Dataset Information

Developing more generalizable prediction models from pooled studies and large clustered data sets.

ABSTRACT: Prediction models often yield inaccurate predictions for new individuals. Large data sets from pooled studies or electronic healthcare records may alleviate this with an increased sample size and variability in sample characteristics. However, existing strategies for prediction model development generally do not account for heterogeneity in predictor-outcome associations between different settings and populations. This limits the generalizability of developed models (even from large, combined, clustered data sets) and necessitates local revisions. We aim to develop methodology for producing prediction models that require less tailoring to different settings and populations. We adopt internal-external cross-validation to assess and reduce heterogeneity in models' predictive performance during the development. We propose a predictor selection algorithm that optimizes the (weighted) average performance while minimizing its variability across the hold-out clusters (or studies). Predictors are added iteratively until the estimated generalizability is optimized. We illustrate this by developing a model for predicting the risk of atrial fibrillation and updating an existing one for diagnosing deep vein thrombosis, using individual participant data from 20 cohorts (N = 10 873) and 11 diagnostic studies (N = 10 014), respectively. Meta-analysis of calibration and discrimination performance in each hold-out cluster shows that trade-offs between average and heterogeneity of performance occurred. Our methodology enables the assessment of heterogeneity of prediction model performance during model development in multiple or clustered data sets, thereby informing researchers on predictor selection to improve the generalizability to different settings and populations, and reduce the need for model tailoring. Our methodology has been implemented in the R package metamisc.

SUBMITTER: de Jong VMT

PROVIDER: S-EPMC8252590 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundMachine learning methodologies are gaining popularity for developing medical prediction models for datasets with a large number of predictors, particularly in the setting of clustered and longitudinal data. Binary Mixed Model (BiMM) forest is a promising machine learning algorithm which may be applied to develop prediction models for clustered and longitudinal binary outcomes. Although machine learning methods for clustered and longitudinal methods such as BiMM forest exist, feature selection has not been analyzed via data simulations. Feature selection improves the practicality and ease of use of prediction models for clinicians by reducing the burden of data collection. Thus, feature selection procedures are not only beneficial, but are often necessary for development of medical prediction models. In this study, we aim to assess feature selection within the BiMM forest setting for modeling clustered and longitudinal binary outcomes.MethodsWe conducted a simulation study to compare BiMM forest with feature selection (backward elimination or stepwise selection) to standard generalized linear mixed model feature selection methods (shrinkage and backward elimination). We also evaluated feature selection methods to develop models predicting mobility disability in older adults using the Health, Aging and Body Composition Study dataset as an example utilization of the proposed methodology.ResultsBiMM forest with backward elimination generally offered higher computational efficiency, similar or higher predictive performance (accuracy and area under the receiver operating curve), and similar or higher ability to identify correct features compared to linear methods for the different simulated scenarios. For predicting mobility disability in older adults, methods generally performed similarly in terms of accuracy, area under the receiver operating curve, and specificity; however, BiMM forest with backward elimination had the highest sensitivity.ConclusionsThis study is novel because it is the first investigation of feature selection for developing random forest prediction models for clustered and longitudinal binary outcomes. Results from the simulation study reveal that BiMM forest with backward elimination has the highest accuracy (performance and identification of correct features) and lowest computation time compared to other feature selection methods in some scenarios and similar performance in other scenarios. Many informatics datasets have clustered and longitudinal outcomes and results from this study suggest that BiMM forest with backward elimination may be beneficial for developing medical prediction models.

Project description:BackgroundClinical prediction models often fail to generalize in the context of clustered data, because most models fail to account for heterogeneity in outcome values and covariate effects across clusters. Furthermore, standard approaches for modeling clustered data, including generalized linear mixed-effects models, would not be expected to provide accurate predictions in novel clusters, because such predictions are typically based on the hypothetical mean cluster. We hypothesized that dynamic mixed-effects models, which incorporate data from previous predictions to refine the model for future predictions, would allow for cluster-specific predictions in novel clusters as the model is updated over time, thus improving overall model generalizability.ResultsWe quantified the potential gains in prediction accuracy from using a dynamic modeling strategy in a simulation study. Furthermore, because clinical prediction models in the context of clustered data often involve outcomes that are dependent on patient volume, we examined whether using dynamic mixed-effects models would be robust to misspecification of the volume-outcome relationship. Our results indicated that dynamic mixed-effects models led to substantial improvements in prediction accuracy in clustered populations over a broad range of conditions, and were uniformly superior to static models. In addition, dynamic mixed-effects models were particularly robust to misspecification of the volume-outcome relationship and to variation in the frequency of model updating. The extent of the improvement in prediction accuracy that was observed with dynamic mixed-effects models depended on the relative impact of fixed and random effects on the outcome as well as the degree of misspecification of model fixed effects.ConclusionsDynamic mixed-effects models led to substantial improvements in prediction model accuracy across a broad range of simulated conditions. Therefore, dynamic mixed-effects models could be a useful alternative to standard static models for improving the generalizability of clinical prediction models in the setting of clustered data, and, thus, well worth the logistical challenges that may accompany their implementation in practice.

