Dataset Information

Incorporating repeated measurements into prediction models in the critical care setting: a framework, systematic review and meta-analysis.

ABSTRACT: BACKGROUND:The incorporation of repeated measurements into multivariable prediction research may greatly enhance predictive performance. However, the methodological possibilities vary widely and a structured overview of the possible and utilized approaches lacks. Therefore, we [1] propose a structured framework for these approaches, [2] determine what methods are currently used to incorporate repeated measurements in prediction research in the critical care setting and, where possible, [3] assess the added discriminative value of incorporating repeated measurements. METHODS:The proposed framework consists of three domains: the observation window (static or dynamic), the processing of the raw data (raw data modelling, feature extraction and reduction) and the type of modelling. A systematic review was performed to identify studies which incorporate repeated measurements to predict (e.g. mortality) in the critical care setting. The within-study difference in c-statistics between models with versus without repeated measurements were obtained and pooled in a meta-analysis. RESULTS:From the 2618 studies found, 29 studies incorporated multiple repeated measurements. The annual number of studies with repeated measurements increased from 2.8/year (2000-2005) to 16.0/year (2016-2018). The majority of studies that incorporated repeated measurements for prediction research used a dynamic observation window, and extracted features directly from the data. Differences in c statistics ranged from -?0.048 to 0.217 in favour of models that utilize repeated measurements. CONCLUSIONS:Repeated measurements are increasingly common to predict events in the critical care domain, but their incorporation is lagging. A framework of possible approaches could aid researchers to optimize future prediction models.

SUBMITTER: Plate JDJ

PROVIDER: S-EPMC6815391 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Incorporating repeated measurements into prediction models in the critical care setting: a framework, systematic review and meta-analysis.

Plate Joost D J JDJ van de Leur Rutger R RR Leenen Luke P H LPH Hietbrink Falco F Peelen Linda M LM Eijkemans M J C MJC

BMC medical research methodology 20191026 1

<h4>Background</h4>The incorporation of repeated measurements into multivariable prediction research may greatly enhance predictive performance. However, the methodological possibilities vary widely and a structured overview of the possible and utilized approaches lacks. Therefore, we [1] propose a structured framework for these approaches, [2] determine what methods are currently used to incorporate repeated measurements in prediction research in the critical care setting and, where possible, [ ...[more]

PMID: 31655567

Similar Datasets

Project description:Despite development of new technologies for caries control, tooth decay in primary teeth remains a major global health problem. Caries risk assessment (CRA) models for toddlers and preschoolers are rare. Among them, almost all models use dental factors (e.g., past caries experience) to predict future caries risk, with limited clinical/community applicability owing to relatively uncommon dental visits compared to frequent medical visits during the first year of life. The objective of this study was to construct and evaluate risk prediction models using information easily accessible to medical practitioners to forecast caries at 2 and 3 y of age. Data were obtained from the Growing Up in Singapore Towards Healthy Outcomes (GUSTO) mother-offspring cohort. Caries was diagnosed using modified International Caries Detection and Assessment System criteria. Risk prediction models were constructed using multivariable logistic regression coupled with receiver operating characteristic analyses. Imputation was performed using multiple imputation by chained equations to assess effect of missing data. Caries rates at ages 2 y (n = 535) and 3 y (n = 721) were 17.8% and 42.9%, respectively. Risk prediction models predicting overall caries risk at 2 and 3 y demonstrated area under the curve (AUC) (95% confidence interval) of 0.81 (0.75-0.87) and 0.79 (0.74-0.84), respectively, while those predicting moderate to extensive lesions showed 0.91 (0.85-0.97) and 0.79 (0.73-0.85), respectively. Postimputation results showed reduced AUC of 0.75 (0.74-0.81) and 0.71 (0.67-0.75) at years 2 and 3, respectively, for overall caries risk, while AUC was 0.84 (0.76-0.92) and 0.75 (0.70-0.80), respectively, for moderate to extensive caries. Addition of anterior caries significantly increased AUC in all year 3 models with or without imputation (all P < 0.05). Significant predictors/protectors were identified, including ethnicity, prenatal tobacco smoke exposure, history of allergies before 12 mo, history of chronic maternal illness, maternal brushing frequency, childbearing age, and so on. Integrating oral-general health care using medical CRA models may be promising in screening caries-susceptible infants/toddlers, especially when medical professionals are trained to "lift the lip" to identify anterior caries lesions.

