Prognostic Bayesian networks
Peter Rosseel2007, Journal of Biomedical Informatics
Sign up for access to the world's latest research
checkGet notified about relevant papers
checkSave papers to use in your research
checkJoin the discussion with peers
checkTrack your impact
Abstract
Prognostic models are tools to predict the future outcome of disease and disease treatment, one of the fundamental tasks in clinical medicine. This article presents the prognostic Bayesian network (PBN) as a new type of prognostic model that builds on the Bayesian network methodology, and implements a dynamic, process-oriented view on prognosis. A PBN describes the mutual relationships between variables that come into play during subsequent stages of a care process and a clinical outcome. A dedicated procedure for inducing these networks from clinical data is presented. In this procedure, the network is composed of a collection of local supervised learning models that are recursively learned from the data. The procedure optimizes performance of the network's primary task, outcome prediction, and handles the fact that patients may drop out of the process in earlier stages. Furthermore, the article describes how PBNs can be applied to solve a number of information problems that are related to medical prognosis.
Related papers
Prognostic Bayesian networks: I: Rationale, learning procedure, and clinical use
Journal of Biomedical Informatics, 2007
Prognostic models are tools to predict the future outcome of disease and disease treatment, one of the fundamental tasks in clinical medicine. This article presents the prognostic Bayesian network (PBN) as a new type of prognostic model that builds on the Bayesian network methodology, and implements a dynamic, process-oriented view on prognosis. A PBN describes the mutual relationships between variables that come into play during subsequent stages of a care process and a clinical outcome. A dedicated procedure for inducing these networks from clinical data is presented. In this procedure, the network is composed of a collection of local supervised learning models that are recursively learned from the data. The procedure optimizes performance of the network’s primary task, outcome prediction, and handles the fact that patients may drop out of the process in earlier stages. Furthermore, the article describes how PBNs can be applied to solve a number of information problems that are re...
Dynamic Bayesian networks as prognostic models for clinical patient management
Journal of biomedical informatics, 2008
Prognostic models in medicine are usually been built using simple decision rules, proportional hazards models, or Markov models. Dynamic Bayesian networks (DBNs) offer an approach that allows for the incorporation of the causal and temporal nature of medical domain knowledge as elicited from domain experts, thereby allowing for detailed prognostic predictions. The aim of this paper is to describe the considerations that must be taken into account when constructing a DBN for complex medical domains and to demonstrate their usefulness in practice. To this end, we focus on the construction of a DBN for prognosis of carcinoid patients, compare performance with that of a proportional hazards model, and describe predictions for three individual patients. We show that the DBN can make detailed predictions, about not only patient survival, but also other variables of interest, such as disease progression, the effect of treatment, and the development of complications. Strengths and limitations of our approach are discussed and compared with those offered by traditional methods.
A New Method for Predicting Patient Survivorship Using Efficient Bayesian Network Learning
Cancer Informatics, 2014
The purpose of this investigation is to develop and evaluate a new Bayesian network (BN)-based patient survivorship prediction method. The central hypothesis is that the method predicts patient survivorship well, while having the capability to handle high-dimensional data and be incorporated into a clinical decision support system (CDSS). We have developed EBMC_Survivorship (EBMC_S), which predicts survivorship for each year individually. EBMC_S is based on the EBMC BN algorithm, which has been shown to handle high-dimensional data. BNs have excellent architecture for decision support systems. In this study, we evaluate EBMC_S using the Molecular Taxonomy of Breast Cancer International Consortium (METABRIC) dataset, which concerns breast tumors. A 5-fold cross-validation study indicates that EMBC_S performs better than the Cox proportional hazard model and is comparable to the random survival forest method. We show that EBMC_S provides additional information such as sensitivity analyses, which covariates predict each year, and yearly areas under the ROC curve (AUROCs). We conclude that our investigation supports the central hypothesis.
Towards a Method of Building Causal Bayesian Networks for Prognostic Decision Support
2011
With the current trend toward pervasive health care, personalised health care, and the ever growing amount of evidence coming from biomedical research, methods that can handle reasoning and learning under uncertainty are becoming more and more important. The ongoing developments of the past two decades in the field of artificial intelligence have made it now possible to apply probabilistic methods to solve problems in real-world biomedical domains. Many representations have been suggested for solving problems in biomedical domains. Bayesian networks and influence diagrams have proved themselves useful for problems where probabilistic uncertainty is important, such as medical decision making and prognostics; logics have proved themselves useful in areas such as diagnosis. In recent years, the field of statistical relational learning has led to new formalisms which integrate probabilistic graphical models and logic. These formalisms provide exciting new opportunities for medical applications as they can be used to learn from structured medical data and reason with them using both logical and probabilistic methods. Another major theme for this workshop is in the handling of semantic concepts such as space and time in the biomedical domain. Space is an important concept when developing probabilistic models of, e.g., the spread of infectious disease, either in the hospital or in the community at large. Temporal reasoning is especially important in the context of personalised health care. Consider for example the translation of biomedical research that is expected to lead to more complex decision making, e.g., how to optimally select a sequence of drugs targeting biological pathways when treating a malignant tumour. There are strong expectations that such personalised and specific drugs will soon be available in the clinical practice. We selected eleven papers for full presentation. All these contributions fit the format of the workshop: they develop new approaches for integrating logical and semantical concepts with probabilistic methods or apply existing methods to problems from the biomedical domain. Furthermore, we feel honoured to have Jesse Davis and Milos Hauskrecht as invited speakers. Jesse Davis has made significant contributions in the application of statistical relational learning techniques in the medical domain. Milos Hauskrecht is well-known for his work in the analysis of time-series data (e.g., using POMDPs) in biomedical informatics. The organisers would like to acknowledge the support from the AIME organisation. We would also like to thank the program committee members for their support and reviewing, which have improved the accepted papers significantly.
Bayesian Networks for Clinical Decision Support in Lung Cancer Care
PLoS ONE, 2013
Survival prediction and treatment selection in lung cancer care are characterised by high levels of uncertainty. Bayesian Networks (BNs), which naturally reason with uncertain domain knowledge, can be applied to aid lung cancer experts by providing personalised survival estimates and treatment selection recommendations. Based on the English Lung Cancer Database (LUCADA), we evaluate the feasibility of BNs for these two tasks, while comparing the performances of various causal discovery approaches to uncover the most feasible network structure from expert knowledge and data. We show first that the BN structure elicited from clinicians achieves a disappointing area under the ROC curve of 0.75 (± 0.03), whereas a structure learned by the CAMML hybrid causal discovery algorithm, which adheres with the temporal restrictions, achieves 0.81 (± 0.03). Second, our causal intervention results reveal that BN treatment recommendations, based on prescribing the treatment plan that maximises survival, can only predict the recorded treatment plan 29% of the time. However, this percentage rises to 76% when partial matches are included.
Bayesian networks for patient monitoring
Artificial Intelligence in Medicine, 1992
Berzuini, C., R. Bellazzi, S. Quaglini and D.J. Spiegelhalter, Bayesian networks for patient monitoring, Artificial Intelligence in Medicine 4 (1992) 243-260.
Predicting Disease Complications Using a Stepwise Hidden Variable Approach for Learning Dynamic Bayesian Networks
—Predicting Diabetes Type 2 Mellitus (T2DM) complications such as retinopathy and liver disease is still a challenge despite being a growing public health concern worldwide. This is due to the complex interactions between complications and other features, as well as between the different complications , themselves. What is more, there are likely to be many unmeasured effects that impact the disease progression of different patients. Probabilistic graphical models such as Dynamic Bayesian Networks (DBNs) have demonstrated much promise in the modeling of disease progression and they can naturally incorporate hidden (latent) variables using the EM algorithm. Unlike deep learning approaches that attempt to model complex interactions in data by using a large number of hidden variables, we adopt a different approach. We are interested in models that not only capture unmeasured effects but are also transparent in how they model data so that knowledge about disease processes can be extracted and trust in the model can be maintained by clinicians. As a result, we have developed a step-wise hidden variable structure learning process that incrementally adds hidden variables based on the IC* algorithm. To the best of our knowledge, this is the first study for classifying disease complication using a step-wise learning methodology for identifying hidden and T2DM features with a DBN structure from clinical data. Our extensive set of experiments show that the proposed method improves classification accuracy, identifying the correct number of hidden variables, and targeting their precise location within the network structure.
Patient-specific Bayesian Network in a Clinical Environment
2020
Patient-specific Bayesian Network in a Clinical Environment "If used properly, clinical decision support systems have the potential to change the way medicine has been taught and practiced."-Berner, 2007.
Dynamic Bayesian Networks to predict sequences of organ failures in patients admitted to ICU
Journal of Biomedical Informatics, 2014
You may download, copy and otherwise use the AAM for non-commercial purposes provided that your license is limited by the following restrictions: (1) You may use this AAM for non-commercial purposes only under the terms of the CC-BY-NC-ND license. (2) The integrity of the work and identification of the author, copyright owner, and publisher must be preserved in any copy.
Bayesian networks for health care support
2016
BFs to analyse the impact of Diagnosis on Number of meetings The analysis of observational data requires the use of a model, such as a multivariate regression. Bayesian networks (BNs) are well known as expert systems but can also be used to model data. A BN is a probabilistic model that represents the probabilistic relationships and conditional dependencies among variables. A BN allows probabilistic inference to be performed coherently, using the law of probability. Also a BN has the from the Barts and the London HPB (HepatoPancreaticoBiliary) centre following some changes to the MDT process. By evaluating the strength of each of the associations, we examine whether the MDT process has improved treatment recommendations for these patients.. 8 1.2 Structure of this thesis Chapter 2 discusses the potential benefits of Bayesian methods for introducing new changes in health service. We review the existing approaches to examine the effectiveness of complex health care initiatives and discuss the pitfalls of these approaches. Chapter 3 introduces BNs and reviews existing methods for their construction, including both expert judgement and learning from data. The importance of dynamic
Bayesian network classifier for medical data analysis
International Journal of Computers …, 2009
Bayesian networks encode causal relations between variables using probability and graph theory. They can be used both for prediction of an outcome and interpretation of predictions based on the encoded causal relations. In this paper we analyse a tree-like Bayesian network learning algorithm optimised for classification of data and we give solutions to the interpretation and analysis of predictions. The classification of logical -i.e. binary -data arises specifically in the field of medical diagnosis, where we have to predict the survival chance based on different types of medical observations or we must select the most relevant cause corresponding again to a given patient record. Surgery survival prediction was examined with the algorithm. Bypass surgery survival chance must be computed for a given patient, having a data-set of medical examinations for patients.
Decision support using Bayesian networks for clinical decision making
2012
This thesis investigates the use of Bayesian Networks (BNs), augmented by the Dynamic Discretization Algorithm, to model a variety of clinical problems. In particular, the thesis demonstrates four novel applications of BN and dynamic discretization to clinical problems. Firstly, it demonstrates the flexibility of the Dynamic Discretization Algorithm in modeling existing medical knowledge using appropriate statistical distributions. Many practical applications of BNs use the relative frequency approach while translating existing medical knowledge to a prior distribution in a BN model. This approach does not capture the full uncertainty surrounding the prior knowledge. Secondly, it demonstrates a novel use of the multinomial BN formulation in learning parameters of categorical variables. The traditional approach requires fixed number of parameters during the learning process but this framework allows an analyst to generate a multinomial BN model based on the number of parameters requi...
AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning
ArXiv, 2018
Clinical prognostic models derived from largescale healthcare data can inform critical diagnostic and therapeutic decisions. To enable off-theshelf usage of machine learning (ML) in prognostic research, we developed AUTOPROGNOSIS: a system for automating the design of predictive modeling pipelines tailored for clinical prognosis. AUTOPROGNOSIS optimizes ensembles of pipeline configurations efficiently using a novel batched Bayesian optimization (BO) algorithm that learns a low-dimensional decomposition of the pipelines high-dimensional hyperparameter space in concurrence with the BO procedure. This is achieved by modeling the pipelines performances as a black-box function with a Gaussian process prior, and modeling the similarities between the pipelines baseline algorithms via a sparse additive kernel with a Dirichlet prior. Meta-learning is used to warmstart BO with external data from similar patient cohorts by calibrating the priors using an algorithm that mimics the empirical Bay...
Learning Bayesian networks for clinical time series analysis
Journal of Biomedical Informatics
Autonomous chronic disease management requires models that are able to interpret time series data from patients. However, construction of such models by means of machine learning requires the availability of costly health-care data, often resulting in small samples. We analysed data from chronic obstructive pulmonary disease (COPD) patients with the goal of constructing a model to predict the occurrence of exacerbation events, i.e., episodes of decreased pulmonary health status. Data from 10 COPD patients, gathered with our home monitoring system, were used for temporal Bayesian network learning, combined with bootstrapping methods for data analysis of small data samples.For comparison a temporal variant of augmented naive Bayes models and a temporal nodes Bayesian network (TNBN) were constructed. The performances of the methods were first tested with synthetic data. Subsequently, different COPD models were compared to each other using an external validation data set. The model lear...
Bayesian Networks for Risk Prediction Using Real-World Data: A Tool for Precision Medicine
Value in Health, 2019
The fields of medicine and public health are undergoing a data revolution. An increasing availability of data has brought about a growing interest in machine-learning algorithms. Our objective is to present the reader with an introduction to a knowledge representation and machine-learning tool for risk estimation in medical science known as Bayesian networks (BNs). Study Design: In this article we review how BNs are compact and intuitive graphical representations of joint probability distributions (JPDs) that can be used to conduct causal reasoning and risk estimation analysis and offer several advantages over regression-based methods. We discuss how BNs represent a different approach to risk estimation in that they are graphical representations of JPDs that take the form of a network representing model random variables and the influences between them, respectively. Methods: We explore some of the challenges associated with traditional risk prediction methods and then describe BNs, their construction, application, and advantages in risk prediction based on examples in cancer and heart disease. Results: Risk modeling with BNs has advantages over regressionbased approaches, and in this article we focus on three that are relevant to health outcomes research: (1) the generation of network structures in which relationships between variables can be easily communicated; (2) their ability to apply Bayes's theorem to conduct individual-level risk estimation; and (3) their easy transformation into decision models. Conclusions: Bayesian networks represent a powerful and flexible tool for the analysis of health economics and outcomes research data in the era of precision medicine.
Using hierarchical dynamic Bayesian networks to investigate dynamics of organ failure in patients in the Intensive Care Unit
Journal of Biomedical Informatics, 2010
In intensive care medicine close monitoring of organ failure status is important for the prognosis of patients and for choices regarding ICU management. Major challenges in analyzing the multitude of data pertaining to the functioning of the organ systems over time are to extract meaningful clinical patterns and to provide predictions for the future course of diseases. With their explicit states and probabilistic state transitions, Markov models seem to fit this purpose well. In complex domains such as intensive care a choice is often made between a simple model that is estimated from the data, or a more complex model in which the parameters are provided by domain experts.
Weighted Bayesian Belief Network: A Computational Intelligence Approach for Predictive Modeling in Clinical Datasets
Hindawi Computational Intelligence and Neuroscience, 2022
There are growing concerns about the mortality due to Breast cancer many of which often result from delayed detection and treatment. So an effective computational approach is needed to develop a predictive model which will help patients and physicians to manage the situation timely. is study presented a Weighted Bayesian Belief Network (WBBN) modeling for breast cancer prediction using the UCI breast cancer dataset. New automated ranking method was used to assign proper weights to attribute value pair based on their impact on causing the disease. Association between attributes was generated using weighted association rule mining between two attributes, multiattributes, and with class labels to generate rules. Weighted Bayesian confidence and weighted Bayesian lift measures were used to produce strong rules to build the model. To build WBBN, the Open Markov tool was used for structure and parametric learning using generated strong rules. e model was trained using 70% records and tested on 30% records with a threshold value of minimum support 36% and condence 70% which produced results with an accuracy of 97.18%. Experimental results show that WBBN achieved better results in most cases compared to other predictive models. e study would contribute to the fight against breast cancer and the quality of treatment.
Tree-like bayesian network classifiers for surgery survival chance prediction
Int. J. of Computers, Communications and …, 2008
Bayesian Networks encode causal relations between variables using probability and graph theory. We exploit the causal relations to detect dependency structures in database consisting of a small number of observations having high dimensions. Bypass surgery survival chance must be inferred from a database consisting of 66 medical examinations for 313 patients. Tree-like Bayesian were inferred based on mutual information and than analysed for classification of data, respect to survival. Bayesian Network approach allows us to interpret the predictions of the system thus helping the doctor in after surgery treatment prescription. In this paper we present the used methods and results on artificial data.
A Functional Model for Structure Learning and Parameter Estimation in Continuous Time Bayesian Network: An Application in Identifying Patterns of Multiple Chronic Conditions
IEEE Access
Bayesian networks are powerful statistical models to study the probabilistic relationships among sets of random variables with significant applications in disease modeling and prediction. Here, we propose a continuous time Bayesian network with conditional dependencies, represented as regularized Poisson regression, to model the impact of exogenous variables on the conditional intensities of the network. We also propose an adaptive group regularization method with an intuitive early stopping feature based on Gaussian mixture model clustering for efficient learning of the structure and parameters of the proposed network. Using a dataset of patients with multiple chronic conditions extracted from electronic health records of the Department of Veterans Affairs, we compare the performance of the proposed approach with some of the existing methods in the literature for both short-term (one-year ahead) and long-term (multiyear ahead) predictions. The proposed system provides a sparse intuitive representation of the complex functional relationships between multiple chronic conditions. It also provides the capability of analyzing multiple disease trajectories over time, given any combination of preexisting conditions.
Prognostic performance of two expert systems based on Bayesian belief networks
Decision Support Systems, 2000
Ž. A decision support system for the prognosis at 24 h of head-injured patients of the intensive care unit ICU , based on Ž. Bayesian belief networks, is constructed by model selection methods applied to a database 637 cases of seven clinical and laboratory variables. Its performance is compared to other systems, including a simpler belief network that assumes conditional independence among the findings, and a human expert. Results indicate that its performance is not significantly different than that of the neurosurgeon expert and better than the performance of the independence model. Thus, the prognostic judgment of non-neurosurgeon ICU clinicians can be aided by the use of this system.
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.