Bayesian Networks in Healthcare: What is preventing their adoption?
July 20, 2020
Evangelia Kyrimi, Kudakwashe Dube, Norman Fenton, Ali Fahmi, Mariana Neves, David Marsh and Scott McLachlan(2020): Bayesian Networks in Healthcare: What is preventing their adoption? (Submitted 10 Jul 2020)From Kuda Dube’s research highlights
Abstract: Bayesian networks (BNs) are known to be versatile in their capability to support medical decision-making in a variety of healthcare contexts. However, despite having gained significant research attention in the literature, BN adoption in clinical practice remains an elusive problem. This is made worse by the absence, in the literature, of a comprehensive analysis of the benefits, barriers and facilitating factors (BBF) for implementing BN-based systems in healthcare. This paper seeks to address this gap. By using the ITPOSMO-BBF framework, we reviewed works describing BNs in healthcare and identified the challenges and advantages discussed by authors when proposing their BN-based systems. Several BBF factors related to data, resource, resistance, and performance were identified. Most of the discussed barriers and facilitating factors are related to information and technology, while the majority of benefits are about processes and objectives. We believe that the output of this review can enhance the dialogue among researchers by providing a deeper understanding for the neglected issue of BN adoption in practice and promoting efforts for implementing BN-based systems.
- HIKER Group Presents at IEEE GHTC 2020
- Bayesian Networks in Healthcare: What is preventing their adoption?
- A privacy-preserving Bayesian network model for personalised COVID19 risk assessment and contact tracing
- Dr Scott McLachlan on UK Government’s latest about-face on the NHS Contact Tracing App
- New journal article: Bayesian Networks in Healthcare: Distribution by Medical Condition