Available methods for the joint modelling of longitudinal and time-to-event outcomes have typically only allowed for a single longitudinal outcome and a solitary event time. In practice, clinical studies are likely to record multiple longitudinal outcomes. Incorporating all sources of data will improve the predictive capability of any model and lead to more informative inferences for the purpose of medical decision-making. We reviewed current methodologies of joint modelling for time-to-event data and multivariate longitudinal data including the distributional and modelling assumptions, the association structures, estimation approaches, software tools for implementation and clinical applications of the methodologies. We found that a large number of different models have recently been proposed. Most considered jointly modelling linear mixed models with proportional hazard models, with correlation between multiple longitudinal outcomes accounted for through multivariate normally distributed random effects. So-called current value and random effects parameterisations are commonly used to link the models. Despite developments, software is still lacking, which has translated into limited uptake by medical researchers. Although, in an era of personalized medicine, the value of multivariate joint modelling has been established, researchers are currently limited in their ability to fit these models routinely. We make a series of recommendations for future research needs.

Systematic evaluations of the quality of research on a single prognostic biomarker are rare. We sought to evaluate the quality of prognostic research evidence for the association of C-reactive protein (CRP) with fatal and nonfatal events among patients with stable coronary disease. We searched MEDLINE (1966 to 2009) and EMBASE (1980 to 2009) and selected prospective studies of patients with stable coronary disease, reporting a relative risk for the association of CRP with death and nonfatal cardiovascular events. We included 83 studies, reporting 61,684 patients and 6,485 outcome events. No study reported a prespecified statistical analysis protocol; only two studies reported the time elapsed (in months or years) between initial presentation of symptomatic coronary disease and inclusion in the study. Studies reported a median of seven items (of 17) from the REMARK reporting guidelines, with no evidence of change over time. The pooled relative risk for the top versus bottom third of CRP distribution was 1.97 (95% confidence interval [CI] 1.78–2.17), with substantial heterogeneity (I² = 79.5). Only 13 studies adjusted for conventional risk factors (age, sex, smoking, obesity, diabetes, and low-density lipoprotein [LDL] cholesterol) and these had a relative risk of 1.65 (95% CI 1.39–1.96), I² = 33.7. Studies reported ten different ways of comparing CRP values, with weaker relative risks for those based on continuous measures. Adjusting for publication bias (for which there was strong evidence, Egger's p<0.001) using a validated method reduced the relative risk to 1.19 (95% CI 1.13–1.25). Only two studies reported a measure of discrimination (c-statistic). In 20 studies the detection rate for subsequent events could be calculated and was 31% for a 10% false positive rate, and the calculated pooled c-statistic was 0.61 (0.57–0.66). Multiple types of reporting bias, and publication bias, make the magnitude of any independent association between CRP and prognosis among patients with stable coronary disease sufficiently uncertain that no clinical practice recommendations can be made. Publication of prespecified statistical analytic protocols and prospective registration of studies, among other measures, might help improve the quality of prognostic biomarker research. Please see later in the article for the Editors' Summary

Joint modelling of longitudinal and time-to-event outcomes has received considerable attention over recent years. Commensurate with this has been a rise in statistical software options for fitting these models. However, these tools have generally been limited to a single longitudinal outcome. Here, we describe the classical joint model to the case of multiple longitudinal outcomes, propose a practical algorithm for fitting the models, and demonstrate how to fit the models using a new package for the statistical software platform R, joineRML. A multivariate linear mixed sub-model is specified for the longitudinal outcomes, and a Cox proportional hazards regression model with time-varying covariates is specified for the event time sub-model. The association between models is captured through a zero-mean multivariate latent Gaussian process. The models are fitted using a Monte Carlo Expectation-Maximisation algorithm, and inferences are based on approximate standard errors from the empirical profile information matrix, which are contrasted to an alternative bootstrap estimation approach. We illustrate the model and software on a real data example for patients with primary biliary cirrhosis with three repeatedly measured biomarkers. An open-source software package capable of fitting multivariate joint models is available. The underlying algorithm and source code makes use of several methods to increase computational speed.

Objective To determine whether the effect of South Asian ethnicity differs between studies of incidence and prognosis of coronary disease. Design Systematic literature review and meta-analysis, and cohort analysis from a national acute coronary syndrome (ACS) registry linked to mortality (National Institute of Cardiovascular Outcomes Research/Myocardial Infarction National Audit Project). Setting International for the review, and England and Wales for the cohort analysis. Patients The numbers of South Asians included in the meta-analysis were 111 555 (incidence) and 14 531 (prognosis) of whom 8251 were from the ACS cohort. Main outcome measures Incidence studies: non-fatal myocardial infarction or fatal coronary heart disease; prognostic studies: mortality; HRs for 1-year all-cause death in ACS cohort. Results South Asians had higher incidence of coronary disease compared with white subjects (HR 1.35 95% CI 1.30 to 1.40) based on meta-analysis of nine studies. Among 10 studies on prognosis, South Asians had better prognosis compared with white subjects (HR 0.78 95% CI 0.74 to 0.82). In the ACS cohort, the impact of diabetes (42.4% of South Asians, 16.9% of white subjects) on 1-year mortality was stronger in South Asians than white subjects (age-adjusted HR 1.83 95% CI 1.59 to 2.11 vs 1.53 95% CI 1.49 to 1.57). However, prognosis was better in South Asians even among diabetics, older people and those living in areas of the highest social deprivation. Conclusions South Asian ethnicity is associated with higher incidence of coronary disease, but lower mortality once coronary disease is manifest. The dissociation between effects on incidence and prognosis suggests that public health initiatives to reduce inequalities in mortality between South Asian and white populations should focus on primary prevention. This is a CALIBER study with ClinicalTrials.gov Identifier: NCT01163513.

Impactful academic research plays a stellar role in society, pressing to ask the question of how one measures the impact created by different areas of academic research. Measuring the societal, cultural, economic and scientific impact of research is currently the priority of the National Science Foundation, European Commission and several research funding agencies. The recently concluded United Kingdom’s national research quality exercise, the Research Excellence Framework (REF) 2014, which piloted impact assessment as part of the overall evaluation offers a lens to view how impact of research in different disciplines can be measured. Overall research quality was assessed through quality of outputs, ‘impact’ and research environment. We performed two studies using the REF 2014 as a case study. The first study on 363 Impact Case Studies (ICSs) submitted in 5 research areas (UoAs) reveals that, in general, the impact scores were constructed upon a combination of factors i.e. quantity of quartile-one (Q1) publications, quantity and value of grants/income, number of researchers stated in the ICSs, spin-offs created, discoveries/patents and presentation of esteem data, informing researchers/ academics of the factors to consider in order to achieve a better impact score in research impact assessments. However, there were differences among disciplines in terms of the role played by the factors in achieving their overall scores for the ICSs. The outcome of this study is thus a set of impact indicators, and their relationship with the overall score of impact of research in different disciplines as determined in REF2014, which would in the first instance provide some answers to impact measures that would be useful for researchers in different disciplines. The second study extracts the general themes of impact reported by universities by performing a word frequency analysis in all the ICSs submitted in the five chosen research areas, which were substantially varied owing to their fields.