Continuous outcome logistic regression for analyzing body mass index distributions.
Ontology highlight
ABSTRACT:
SUBMITTER: Lohse T
PROVIDER: S-EPMC5721934 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:This paper details the design, evaluation, and implementation of a framework for detecting and modeling nonlinearity between a binary outcome and a continuous predictor variable adjusted for covariates in complex samples. The framework provides familiar-looking parameterizations of output in terms of linear slope coefficients and odds ratios. Estimation methods focus on maximum likelihood optimization of piecewise linear free-knot splines formulated as B-splines. Correctly specifying the optimal number and positions of the knots improves the model, but is marked by computational intensity and numerical instability. Our inference methods utilize both parametric and nonparametric bootstrapping. Unlike other nonlinear modeling packages, this framework is designed to incorporate multistage survey sample designs common to nationally representative datasets. We illustrate the approach and evaluate its performance in specifying the correct number of knots under various conditions with an example using body mass index (BMI; kg/m2) and the complex multi-stage sampling design from the Third National Health and Nutrition Examination Survey to simulate binary mortality outcomes data having realistic nonlinear sample-weighted risk associations with BMI. BMI and mortality data provide a particularly apt example and area of application since BMI is commonly recorded in large health surveys with complex designs, often categorized for modeling, and nonlinearly related to mortality. When complex sample design considerations were ignored, our method was generally similar to or more accurate than two common model selection procedures, Schwarz's Bayesian Information Criterion (BIC) and Akaike's Information Criterion (AIC), in terms of correctly selecting the correct number of knots. Our approach provided accurate knot selections when complex sampling weights were incorporated, while AIC and BIC were not effective under these conditions.
| S-EPMC4297674 | biostudies-literature
Project description:ObjectiveTo determine whether the obesity paradox exists in patients who undergo carotid artery stenting (CAS) or carotid endarterectomy (CEA) for symptomatic carotid artery stenosis.MethodsWe combined individual patient data from 2 randomized trials (Endarterectomy vs Angioplasty in Patients with Symptomatic Severe Carotid Stenosis and Stent-Protected Angioplasty vs Carotid Endarterectomy) and 3 centers in a third trial (International Carotid Stenting Study). Baseline body mass index (BMI) was available for 1,969 patients and classified into 4 groups: <20, 20-<25, 25-<30, and ≥30 kg/m2. Primary outcome was stroke or death, investigated separately for the periprocedural and postprocedural period (≤120 days/>120 days after randomization). This outcome was compared between different BMI strata in CAS and CEA patients separately, and in the total group. We performed intention-to-treat multivariable Cox regression analyses.ResultsMedian follow-up was 2.0 years. Stroke or death occurred in 159 patients in the periprocedural (cumulative risk 8.1%) and in 270 patients in the postprocedural period (rate 4.8/100 person-years). BMI did not affect periprocedural risk of stroke or death for patients assigned to CAS (ptrend = 0.39) or CEA (ptrend = 0.77) or for the total group (ptrend = 0.48). Within the total group, patients with BMI 25-<30 had lower postprocedural risk of stroke or death than patients with BMI 20-<25 (BMI 25-<30 vs BMI 20-<25; hazard ratio 0.72; 95% confidence interval 0.55-0.94).ConclusionsBMI is not associated with periprocedural risk of stroke or death; however, BMI 25-<30 is associated with lower postprocedural risk than BMI 20-<25. These observations were similar for CAS and CEA.
| S-EPMC5440240 | biostudies-literature
Project description:Under the logistic regression framework, we propose a forward-backward method, SODA, for variable selection with both main and quadratic interaction terms. In the forward stage, SODA adds in predictors that have significant overall effects, whereas in the backward stage SODA removes unimportant terms to optimize the extended Bayesian Information Criterion (EBIC). Compared with existing methods for variable selection in quadratic discriminant analysis, SODA can deal with high-dimensional data in which the number of predictors is much larger than the sample size and does not require the joint normality assumption on predictors, leading to much enhanced robustness. We further extend SODA to conduct variable selection and model fitting for general index models. Compared with existing variable selection methods based on the Sliced Inverse Regression (SIR) (Li, 1991), SODA requires neither linearity nor constant variance condition and is thus more robust. Our theoretical analysis establishes the variable-selection consistency of SODA under high-dimensional settings, and our simulation studies as well as real-data applications demonstrate superior performances of SODA in dealing with non-Gaussian design matrices in both logistic and general index models.
| S-EPMC7451675 | biostudies-literature
Project description:ObjectivesBeneficial effects of overweight and obesity on mortality after acute myocardial infarction (AMI) have been described as "Body Mass Index (BMI) paradox". However, the effects of BMI is still on debate. We analyzed the association between BMI and 1-year clinical outcomes after AMI.MethodsAmong 13,104 AMI patients registered in Korea Acute Myocardial Infarction Registry-National Institute of Health (KAMIR-NIH) between November 2011 and December 2015, 10,568 patients who eligible for this study were classified into 3 groups according to BMI (Group 1; < 22 kg/m2, 22 ≤ Group 2 < 26 kg/m2, Group 3; ≥ 26 kg/m2). The primary end point was all cause death at 1 year.ResultsOver the median follow-up of 12 months, the event of primary end point occurred more frequently in the Group 1 patients than in the Group 3 patients (primary endpoint: adjusted hazard ratio [aHR], 1.537; 95% confidence interval [CI] 1.177 to 2.007, p = 0.002). Especially, cardiac death played a major role in this effect (aHR, 1.548; 95% confidence interval [CI] 1.128 to 2.124, p = 0.007).ConclusionsHigher BMI appeared to be good prognostic factor on 1-year all cause death after AMI. This result suggests that higher BMI or obesity might confer a protective advantage over the life-quality after AMI.
| S-EPMC6570024 | biostudies-literature
Project description:ImportanceBody mass index (BMI) is used to diagnose obesity in adolescents worldwide, despite evidence that weight does not scale with height squared in adolescents. To account for this, health care providers diagnose obesity using BMI percentiles for each age (BMI z scores), but this does not ensure that BMI is accurate in adolescents.ObjectiveTo compare the accuracy of BMI vs other body fat indices of the form body mass divided by heightn in estimating body fat levels in adolescents.Design, setting, and participantsCross-sectional data from the 1999 to 2006 US National Health and Nutrition Examination Survey were analyzed between September 2015 and December 2016.Main outcomes and measuresDual-energy x-ray absorptiometry and anthropometric data were used to determine changes in body fat levels, body proportions, and the scaling relationships among body mass, height, and percent body fat. To assess the merits of each adiposity index, 3 criteria were used: stability with age, accuracy in estimating percent body fat, and accuracy in classifying adolescents as overweight vs normal weight.ResultsParticipants included 2285 non-Hispanic white participants aged 8 to 29 years. Percent body fat varied with both age and height during adolescence, invalidating the standard weight-to-height regression as the way of finding the optimal body fat index. Because the correct regression model (percent body fat is proportional to mass divided by heightn) suggested that percent body fat scales to height with an exponent closer to 3, we therefore focused on the tri-ponderal mass index (TMI; mass divided by height cubed) as an alternative to BMI z scores. For ages 8 to 17 years, TMI yielded greater stability with age and estimated percent body fat better than BMI (R2?=?0.64 vs 0.38 in boys and R2?=?0.72 vs 0.66 in girls). Moreover, TMI misclassified adolescents as overweight vs normal weight less often than BMI z scores (TMI, 8.4%; 95% CI, 7.3%-9.5% vs BMI, 19.4%; 95% CI, 17.8%-20.0%; P?<?.001) and performed equally as well as updated BMI percentiles derived from the same data set (TMI, 8.4%; 95% CI, 7.3%-9.5% vs BMI, 8.0%; 95% CI, 6.9%-9.1%; P?=?.62).Conclusions and relevanceThe tri-ponderal mass index estimates body fat levels more accurately than BMI in non-Hispanic white adolescents aged 8 to 17 years. Moreover, TMI diagnoses adolescents as overweight more accurately than BMI z scores and equally as well as updated BMI percentiles but is much simpler to use than either because it does not involve complicated percentiles. Taken together, it is worth considering replacing BMI z scores with TMI to estimate body fat levels in adolescents.
| S-EPMC5710345 | biostudies-literature
Project description:BackgroundNational data on body mass index (BMI), computed from self-reported height and weight, is readily available for many populations including the Canadian population. Because self-reported weight is found to be systematically under-reported, it has been proposed that the bias in self-reported BMI can be corrected using equations derived from data sets which include both self-reported and measured height and weight. Such correction equations have been developed and adopted. We aim to evaluate the usefulness (i.e., distributional similarity; sensitivity and specificity; and predictive utility vis-à-vis disease outcomes) of existing and new correction equations in population-based research.MethodsThe Canadian Community Health Surveys from 2005 and 2008 include both measured and self-reported values of height and weight, which allows for construction and evaluation of correction equations. We focused on adults age 18-65, and compared three correction equations (two correcting weight only, and one correcting BMI) against self-reported and measured BMI. We first compared population distributions of BMI. Second, we compared the sensitivity and specificity of self-reported BMI and corrected BMI against measured BMI. Third, we compared the self-reported and corrected BMI in terms of association with health outcomes using logistic regression.ResultsAll corrections outperformed self-report when estimating the full BMI distribution; the weight-only correction outperformed the BMI-only correction for females in the 23-28 kg/m2 BMI range. In terms of sensitivity/specificity, when estimating obesity prevalence, corrected values of BMI (from any equation) were superior to self-report. In terms of modelling BMI-disease outcome associations, findings were mixed, with no correction proving consistently superior to self-report.ConclusionsIf researchers are interested in modelling the full population distribution of BMI, or estimating the prevalence of obesity in a population, then a correction of any kind included in this study is recommended. If the researcher is interested in using BMI as a predictor variable for modelling disease, then both self-reported and corrected BMI result in biased estimates of association.
| S-EPMC4108015 | biostudies-literature
Project description:The relation between obesity and stroke outcome has been disputed. This study was aimed to determine the association of body mass index (BMI) with mortality and functional outcome in patients with acute ischemic stroke. Data were from a national, multi-centre, prospective, hospital-based register: the ChinaQUEST (Quality Evaluation of Stroke Care and Treatment) study. Of 4782 acute ischemic stroke patients, 282 were underweight (BMI?<?18.5?kg/m2), 2306 were normal-weight (BMI 18.5 to?<?24?kg/m2), 1677 were overweight (BMI 24 to <28?kg/m2) and 517 were obese (BMI???28?kg/m2). The risks of death at 12 months and death or high dependency at 3 and 12 months in overweight (HR: 0.97, 95% CI: 0.78-1.20; OR: 0.93, 95% CI: 0.80-1.09; OR: 0.95, 95% CI: 0.81-1.12) and obese patients (HR: 1.07, 95% CI: 0.78-1.48; OR: 0.96, 95% CI: 0.75-1.22; OR: 1.06, 95% CI: 0.83-1.35) did not differ from normal-weight patients significantly after adjusting for baseline characteristics. Underweight patients had significantly increased risks of these three outcomes. In ischemic stroke patients, being overweight or obese was not associated with decreased mortality or better functional recovery but being underweight predicted unfavourable outcomes.
| S-EPMC5451428 | biostudies-other
Project description:Genome wide DNA methylation profiling of MZ twins discordant and concordant for BMI. The Illumina Infinium 450k Human DNA methylation Beadchip was used to obtain DNA methylation profiles across approximately 485,000 CpGs. Samples included 30 MZ twin pairs discordant for BMI and 10 pairs concordant for BMI.
2015-04-20 | GSE43975 | GEO
Project description:ObjectiveUsing meta-regression this paper sets out the minimum change in body mass index-SD score (BMI-SDS) required to improve adiposity as percentage body fat for children and adolescents with obesity.DesignMeta-regression.SettingStudies were identified as part of a large-scale systematic review of the following electronic databases: AMED, Embase, MEDLINE via OVID, Web of Science and CENTRAL via Cochrane library.ParticipantsIndividuals aged 4-19 years with a diagnosis of obesity according to defined BMI thresholds.InterventionsStudies of lifestyle treatment interventions that included dietary, physical activity and/or behavioural components with the objective of reducing obesity were included. Interventions of <2 weeks duration and those that involved surgical and/or pharmacological components (eg, bariatric surgery, drug therapy) were excluded.Primary and secondary outcome measuresTo be included in the review, studies had to report baseline and post-intervention BMI-SDS or change measurements (primary outcome measures) plus one or more of the following markers of metabolic health (secondary outcome measures): adiposity measures other than BMI; blood pressure; glucose; inflammation; insulin sensitivity/resistance; lipid profile; liver function. This paper focuses on adiposity measures only. Further papers in this series will report on other outcome measures.ResultsThis paper explores the potential impact of BMI-SDS reduction in terms of change in percentage body fat. Thirty-nine studies reporting change in mean percentage body fat were analysed. Meta-regression demonstrated that reduction of at least 0.6 in mean BMI-SDS ensured a mean reduction of percentage body fat mass, in the sense that the associated 95% prediction interval for change in mean percentage body fat was wholly negative.ConclusionsInterventions demonstrating reductions of 0.6 BMI-SDS might be termed successful in reducing adiposity, a key purpose of weight management interventions.Trial registration numberCRD42016025317.
| S-EPMC6720247 | biostudies-literature
Project description:Whether overweight or obese end stage renal disease (ESRD) patients are suitable for renal transplantation (RT) is often debated. The objective of this review and meta-analysis was to systematically investigate the outcome of low versus high BMI recipients after RT.Comprehensive searches were conducted in MEDLINE OvidSP, Web of Science, Google Scholar, Embase, and CENTRAL (the Cochrane Library 2014, issue 8). We reviewed four major guidelines that are available regarding (potential) RT recipients. The methodology was in accordance with the Cochrane Handbook for Systematic Reviews of Interventions and written based on the PRISMA statement. The quality assessment of studies was performed by using the GRADE tool. A meta-analysis was performed using Review Manager 5.3. Random-effects models were used.After identifying 5,526 studies addressing this topic, 56 studies were included. We extracted data for 37 outcome measures (including data of more than 209,000 RT recipients), of which 26 could be meta-analysed. The following outcome measures demonstrated significant differences in favour of low BMI (<30) recipients: mortality (RR?=?1.52), delayed graft function (RR?=?1.52), acute rejection (RR?=?1.17), 1-, 2-, and 3-year graft survival (RR?=?0.97, 0.95, and 0.97), 1-, 2-, and 3-year patient survival (RR?=?0.99, 0.99, and 0.99), wound infection and dehiscence (RR?=?3.13 and 4.85), NODAT (RR?=?2.24), length of hospital stay (2.31 days), operation duration (0.77 hours), hypertension (RR?=?1.35), and incisional hernia (RR?=?2.72). However, patient survival expressed in hazard ratios was in significant favour of high BMI recipients. Differences in other outcome parameters were not significant.Several of the pooled outcome measurements show significant benefits for 'low' BMI (<30) recipients. Therefore, we postulate that ESRD patients with a BMI >30 preferably should lose weight prior to RT. If this cannot be achieved with common measures, in morbidly obese RT candidates, bariatric surgery could be considered.
| S-EPMC4427990 | biostudies-literature