Biomedical subjects

Richard D Riley

Publications and source records attributed to Richard D Riley.

5 recordsLinked to original sources

PubMed2007

Bivariate random-effects meta-analysis and the estimation of between-study correlation.

BACKGROUND: When multiple endpoints are of interest in evidence synthesis, a multivariate meta-analysis can jointly synthesise those endpoints and utilise their correlation. A multivariate random-effects meta-analysis must incorporate and estimate the between-study correlation (rhoB). METHODS: In this paper we assess maximum likelihood estimation of a general normal model and a generalised model for bivariate random-effects meta-analysis (BRMA). We consider two applied examples, one involving a diagnostic marker and the other a surrogate outcome. These motivate a simulation study where estimation properties from BRMA are compared with those from two separate univariate random-effects meta-analyses (URMAs), the traditional approach. RESULTS: The normal BRMA model estimates rhoB as -1 in both applied examples. Analytically we show this is due to the maximum likelihood estimator sensibly truncating the between-study covariance matrix on the boundary of its parameter space. Our simulations reveal this commonly occurs when the number of studies is small or the within-study variation is relatively large; it also causes upwardly biased between-study variance estimates, which are inflated to compensate for the restriction on rhoB. Importantly, this does not induce any systematic bias in the pooled estimates and produces conservative standard errors and mean-square errors. Furthermore, the normal BRMA is preferable to two normal URMAs; the mean-square error and standard error of pooled estimates is generally smaller in the BRMA, especially given data missing at random. For meta-analysis of proportions we then show that a generalised BRMA model is better still. This correctly uses a binomial rather than normal distribution, and produces better estimates than the normal BRMA and also two generalised URMAs; however the model may sometimes not converge due to difficulties estimating rhoB. CONCLUSION: A BRMA model offers numerous advantages over separate univariate synthesises; this paper highlights some of these benefits in both a normal and generalised modelling framework, and examines the estimation of between-study correlation to aid practitioners.

CD4 Lymphocyte Count↗

PubMed2005

Meta-analysis of genetic studies using Mendelian randomization--a multivariate approach.

In traditional epidemiological studies the association between phenotype (risk factor) and disease is often biased by confounding and reverse causation. As a person's genotype is assigned by a seemingly random process, genes are potentially useful instrumental variables for adjusting for such bias. This type of adjustment combines information on the genotype-disease association and the genotype-phenotype association to estimate the phenotype-disease association and has become known as Mendelian randomization. The information on genotype-disease and genotype-phenotype may well come from a meta-analysis. In such a synthesis, a multivariate approach needs to be used whenever some studies provide evidence on both the genotype-phenotype and genotype-disease associations. This paper presents two multivariate meta-analytical models, which differ in their treatment of the heterogeneities (between-study variances). Heterogeneities on the genotype-phenotype and genotype-disease associations may be highly correlated, but a multivariate model that parameterizes the heterogeneity directly is difficult to fit because that correlation is poorly estimated. We advocate an alternative model that treats the heterogeneities on genotype-phenotype and phenotype-disease as being independent. This model fits readily and implicitly defines the correlation between the heterogeneities on genotype-phenotype and genotype-disease. We show how either maximum likelihood or a Bayesian approach with vague prior distributions can be used to fit the alternative model.

Coronary Disease↗

PubMed2005

Primer: an evidence-based approach to prognostic markers.

Prognostic markers can help to identify patients at different degrees of risk for specific outcomes, facilitate treatment choice, and aid patient counseling. Compared with other research designs, prognostic studies have been relatively neglected in the broad efforts to improve the quality of medical research, despite their ubiquity. Large protocol-driven, prospective studies are the ideal, with clear, unbiased reporting of the methods used and the results obtained. Unfortunately, published prognostic studies rarely meet such standards, and in this article we discuss their main problems and how they can be improved. In particular, an evidence-based approach to prognostic markers is required, as it is usually difficult to ascertain the benefit of a marker from single studies and a clear view is only likely to emerge from looking across multiple studies. Current systematic reviews and meta-analyses often fail to provide clear evidence-based answers, and rather only draw attention to the paucity of good-quality evidence. Prospectively planned pooled analyses of high-quality studies, along with general availability of individual patient data and adherence to reporting guidelines, would help alleviate many of these problems.

Biomarkers, Tumor↗

PubMed2004

A systematic review of molecular and biological tumor markers in neuroblastoma.

PURPOSE: The aim of this study was to conduct a systematic review, and where possible meta-analyses, of molecular and biological tumor markers described in neuroblastoma, and to establish an evidence-based perspective on their clinical value for the screening, diagnosis, prognosis, and monitoring of patients. EXPERIMENTAL DESIGN: A well-defined, reproducible search strategy was used to identify the relevant literature from 1966 to February 2000. RESULTS: A total of 428 papers studying the use of 195 different tumor markers in neuroblastoma were identified. Small sample sizes, poor statistical reporting, large heterogeneity across studies (e.g., in cutoff levels), and publication bias limited meta-analysis to the area of prognosis only; MYCN, chromosome 1p, DNA index, vanillylmandelic acid:homovanillic acid ratio, CD44, Trk-A, neuron-specific enolase, lactate dehydrogenase, ferritin, and multidrug resistance were all identified as potentially important prognostic tools. CONCLUSIONS: This systematic review forms a knowledge base of the tumor markers studied thus far in neuroblastoma, and has identified some of the most important prognostic markers, which should be considered in future research and treatment strategies. Importantly, the review has also highlighted some general problems across primary tumor marker studies, in particular poor and heterogeneous reporting. These need to be addressed to allow better clinical interpretation and enable more appropriate evidence-based reviews in the future. In particular, collaboration of cancer research groups is needed to enable bigger sample sizes, standardize methods of analysis and reporting, and facilitate the pooling of individual patient data.

Biomarkers, Tumor↗

PubMed2004

Sensitivity analyses allowed more appropriate and reliable meta-analysis conclusions for multiple outcomes when missing data was present.

OBJECTIVE: A major problem for meta-analysis of multiple outcomes is the unavailability of some estimates from published and unpublished studies. Dissemination bias, in how and what outcomes are reported or published, may be causing this incompleteness. This article illustrates these problems and presents possible sensitivity analyses to allow the most reliable conclusions. STUDY DESIGN AND SETTING: In a systematic review of prognostic marker MYC-N in neuroblastoma, meta-analysis for overall survival (OS) and disease-free survival (DFS) was of interest. Only 17 published studies enabled extraction of both outcome estimates, 25 enabled only DFS, 39 enabled only OS, and 70 enabled neither outcome. Unidentified unpublished studies may also exist. We assessed the robustness of the pooled estimates to the problem of missing information. Because OS and DFS estimates seemed to be related, we used the known outcome estimates to predict estimates known to be missing, and combined this approach with existing methods for assessing dissemination bias. RESULTS: The results of the sensitivity analyses suggested that the original meta-analysis results were likely to be an overestimate of the true OS and DFS effect-sizes but strengthened the belief that MYC-N is a potentially important prognostic marker in neuroblastoma. CONCLUSION: Sensitivity analyses in meta-analysis allow more appropriate and reliable conclusions when problems such as unavailable estimates and dissemination bias are present.

Biomarkers, Tumor↗