A Bayesian network model for predicting cardiovascular risk. (April 2023)

• Record Type: Journal Article
• Authors: Ordovas, J.M.; Rios-Insua, D.; Santos-Lozano, A.; Lucia, A.; Torres, A.; Kosgodagan, A.; Camacho, J.M.
• Is Part Of: Computer methods and programs in biomedicine. Volume 231(2023)
• Publication Date: 2023-04
• Subjects: Bayesian network -- Cardiovascular diseases -- Healthcare -- Disease treatment -- Health policy; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2023.107405
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Analysis of cardiovascular risk factors through a Bayesian network. Accessible model for the diagnosis of CV medical conditions. Probabilistic tool to support research decisions. Support system to decide the most appropriate treatment. Free software with implemented model. Abstract: Background and Objective: Cardiovascular diseases are the leading death cause in Europe and entail large treatment costs. Cardiovascular risk prediction is crucial for the management and control of cardiovascular diseases. Based on a Bayesian network built from a large population database and expert judgment, this work studies interrelations between cardiovascular risk factors, emphasizing the predictive assessment of medical conditions, and providing a computational tool to explore and hypothesize such interrelations. Methods: We implement a Bayesian network model that considers modifiable and non-modifiable cardiovascular risk factors as well as related medical conditions. Both the structure and the probability tables in the underlying model are built using a large dataset collected from annual work health assessments as well as expert information, with uncertainty characterized through posterior distributions. Results: The implemented model allows for making inferences and predictions about cardiovascular risk factors. The model can be utilized as a decision- support tool to suggest diagnosis, treatment, policy, and research hypothesis. The work is complemented with a free software implementing the model for practitioners' use. Conclusions: Our implementation of the Bayesian network model facilitates answering public health, policy, diagnosis, and research questions concerning cardiovascular risk factors.