A data-driven Bayesian belief network model for exploring patient experience drivers in healthcare sector

Patient experience is a key quality indicator driven by various patient- and provider-related factors in healthcare systems. While several studies provided different insights on patient experience factors, limited research investigates the interdependencies between provider-related factors and patient experience. This study aims to develop a data-driven Bayesian belief network (BBN) model that explores the role and relative importance of provider-related factors influencing patient experience. A BBN model was developed using structural learning algorithms such as tree augmented Naïve Bayes. We used hospital-level aggregated survey data from the British National Health Service to explore the impact of eight provider-related factors on overall patient experience. Moreover, sensitivity and scenario-based analyses were performed on the model. Our results showed that the most influential factors that lead to a high patient experience score are: (1) confidence and trust, (2) respect for patient-centered values, preferences, and expressed needs, and (3) emotional support. Further sensitivity and scenario analyses provided significant insights into the effect of different hypothetical interventions and how the patient experience is affected. The study findings can help healthcare managers utilize and allocate their resources more effectively to improve the overall patient experience in healthcare systems.