Project description:Helium is a low-density inert gas whose physical properties are very different from those of nitrogen and oxygen. Such properties could be clinically useful in the adult critical care setting, especially in patients with upper to more distal airway obstruction requiring moderate to intermediate levels of FiO2. However, despite decades of utilization and reporting, it is still difficult to give any firm clinical recommendation in this setting. Numerous case reports are available in the context of upper airway obstruction of different origins, but there is a lack of controlled studies for this indication. One study reported a helium-induced beneficial effect on surrogates of work of breathing after extubation in non-COPD patients, possibly in relation to laryngeal consequences of tracheal intubation. Physiological benefits of helium-oxygen breathing have been demonstrated in the context of acute severe asthma, but there is a lack of large controlled studies demonstrating an effect on pertinent clinical endpoints, except for a study reported only as an abstract, which mentioned a reduction in the intubation rate in helium-treated patients. Finally, there are a number of physiological studies in the context of COLD-COPD patients demonstrating a beneficial effect, mainly by a reduction in the resistive inspiratory work of breathing but also by a reduction in hyperinflation. Reduction of hypercapnia was mainly observed in spontaneously breathing and noninvasively ventilated helium-treated patients but not in intubated patients during controlled ventilation, suggesting that the decrease in PaCO2 was mainly in relation to a diminution in CO2 production, related to the diminution in work of breathing and not an improved alveolar ventilation. Moreover, there is little evidence that helium-oxygen could improve parameters of heterogeneity in such patients. Two RCTs were unable to demonstrate a reduction in the intubation rate in such setting, but they were likely underpowered. An adequately powered international multicentric study is ongoing and will help to determinate the exact place of the helium-oxygen mixture in the future. The place of the mixture during the weaning period will deserve further evaluation.

Project description:OBJECTIVE:To identify risk prediction models for prostate cancer (PCa) that can be used in the primary care and community health settings. DESIGN:Systematic review. DATA SOURCES:MEDLINE and Embase databases combined from inception and up to the end of January 2019. ELIGIBILITY:Studies were included based on satisfying all the following criteria: (i) presenting an evaluation of PCa risk at initial biopsy in patients with no history of PCa, (ii) studies not incorporating an invasive clinical assessment or expensive biomarker/genetic tests, (iii) inclusion of at least two variables with prostate-specific antigen (PSA) being one of them, and (iv) studies reporting a measure of predictive performance. The quality of the studies and risk of bias was assessed by using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). DATA EXTRACTION AND SYNTHESIS:Relevant information extracted for each model included: the year of publication, source of data, type of model, number of patients, country, age, PSA range, mean/median PSA, other variables included in the model, number of biopsy cores to assess outcomes, study endpoint(s), cancer detection, model validation and model performance. RESULTS:An initial search yielded 109 potential studies, of which five met the set criteria. Four studies were cohort-based and one was a case-control study. PCa detection rate was between 20.6% and 55.8%. Area under the curve (AUC) was reported in four studies and ranged from 0.65 to 0.75. All models showed significant improvement in predicting PCa compared with being based on PSA alone. The difference in AUC between extended models and PSA alone was between 0.06 and 0.21. CONCLUSION:Only a few PCa risk prediction models have the potential to be readily used in the primary healthcare or community health setting. Further studies are needed to investigate other potential variables that could be integrated into models to improve their clinical utility for PCa testing in a community setting.

Dataset Information

Incorporating repeated measurements into prediction models in the critical care setting: a framework, systematic review and meta-analysis.

Publications

Incorporating repeated measurements into prediction models in the critical care setting: a framework, systematic review and meta-analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets