Developed a framework to predict who is likely to make an avoidable ER visit using machine learning and text mining techniques, to identify up to $10M in annual cost reduction
Members may be visiting an ER unnecessarily for convenience, desire for a more effective PCP, from insufficient co-pay funds, or an unmanaged condition. Using clinical rules, we first identified lowintensity conditions where an ER visit could have been avoided and offered more than 40 hypotheses for factors which could be predictive of avoidable ER visits.
To test these hypotheses, we identified different structured and unstructured data sources such as call center notes,
Members with past ER visits are 8 times more likely to visit ER unnecessarily
Members visiting multiple PCP are twice as likely to make an avoidable ER visit
Each avoided ER visit, could reduce cost by $1,500 leading to $10M in potential cost saving
Optimized ER utilization can substantially improve member health outcomes
Ensemble framework of text mining and machine learning methods to improve accuracy in rare event scenarios