ABSTRACT
Approximately 23% of patients discharged from primary healthcare facilities are readmitted within 30 days at an annual cost of roughly $42 billion. To remedy this problem, healthcare providers are attempting to deploy readmission risk estimation tools, but how they might be used in the traditional, human-expert-centered decision process is not well understood. One such tool estimates readmission risk based on 50 patient-specific factors. This paper reports on a study performed in collaboration with Order of St. Francis Healthcare to determine how healthcare workers' own risk estimates are influenced by the tool, specifically testing the hypothesis that they will first anchor towards tool results while making adjustments based on their expertise, and then make further adjustments when additional human expert opinions are presented. Task analysis was performed, fictional patient scenarios were developed, and a survey of 56 subjects in two stratified groups of case managers was conducted. Data from the control and experiment groups were analyzed using ANOVA/GLM and t-tests. Results indicate that the healthcare workers' risk estimates were influenced by the anchor provided by the tool, then adjusted based on their expertise. The workers further adjusted their estimates in response to new expert human inputs. Thus, a reliance on both the predictive model and human expertise was observed.
