A Bayesian Study of the Dynamic Effect of Comorbidities on Hospital Outcomes of Care for Congestive Heart Failure Patients

Abstract

Comorbidities can have a cumulative effect on hospital outcomes of care, such as the length of stay (LOS), and hospital mortality. This study examines patients hospitalized with congestive heart failure (CHF), a life-threatening condition, which, when it coexists with a burdened disease profile, the risk for negative hospital outcomes increases. Since coexisting conditions co-interact, with a variable effect on outcomes, clinicians should be able to recognize these joint effects. In order to study CHF comorbidities, we used medical claims data from the Centers for Medicare and Medicaid Services (CMS). After extracting the most frequent cluster of CHF comorbidities, we: (i) Calculated, step-by-step, the conditional probabilities for each disease combination inside this cluster; (ii) estimated the cumulative effect of each comorbidity combination on the LOS and hospital mortality; and (iii) constructed (a) Bayesian, scenario-based graphs, and (b) Bayes-networks to visualize results. Results show that, for CHF patients, different comorbidity constructs have a variable effect on the LOS and hospital mortality. Therefore, dynamic comorbidity risk assessment methods should be implemented for informed clinical decision making in an ongoing effort for quality of care improvements.

Keywords

• comorbidities
• congestive heart failure
• health informatics
• Bayes networks
• clustering
• risk assessment
• clinical decision making