BackgroundConfounding bias is a common concern in epidemiological research. Its presence is often determined by comparing exposure effects between univariable- and multivariable regression models, using an arbitrary threshold of a 10% difference to indicate confounding bias. However, many clinical researchers are not aware that the use of this change-in-estimate criterion may lead to wrong conclusions when applied to logistic regression coefficients. This is due to a statistical phenomenon called noncollapsibility, which manifests itself in logistic regression models. This paper aims to clarify the role of noncollapsibility in logistic regression and to provide guidance in determining the presence of confounding bias.MethodsA Monte Carlo simulation study was designed to uncover patterns of confounding bias and noncollapsibility effects in logistic regression. An empirical data example was used to illustrate the inability of the change-in-estimate criterion to distinguish confounding bias from noncollapsibility effects.ResultsThe simulation study showed that, depending on the sign and magnitude of the confounding bias and the noncollapsibility effect, the difference between the effect estimates from univariable- and multivariable regression models may underestimate or overestimate the magnitude of the confounding bias. Because of the noncollapsibility effect, multivariable regression analysis and inverse probability weighting provided different but valid estimates of the confounder-adjusted exposure effect. In our data example, confounding bias was underestimated by the change in estimate due to the presence of a noncollapsibility effect.ConclusionIn logistic regression, the difference between the univariable- and multivariable effect estimate might not only reflect confounding bias but also a noncollapsibility effect. Ideally, the set of confounders is determined at the study design phase and based on subject matter knowledge. To quantify confounding bias, one could compare the unadjusted exposure effect estimate and the estimate from an inverse probability weighted model.
MULTIFILE
Full text met een HU Account Objective: To quantify diversity in components of self-management interventions and explore which components are associated with improvement in health-related quality of life (HRQoL) in patients with chronic heart failure (CHF), chronic obstructive pulmonary disease (COPD), or type 2 diabetes mellitus (T2DM). Methods: Systematic literature search was conducted from January 1985 through June 2013. Included studies were randomised trials in patients with CHF, COPD, or T2DM, comparing self-management interventions with usual care, and reporting data on disease-specific HRQoL. Data were analysed with weighted random effects linear regression models. Results: 47 trials were included, representing 10,596 patients. Self-management interventions showed great diversity in mode, content, intensity, and duration. Although self-management interventions overall improved HRQoL at 6 and 12 months, meta-regression showed counterintuitive negative effects of standardised training of interventionists (SMD = 0.16, 95% CI: 0.31 to 0.01) and peer interaction (SMD = 0.23, 95% CI 0.39 to 0.06) on HRQoL at 6 months. Conclusion: Self-management interventions improve HRQoL at 6 and 12 months, but interventions evaluated are highly heterogeneous. No components were identified that favourably affected HRQoL. Standardised training and peer interaction negatively influenced HRQoL, but the underlying mechanism remains unclear. Practice implications: Future research should address process evaluations and study response to selfmanagement on the level of individual patients
MULTIFILE
Digitalization is the core component of future development in the 4.0 industrial era. It represents a powerful mechanism for enhancing the sustainable competitiveness of economies worldwide. Diverse triggering effects shape future digitalization trends. Thus, the main research goal in this study is to use sustainable competitiveness pillars (such as social, economic, environmental and energy) to evaluate international digitalization development. The proposed empirical model generates comprehensive knowledge of the sustainable competitiveness-digitalization nexus. For that purpose, a nonlinear regression has been applied on gathered annual data that consist of 33 European countries, ranging from 2010 to 2016. The dataset has been deployed using Bernoulli’s binominal distribution to derive training and testing samples and the entire analysis has been adjusted in that context. The empirical findings of artificial neural networks (ANN) suggest strong effects of the economic and energy use indicators on the digitalization progress. Nonlinear regression and ANN model summary report valuable results with a high degree of coefficient of determination (R2>0.9 for all models). Research findings state that the digitalization process is multidimensional and cannot be evaluated as an isolated phenomenon without incorporating other relevant factors that emerge in the environment. Indicators report the consumption of electrical energy in industry and households and GDP per capita to achieve the strongest effect.
MULTIFILE
Zijn data-analyse en bio-informatica de sleutel naar voorspellingen over de invloed van giftige stoffen op de gezondheid van mensen? Het project DART Pathfinder is een vervolgonderzoek naar een dierproefvrije testmethode. Met moderne ICT-technieken proberen we die voorspellingen te doen.Doel Het doel van dit project is om gegevens over giftige stoffen uit verschillende data bronnen samen te brengen. In het onderzoek gebruiken we technieken uit de bio-informatica. Zo willen we de eigenschappen van giftige stoffen beter in kaart brengen en (nadelige) effecten van soortgelijke stoffen kunnen voorspellen. Veel bedrijven maken producten of stoffen, die getest moeten worden of ze veilig zijn. Met dit project helpen we bedrijven om o.b.v. bestaande gegevens een betere keuze te maken welke testen ze hiervoor het beste kunnen gebruiken. Resultaten Kennis over computer modellen die voorspellingen doen, zoals machine learning, regression tree-based models; Nieuwe algoritmen (instructies om berekeningen uit te voeren) Inzicht in nieuwe biologische mechanismen obv data science Nieuwe statische methoden om data te analysen en voorspellingen te doen. Looptijd 01 februari 2018 - 01 februari 2022 Aanpak Met de gegevens uit het onderzoek maken we een computermodel dat voorspelt of giftige stoffen invloed hebben op de voortplanting en ontwikkeling van mensen. Die voorspelling gebeurt via machine learning, algoritmen en statistische methoden. Voor dit model wordt informatie uit publieke databases over fysische en chemische eigenschappen van mogelijk gevaarlijke stoffen samengevoegd met de gegevens over de invloed van deze stoffen op levende organismen. Net als in het eerste onderzoek (PreDART) werken we met rondwormen (C.elegans) en embryo's van zebravissen, met als doel geen proeven meer met ratten en konijnen te hoeven doen.
