Standard multiple imputation of survey data didn't perform better than simple substitution in enhancing an administrative dataset: the example of self-rated health in England.
Ontology highlight
ABSTRACT: Background
Health surveys provide a rich array of information but on relatively small numbers of individuals and evidence suggests that they are becoming less representative as response levels fall. Routinely collected administrative data offer more extensive population coverage but typically comprise fewer health topics. We explore whether data combination and multiple imputation of health variables from survey data is a simple and robust way of generating these variables in the general population.Methods
We use the UK Integrated Household Survey and the English 2011 population census both of which included self-rated general health. Setting aside the census self-rated health data we multiply imputed self-rated health responses for the census using the survey data and compared these with the actual census results in 576 unique groups defined by age, sex, housing tenure and geographic region.Results
Compared with original census data across the groups, multiply imputed proportions of bad or very bad self-rated health were not a markedly better fit than those simply derived from the survey proportions.Conclusion
While multiple imputation may have the potential to augment population data with information from surveys, further testing and refinement is required.
SUBMITTER: Popham F
PROVIDER: S-EPMC8310590 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundPrognostic factors and prognostic models play a key role in medical research and patient management. The Nottingham Prognostic Index (NPI) is a well-established prognostic classification scheme for patients with breast cancer. In a very simple way, it combines the information from tumor size, lymph node stage and tumor grade. For the resulting index cutpoints are proposed to classify it into three to six groups with different prognosis. As not all prognostic information from the three and other standard factors is used, we will consider improvement of the prognostic ability using suitable analysis approaches.Methods and findingsReanalyzing overall survival data of 1560 patients from a clinical database by using multivariable fractional polynomials and further modern statistical methods we illustrate suitable multivariable modelling and methods to derive and assess the prognostic ability of an index. Using a REMARK type profile we summarize relevant steps of the analysis. Adding the information from hormonal receptor status and using the full information from the three NPI components, specifically concerning the number of positive lymph nodes, an extended NPI with improved prognostic ability is derived.ConclusionsThe prognostic ability of even one of the best established prognostic index in medicine can be improved by using suitable statistical methodology to extract the full information from standard clinical data. This extended version of the NPI can serve as a benchmark to assess the added value of new information, ranging from a new single clinical marker to a derived index from omics data. An established benchmark would also help to harmonize the statistical analyses of such studies and protect against the propagation of many false promises concerning the prognostic value of new measurements. Statistical methods used are generally available and can be used for similar analyses in other diseases.
| S-EPMC4777365 | biostudies-literature
Project description:Low availability of inorganic phosphate (Pi), together with aluminum (Al), is a major constraint for plant growth and development in acidic soils. To investigate whether or not Al-resistant cultivars can perform better under Pi deficiency, we chose two wheat cultivars with different Al-responses-Atlas 66, being Al-tolerant, and Scout 66, which is Al-sensitive-and analyzed their responses to Pi deficiency. Results showed that, unexpectedly, the Al-sensitive cultivar Scout 66 contained comparatively higher amount of soluble phosphate (Pi) and total phosphorus (P) both in the roots and in the shoots than Atlas 66 under P deficiency. In addition, Scout 66 exhibited higher root biomass, root volume, and root tip numbers, compared with Atlas 66. The expression of Pi-responsive marker genes, TaIPS1, TaSPX3, and TaSQD2 was strongly induced in both cultivars, but the extents of induction were higher in Scout 66 than in Atlas 66 under long-term Pi starvation. Taken together, our results suggest that the Al-sensitive cultivar Scout 66 performed much better under sole Pi starvation, which sets the following experimental stage to uncover the underlying mechanisms of why Scout 66 can display better under Pi deficiency. Our study also raises an open question whether Al-resistant plants are more sensitive to Pi deficiency.
| S-EPMC6213158 | biostudies-literature
Project description:In recent years, the popularity of tablets has skyrocketed and there has been an explosive growth in apps designed for children. Howhever, many of these apps are released without tests for their effectiveness. This is worrying given that the factors influencing children's learning from touchscreen devices need to be examined in detail. In particular, it has been suggested that children learn less from passive video viewing relative to equivalent live interaction, which would have implications for learning from such digital tools. However, this so-called video deficit may be reduced by allowing children greater influence over their learning environment. Across two touchscreen-based experiments, we examined whether 2- to 4-year-olds benefit from actively choosing what to learn more about in a digital word learning task. We designed a tablet study in which "active" participants were allowed to choose which objects they were taught the label of, while yoked "passive" participants were presented with the objects chosen by their active peers. We then examined recognition of the learned associations across different tasks. In Experiment 1, children in the passive condition outperformed those in the active condition (n = 130). While Experiment 2 replicated these findings in a new group of Malay-speaking children (n = 32), there were no differences in children's learning or recognition of the novel word-object associations using a more implicit looking time measure. These results suggest that there may be performance costs associated with active tasks designed as in the current study, and at the very least, there may not always be systematic benefits associated with active learning in touchscreen-based word learning tasks. The current studies add to the evidence that educational apps need to be evaluated before release: While children might benefit from interactive apps under certain conditions, task design and requirements need to consider factors that may detract from successful performance.
