Combining data and meta-analysis to build Bayesian networks for clinical decision support

Yet, Barbaros
Rasmussen, Todd E.
Tai, Nigel R. M.
Marsh, D. William R.
Complex clinical decisions require the decision maker to evaluate multiple factors that may interact with each other. Many clinical studies, however, report 'univariate' relations between a single factor and outcome. Such univariate statistics are often insufficient to provide useful support for complex clinical decisions even when they are pooled using meta-analysis. More useful decision support could be provided by evidence-based models that take the interaction between factors into account. In this paper, we propose a method of integrating the univariate results of a meta-analysis with a clinical dataset and expert knowledge to construct multivariate Bayesian network (BN) models. The technique reduces the size of the dataset needed to learn the parameters of a model of a given complexity. Supplementing the data with the meta-analysis results avoids the need to either simplify the model - ignoring some complexities of the problem - or to gather more data. The method is illustrated by a clinical case study into the prediction of the viability of severely injured lower extremities. The case study illustrates the advantages of integrating combined evidence into BN development: the BN developed using our method outperformed four different data-driven structure learning methods, and a well-known scoring model (MESS) in this domain.


Value of information analysis for interventional and counterfactual Bayesian networks in forensic medical sciences
Constantinou, Anthony Costa; Yet, Barbaros; Fenton, Norman; Neil, Martin; Marsh, William (2016-01-01)
Objectives: Inspired by real-world examples from the forensic medical sciences domain, we seek to determine whether a decision about an interventional action could be subject to amendments on the basis of some incomplete information within the model, and whether it would be worthwhile for the decision maker to seek further information prior to suggesting a decision.
Building Bayesian networks based on DEMATEL for multiple criteria decision problems: A supplier selection case study
Kaya, Rukiye; Yet, Barbaros (2019-11-01)
Bayesian Networks (BNs) are effective tools for providing decision support based on expert knowledge in uncertain and complex environments. However, building knowledge-based BNs is still a difficult task that lacks systematic and widely accepted methodologies, especially when knowledge is elicited from multiple experts. We propose a novel method that systematically integrates a widely used Multi Criteria Decision Making (MCDM) approach called Decision Making Trial and Evaluation Laboratory (DEMATEL) in BN c...
Towards a Method for Building Causal Bayesian Networks for Prognostic Decision Support
Yet, Barbaros; Marsh, William; Fenton, Norman (null; 2011-07-02)
We describe a method of building a decision support system for clinicians deciding between interventions, using Bayesian Networks (BNs). Using a case study of the amputation of traumatically injured extremities, we explain why existing prognostic models used as decision aids have not been successful in practice. A central idea is the importance of modeling causal relationships, both so that the model conforms to the clinicians ‟ way of reasoning and so that we can predict the probable effect of the availabl...
Shared decision making: a serious game based on OSCE for clinicians
Sülün, Ahmet; Yet, Barbaros; Department of Cognitive Sciences (2022-8-31)
Shared decision making(SDM) is an essential process to improve outcomes and reflect patient views in medical consultation. In SDM, the treatment that patient will take is a decision reached by the participation of both the clinician and the patient. To achieve SDM, clinicians should explain possible treatment options with their pros and cons and encourage patients to join in the process, and patients should state their ideas about the options and preferences about the outcomes. This process follows three st...
Clinical evidence framework for Bayesian networks
Yet, Barbaros; Tai, Nigel R. M.; Marsh, D. William R. (2017-01-01)
There is poor uptake of prognostic decision support models by clinicians regardless of their accuracy. There is evidence that this results from doubts about the basis of the model as the evidence behind clinical models is often not clear to anyone other than their developers. In this paper, we propose a framework for representing the evidence-base of a Bayesian network (BN) decision support model. The aim of this evidence framework is to be able to present all the clinical evidence alongside the BN itself. ...
Citation Formats
B. Yet, T. E. Rasmussen, N. R. M. Tai, and D. W. R. Marsh, “Combining data and meta-analysis to build Bayesian networks for clinical decision support,” JOURNAL OF BIOMEDICAL INFORMATICS, pp. 373–385, 2014, Accessed: 00, 2020. [Online]. Available: