Indirect estimation of a discrete-state discrete-time model using secondary data analysis of regression data.
TL;DR: This paper presents an approach that allows the use of published regression data in a multi- state model when the published study may have ignored intermediary states in the multi-state model, called the Lemonade Method.
Abstract: Multi-state models of chronic disease are becoming increasingly important in medical research to describe the progression of complicated diseases. However, studies seldom observe health outcomes over long time periods. Therefore, current clinical research focuses on the secondary data analysis of the published literature to estimate a single transition probability within the entire model. Unfortunately, there are many difficulties when using secondary data, especially since the states and transitions of published studies may not be consistent with the proposed multi-state model. Early approaches to reconciling published studies with the theoretical framework of a multi-state model have been limited to data available as cumulative counts of progression. This paper presents an approach that allows the use of published regression data in a multi-state model when the published study may have ignored intermediary states in the multi-state model. Colloquially, we call this approach the Lemonade Method since when study data give you lemons, make lemonade. The approach uses maximum likelihood estimation. An example is provided for the progression of heart disease in people with diabetes.
Citations
More filters
TL;DR: A taxonomy based on possible scenarios faced by the analyst when dealing with the available evidence is developed that can help modelers identify the most appropriate methods to use when synthesizing the available data for a given model parameter.
46 citations
TL;DR: A new computer tool designed for chronic disease modeling is described and the modeling capabilities of this tool were used to model the Michigan model for diabetes.
34 citations
TL;DR: A likelihood approach to correctly model the design of clinical studies under the conditions where 1) the theoretical model may include an instantaneous state of distinct interest to the researchers, and 2) the study design may be such that study data can not be used to estimate a single parameter in the theoreticalmodel of interest.
16 citations
Dissertation•
01 Jan 2012
TL;DR: In this paper, a taxonomy of the methodological and analytical issues in the use and synthesis of evidence for cost effectiveness modelling is presented, with guidance on appropriate synthesis methodologies to use and identifying areas where further methodological contributions are needed.
Abstract: Health care economic evaluations assess the costs and consequences of competing interventions, programmes or services. Such assessments use a decision model, with
parameters informed by available evidence. Evidence, however, is rarely derived from a single source, in which case researchers are expected to combine information on multiple sources. This thesis contributes to the methodological debate on the use of evidence, particularly, the use of individual level data (IPD), for cost effectiveness analysis.
This thesis defines a taxonomy which summarises the methodological and analytical issues in the use and synthesis of evidence for cost effectiveness modelling. For
alternative parameter types (e.g. relative effectiveness, costs) the taxonomy offers guidance on appropriate synthesis methodologies to use and identifies areas where
further methodological contributions are needed. The thesis also explores methods of synthesis of IPD and develops novel frameworks which allow both IPD and AD to be jointly modelled, specifically in estimating relative effectiveness. The use of IPD from studies is found desirable, particularly when the estimation of subgroup effects is of interest.
An applied decision model of the cost effectiveness of smoke alarm equipment in households with pre-school children is developed within this thesis. This application
offers a means to evaluate the impact of using IPD on the cost effectiveness outcomes, compared to the use of AD. The thesis examines the advantages of having access to IPD when quantifying decision uncertainty. Additionally, it discusses the use of IPD in estimating the value of further research. Specifically, a framework is used which allows considering population subgroups. It is argued that the use of IPD allows a more suitable characterisation of decision uncertainty, appropriately allowing for subgroup value of information analysis.
8 citations
27 Nov 2013
TL;DR: In this article, reference disease models predict progression of disease within given populations, utilizing publically available clinical data and risk equations, to give a birds-eye view of clinical trials by allowing multiple trials to be systematically compared simultaneously via parallel processing/High Performance Computing which allows competition among alternative equations/hypothesis combinations; cross validation; and, then ranks results according to fitness via a fitness engine.
Abstract: A method wherein reference disease models predict progression of disease within given populations, utilizing publically available clinical data and risk equations, to give a birds-eye view of clinical trials by allowing multiple trials to be systematically compared simultaneously via parallel processing/High Performance Computing which allows competition among alternative equations/hypothesis combinations; cross validation; and, then ranks results according to fitness via a fitness engine.
7 citations
References
More filters
TL;DR: This research was motivated by a desire to model the progression of a chronic disease through various disease stages when data are not available to directly estimate all the transition parameters in the model.
Abstract: SUMMARY This research was motivated by a desire to model the progression of a chronic disease through various disease stages when data are not available to directly estimate all the transition parameters in the model. This is a common occurrence when time and expense make it infeasible to follow a single cohort to estimate all the transition parameters. One diculty of developing a model of chronic disease progression from such data is that the available studies often do not include the transitions of interest. For example, in our model of diabetic nephropathy, many clinical studies did not dierentiate between patients without nephropathy and those who had microalbuminuria (a pre-clinical stage of nephropathy). Another diculty was a lack of data to directly estimate parameters of interest. We consider models which can accommodate such diculties. In this paper we consider the problem of estimating parameters of a discrete-time Markov process when longitudinal data describing the entire process are not available. First, we present a likelihood approach to estimate parameters of a discrete-time Markov model. Next, we use simulation to investigate thenite- sample behaviour of our approach. Finally, we present two examples: a model of diabetic nephropathy and a model of cardiovascular disease in diabetes. Copyright ? 2006 John Wiley & Sons, Ltd.
16 citations
TL;DR: A mortality model where nationally representative survey data on risk factor distributions are combined with data on cohort mortality rates to increase information, i.e., a fixed marginal risk factor distribution is combined with a cohort model representing unobserved individual risk heterogeneity is presented.
Abstract: In analyzing mortality data there may be available information from survey and other sources that describe the marginal distribution of risk factors We present a mortality model where nationally representative survey data on risk factor distributions are combined with data on cohort mortality rates to increase information, ie, a fixed marginal risk factor distribution is combined with a cohort model representing unobserved individual risk heterogeneity The model is applied to lung cancer mortality in nine US white male cohorts aged 30 to 70 in 1950 and followed 38 years Estimates of the cohort specific proportions of smokers were made from the National Health Interview Survey Comparisons are made for models with different patterns of changes with age of individual heterogeneity
10 citations
Additional excerpts
...[13, 14]....
[...]
TL;DR: In this paper, a general data combining statistical strategy is presented and illustrated for smoking behavior and lung cancer mortality and National Health Interview Survey data on smoking is combined with U.S. vital statistics data 1950 to 1987 to analyze the joint distribution of total and Lung cancer mortality.
5 citations