| S-EPMC7707543 | biostudies-literature
Project description:The presence of missing values in a time-series dataset is a very common and well-known problem. Various statistical and machine learning methods have been developed to overcome this problem, with the aim of filling in the missing values in the data. However, the performances of these methods vary widely, showing a high dependence on the type of data and correlations within the data. In our study, we performed some of the well-known imputation methods, such as expectation maximization, k-nearest neighbor, iterative imputer, random forest, and simple imputer, to impute missing data obtained from smart, wearable health trackers. In this manuscript, we proposed the use of data binning for imputation. We showed that the use of data binned around the missing time interval provides a better imputation than the use of a whole dataset. Imputation was performed for 15 min and 1 h of continuous missing data. We used a dataset with different bin sizes, such as 15 min, 30 min, 45 min, and 1 h, and we carried out evaluations using root mean square error (RMSE) values. We observed that the expectation maximization algorithm worked best for the use of binned data. This was followed by the simple imputer, iterative imputer, and k-nearest neighbor, whereas the random forest method had no effect on data binning during imputation. Moreover, the smallest bin sizes of 15 min and 1 h were observed to provide the lowest RMSE values for the majority of the time frames during the imputation of 15 min and 1 h of missing data, respectively. Although applicable to digital health data, we think that this method will also find applicability in other domains.
| S-EPMC9919790 | biostudies-literature
Project description:BackgroundChildhood obesity is high on the policy agenda of wealthier nations, and many interventions have been developed to address it. This work describes an overview of schemes for obese and overweight children and young people in England, and the 'mapping' approach we used.MethodsOur search strategy, inclusion criteria and coding frame had to be suitable for describing a potentially large number of schemes within a short timeframe. Data were collected from key informants, scheme publicity and reports, and via a web-survey. To be included, schemes had to be based in England, follow a structured programme lasting at least two weeks, promote healthy weight, and be delivered exclusively to overweight and/or obese children and young people (age range 4-18). Data were entered into a coding frame recording similar information for each scheme, including any underpinning research evidence, evaluation or monitoring reports. Priority questions were identified in consultation with colleagues from the Department of Health and the Cross Government Obesity Unit.ResultsFifty-one schemes were identified. Some operated in multiple areas, and by using estimates of the number of schemes provided by multi-site scheme leads, we found that between 314 and 375 local programmes were running at any time. Uncertainty is largely due to the largest scheme provider undergoing rapid expansion at the time of the mapping exercise and therefore able to provide only an estimate of the number of programmes running. Many schemes were similar in their approach, had been recently established and were following NICE guidelines on interventions to promote healthy weight. Rigorous evaluation was rare.ConclusionsOur methods enabled us to produce a rapid overview of service activity across a wide geographic area and a range of organisations and sectors. In order to develop the evidence base for childhood obesity interventions, rigorous evaluation of these schemes is required. This overview can serve as a starting point for evaluations of interventions to address obesity. More generally, a rapid and systematic approach of this type is transferable to other types of service activity in health and social care, and may be a tool to inform public health planning.
| S-EPMC2890690 | biostudies-literature
Project description:Insect cuticle has drawn a lot of attention from engineers because of its multifunctional role in the life of insects. Some of these cuticles have an optimal combination of lightweight and good mechanical properties, and have inspired the design of composites with novel microstructures. Among these, beetle elytra have been explored extensively for their multilayered structure, multifunctional roles and mechanical properties. In this study, we investigated the bending properties of elytra by simulating their natural loading condition and comparing it with other loading configurations. Further, we examined the properties of their constitutive bulk layers to understand the contribution of each one to the overall mechanical behaviour. Our results showed that elytra are graded, multilayered composite structures that perform better in natural loading direction in terms of both flexural modulus and strength which is likely an adaptation to withstand loads encountered in the habitat. Experiments are supported by analytical calculations and finite element method modelling, which highlighted the additional role of the relatively stiff external exocuticle and of the flexible thin bottom layer in enhancing flexural mechanical properties. Such studies contribute to the knowledge of the mechanical behaviour of this natural composite material and to the development of novel bioinspired multifunctional composites and for optimized armours.
| S-EPMC6073640 | biostudies-literature
Project description:BACKGROUND:Whether worldwide increases in life expectancy are accompanied by a better health status is still a debate. People age differently, and there is a need to disentangle whether healthy-ageing pathways can be shaped by cohort effects. This study aims to analyse trends in health status in two large nationally representative samples of older adults from England and the USA. METHODS:The sample comprised 55 684 participants from the first seven waves of the English Longitudinal Study of Ageing (ELSA), and the first 11 waves of the Health and Retirement Study (HRS). A common latent health score based on Bayesian multilevel item response theory was used. Two Bayesian mixed-effects multilevel models were used to assess cohort effects on health in ELSA and HRS separately, controlling for the effect of household wealth and educational attainment. RESULTS:Similar ageing trends were found in ELSA (??=?-0.311; p?<?0.001) and HRS (??=?-0.393; p?<?0.001). The level of education moderated the life-course effect on health in both ELSA (??=?-0.082; p?<?0.05) and HRS (??=?-0.084; p?<?0.05). A birth-year effect was found for those belonging to the highest quintiles of household wealth in both ELSA (??=?0.125; p?<?0.001) and HRS (??=?0.170; p?<?0.001). CONCLUSIONS:Health inequalities have increased in recent cohorts, with the wealthiest participants presenting a better health status in both the USA and English populations. Actions to promote health in the ageing population should consider the increasing inequality scenario, not only by applying highly effective interventions, but also by making them accessible to all members of society.
| S-EPMC6929538 | biostudies-literature
Project description:Genes with moderate to low expression heritability may explain a large proportion of complex trait etiology, but such genes cannot be sufficiently captured in conventional transcriptome-wide association studies (TWASs), partly due to the relatively small available reference datasets for developing expression genetic prediction models to capture the moderate to low genetically regulated components of gene expression. Here, we introduce a method, the Summary-level Unified Method for Modeling Integrated Transcriptome (SUMMIT), to improve the expression prediction model accuracy and the power of TWAS by using a large expression quantitative trait loci (eQTL) summary-level dataset. We apply SUMMIT to the eQTL summary-level data provided by the eQTLGen consortium. Through simulation studies and analyses of genome-wide association study summary statistics for 24 complex traits, we show that SUMMIT improves the accuracy of expression prediction in blood, successfully builds expression prediction models for genes with low expression heritability, and achieves higher statistical power than several benchmark methods. Finally, we conduct a case study of COVID-19 severity with SUMMIT and identify 11 likely causal genes associated with COVID-19 severity.
| S-EPMC9593997 | biostudies-literature
Project description:Estimation of natural selection on protein-coding sequences is a key comparative genomics approach for de novo prediction of lineage-specific adaptations. Selective pressure is measured on a per-gene basis by comparing the rate of nonsynonymous substitutions to the rate of synonymous substitutions. All published codon substitution models have been time-reversible and thus assume that sequence composition does not change over time. We previously demonstrated that if time-reversible DNA substitution models are applied in the presence of changing sequence composition, the number of substitutions is systematically biased towards overestimation. We extend these findings to the case of codon substitution models and further demonstrate that the ratio of nonsynonymous to synonymous rates of substitution tends to be underestimated over three data sets of mammals, vertebrates, and insects. Our basis for comparison is a nonstationary codon substitution model that allows sequence composition to change. Goodness-of-fit results demonstrate that our new model tends to fit the data better. Direct measurement of nonstationarity shows that bias in estimates of natural selection and genetic distance increases with the degree of violation of the stationarity assumption. Additionally, inferences drawn under time-reversible models are systematically affected by compositional divergence. As genomic sequences accumulate at an accelerating rate, the importance of accurate de novo estimation of natural selection increases. Our results establish that our new model provides a more robust perspective on this fundamental quantity.
| S-EPMC5381540 | biostudies-literature
Project description:High quality radiology reporting of chest X-ray images is of core importance for high-quality patient diagnosis and care. Automatically generated reports can assist radiologists by reducing their workload and even may prevent errors. Machine Learning (ML) models for this task take an X-ray image as input and output a sequence of words. In this work, we show that ML models for this task based on the popular encoder-decoder approach, like 'Show, Attend and Tell' (SA&T) have similar or worse performance than models that do not use the input image, called unconditioned baseline. An unconditioned model achieved diagnostic accuracy of 0.91 on the IU chest X-ray dataset, and significantly outperformed SA&T (0.877) and other popular ML models (p-value < 0.001). This unconditioned model also outperformed SA&T and similar ML methods on the BLEU-4 and METEOR metrics. Also, an unconditioned version of SA&T obtained by permuting the reports generated from images of the test set, achieved diagnostic accuracy of 0.862, comparable to that of SA&T (p-value ≥ 0.05).
| S-EPMC8629217 | biostudies-literature