, or all-cause, mortality in a large cohort of breast cancer patients.

METHODS: A cohort of 17,880 breast cancer patients, newly diagnosed between 1998 and 2009, was identified from English cancer registries (from the National Cancer Data Repository). This cohort was linked to the UK Clinical Practice Research Datalink, providing prescription records, and to the Office of National Statistics mortality data (up to 2013), identifying 3694 deaths, including 1469 deaths attributable to breast cancer. Unadjusted and adjusted hazard ratios (HRs) for breast cancer-specific, and all-cause, mortality in statin users after breast cancer diagnosis were calculated using time-dependent Cox regression models. Sensitivity analyses were conducted using multiple imputation methods, propensity score methods and a case-control approach.

RESULTS: There was some evidence that statin use after a diagnosis of breast cancer had reduced mortality due to breast cancer and all causes (fully adjusted HR = 0.84 [95% confidence interval = 0.68-1.04] and 0.84 [0.72-0.97], respectively). These associations were more marked for simvastatin 0.79 (0.63-1.00) and 0.81 (0.70-0.95), respectively.

CONCLUSIONS: In this large population-based breast cancer cohort, there was some evidence of reduced mortality in statin users after breast cancer diagnosis. However, these associations were weak in magnitude and were attenuated in some sensitivity analyses.