Bayesian Hierarchical Modeling and the Integration of Heterogeneous Information on the Effectiveness of Cardiovascular Therapies

Abstract

Abstract-When making therapeutic decisions for an individual patient or formulating treatment guidelines on a population level, it is often necessary to utilize information arising from different study designs, settings, or treatments. In clinical practice, heterogeneous information is frequently synthesized qualitatively, whereas in comparative effectiveness research and guideline development, it is imperative that heterogeneous data are integrated quantitatively and in a manner that accurately captures the true uncertainty in the results. Bayesian hierarchical modeling is a technique that utilizes all available information from multiple sources and naturally yields a revised estimate of the treatment effect associated with each source. A hierarchical model consists of multiple levels (ie, a hierarchy) of probability distributions that represent relationships between information arising within single populations or trials, as well as relationships between information arising from different populations or trials. We describe the structure of Bayesian hierarchical models and discuss their advantages over simpler models when multiple information sources are relevant. Key Words: multilevel analysis Ⅲ comparative effectiveness research Ⅲ practice guidelines H ealth care providers must often decide whether to recommend a therapy for a patient for whom directly relevant treatment outcome data are limited or absent. For example, there may be limited experience with the therapy, the disease state may be rare, or the patient may be a member of a population that is underrepresented in available clinical studies. Similarly, those setting health care policy, authoring treatment guidelines, or making coverage determinations must also often make decisions regarding the effectiveness of treatments when directly relevant information is limited. An intuitive approach, frequently used by practicing clinicians, is to consider evidence from related populations and therapies, although the similarity to the patient or population of interest may vary significantly. For example, efficacy data for other drugs in the same class may be available, or the therapy may have been evaluated in populations with different comorbidities, demographic characteristics, or disease severities.Whether at the individual patient or population level, this type of decision-making requires the synthesis of information from heterogeneous sources. Many common statistical methods assume either homogeneity (eg, fixed-effects meta-analysis) or complete independence across populations and are thus ill-suited for the quantitative synthesis of heterogeneous data. Hierarchical, or multilevel, modeling is a statistical method that can be used to quantitatively and coherently combine heterogeneous information. A hierarchical model consists of multiple levels (ie, a hierarchy) of probability distributions that represent relationships between information arising within single populations or trials, as well as relationships between information arising from different popul...

An Empirical Investigation of Bayesian Hierarchical Modeling with Unidimensional IRT Models

“…However, to date little work has investigated the effect of hyperpriors on model parameters (see e.g., Kim, Cohen, Baker, Subkoviak, & Leonard, 1994). Given that the advantages of hierarchical modeling over nonhierarchical modeling have been empirically demonstrated in other areas, such as Bayesian treed models (Chipman, George, & McCulloch, 2002), fossil calibration (Heath, 2012), multiple-recapture population estimation (Clark, Ferraz, Oguge, Hays, & DiCostanzo, 2005), and Cardiovascular therapies (Kwok & Lewis, 2011), it is believed that the Bayesian estimation with hierarchical priors specified for item hyperparameters shall provide us with a better approach in modeling unidimensional item response data when appropriate prior information is not readily available and when datasets are not sufficiently large.…”

An adaptive platform trial for evaluating treatments in patients with life‐threatening hemorrhage from traumatic injuries: Rationale and proposal

“…Thus, estimates of the treatment effects in a subgroup will be based on the outcomes in that subgroup, as well as the consistency of the apparent treatment effects across subgroups. 23,39 Because the platform trial is intended to continue over an extended period, with likely improvements in the effectiveness of the existing standard of trauma care, the inferential model will include a statistical adjustment for time to allow for secular trends. 40 This adjustment, along with randomization ratios designed to maintain a sufficient and stable allocation to the standard of care arm within each domain, 19 helps to ensure valid estimation of treatment effects despite variations in the patient populations and concomitant therapies over time.…”

An adaptive platform trial for evaluating treatments in patients with life‐threatening hemorrhage from traumatic injuries: Ethical and US regulatory considerations

“…This will have additional benefits, including determining how patient age affects pathophysiology and outcomes, and improving the precision of the clinical trial in measuring treatment effects in these subpopulations by leveraging outcome data from non-pregnant adults (e.g., using hierarchical statistical models). 35,36…”