Project description:IntroductionCore outcome sets are standardised lists of outcomes, which should be measured and reported in all clinical studies of a specific condition. This study aims to develop core outcome sets for economic evaluations in asthma studies. Economic outcomes include items such as costs, resource use or quality-adjusted life years. The starting point in developing core outcome sets will be conducting a systematic literature review to establish a preliminary list of reporting items to be considered for inclusion in the core outcome set.Methods and analysisWe will conduct literature searches of peer-reviewed studies published from January 1990 to January 2017. These will include any comparative or observational studies (including economic models) and systematic reviews reporting economic outcomes. All identified economic outcomes will be tabulated together with the major study characteristics, such as population, study design, the nature and intensity of the intervention, mode of data collection and instrument(s) used to derive an outcome. We will undertake a 'realist synthesis review' to analyse the identified economic outcomes. The outcomes will be summarised in the context of evaluation perspectives, types of economic evaluation and methodological approaches. Parallel to undertaking a systematic review, we will conduct semistructured interviews with stakeholders (including people with personal experience of asthma, health professionals, researchers and decision makers) in order to explore additional outcomes which have not been considered, or used, in published studies. The list of outcomes generated from the systematic review and interviews with stakeholders will form the basis of a Delphi survey to refine the identified outcomes into a core outcome set.Ethics and disseminationThe review will not involve access to individual-level data. Findings from our systematic review will be communicated to a broad range of stakeholders including clinical guideline developers, research funders, trial registries, ethics committees and other regulators.

Project description:BackgroundWhen study data are clustered, standard regression analysis is considered inappropriate and analytical techniques for clustered data need to be used. For prediction research in which the interest of predictor effects is on the patient level, random effect regression models are probably preferred over standard regression analysis. It is well known that the random effect parameter estimates and the standard logistic regression parameter estimates are different. Here, we compared random effect and standard logistic regression models for their ability to provide accurate predictions.MethodsUsing an empirical study on 1642 surgical patients at risk of postoperative nausea and vomiting, who were treated by one of 19 anesthesiologists (clusters), we developed prognostic models either with standard or random intercept logistic regression. External validity of these models was assessed in new patients from other anesthesiologists. We supported our results with simulation studies using intra-class correlation coefficients (ICC) of 5%, 15%, or 30%. Standard performance measures and measures adapted for the clustered data structure were estimated.ResultsThe model developed with random effect analysis showed better discrimination than the standard approach, if the cluster effects were used for risk prediction (standard c-index of 0.69 versus 0.66). In the external validation set, both models showed similar discrimination (standard c-index 0.68 versus 0.67). The simulation study confirmed these results. For datasets with a high ICC (≥15%), model calibration was only adequate in external subjects, if the used performance measure assumed the same data structure as the model development method: standard calibration measures showed good calibration for the standard developed model, calibration measures adapting the clustered data structure showed good calibration for the prediction model with random intercept.ConclusionThe models with random intercept discriminate better than the standard model only if the cluster effect is used for predictions. The prediction model with random intercept had good calibration within clusters.

Project description:ObjectiveTo develop a standardised set of economic parameters (core economic parameter set) for economic evaluations in asthma studies.DesignA systematic literature review and an analytical framework.Outcome measuresEconomic parameters used to evaluate costs and cost-effectiveness of healthcare interventions for people with asthma.Data sourcesPubMed, the Cochrane Database of Systematic Reviews, the National Health Service Economic Evaluation Database, the Database of Abstracts of Reviews of Effects and the Health Technology Aaaessment Library starting from 1990.Review methodsResearch methods were based on the realist review methodology and included a number of non-sequential, iterative and overlapping components, such as developing an analytical framework for the realist review; systematic literature review of economic parameters; identifying and categorising economic parameters; producing preliminary list of core economic parameters.ResultsDatabase searches found 2531 publications of which 224 were included in the systematic review. We identified 65 economic parameters that were categorised into 11 groups to enable the realist synthesis. Parameters related to secondary care, primary care, medication use, emergency care and work productivity comprised 84% of all economic parameters. An analytical framework was used to investigate the rationale behind the choices of economic parameters in these studies. The main framework domains included type of intervention, research population, study design, study setting and a stakeholder's perspective.ConclusionPast research thus suggests that in asthma study parameters depicting the use of secondary care, primary care, medication, emergency care and work productivity can be considered as core economic parameters, since they apply to different types of studies. Parameters including diagnostics, healthcare delivery, school activity, informal care, medical devices and health utility apply to a particular type of study (or research question), and thus can be recommended as supplemental parameters.Prospero registration numberCRD42017067867.

Project description:BackgroundRandom effects modelling is routinely used in clustered data, but for prediction models, random effects are commonly substituted with the mean zero after model development. In this study, we proposed a novel approach of including prior knowledge through the random effects distribution and investigated to what extent this could improve the predictive performance.MethodsData were simulated on the basis of a random effects logistic regression model. Five prediction models were specified: a frequentist model that set the random effects to zero for all new clusters, a Bayesian model with weakly informative priors for the random effects of new clusters, Bayesian models with expert opinion incorporated into low informative, medium informative and highly informative priors for the random effects. Expert opinion at the cluster level was elicited in the form of a truncated area of the random effects distribution. The predictive performance of the five models was assessed. In addition, impact of suboptimal expert opinion that deviated from the true quantity as well as including expert opinion by means of a categorical variable in the frequentist approach were explored. The five models were further investigated in various sensitivity analyses.ResultsThe Bayesian prediction model using weakly informative priors for the random effects showed similar results to the frequentist model. Bayesian prediction models using expert opinion as informative priors showed smaller Brier scores, better overall discrimination and calibration, as well as better within cluster calibration. Results also indicated that incorporation of more precise expert opinion led to better predictions. Predictive performance from the frequentist models with expert opinion incorporated as categorical variable showed similar patterns as the Bayesian models with informative priors. When suboptimal expert opinion was used as prior information, results indicated that prediction still improved in certain settings.ConclusionsThe prediction models that incorporated cluster level information showed better performance than the models that did not. The Bayesian prediction models we proposed, with cluster specific expert opinion incorporated as priors for the random effects showed better predictive ability in new data, compared to the frequentist method that replaced random effects with zero after model development.

Dataset Information

Developing more generalizable prediction models from pooled studies and large clustered data sets.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets