Understanding the practical utility of using the analytic potential of patient data in Identifying High-cost patients

Abstract

It is widely known that the minority of patients make up the majority of healthcare costs. Research being done aims at identifying these patients through predictive modeling. In the hopes that providing targeted resources to these patients can prevent inurnment of the high-cost. Lowing the bottom line to the hospital and helping the patient. Yet what degree of utility do these models provide? Most models are applied in a less than realistic setting or fail to state which predicted patients can even be impacted. In this study, I went through patient’s clinical notes to better understand how practical such predictive models are. First, I sought after literature to better understand what variables most predictive models use as a base. I compare these to what was available in the patient’s profile. Then revise what necessary for me to predict high cost given the patient’s clinical notes. With access to UWMC/Harborview and NW Hospital databases, I went through clinical notes to evaluate each patient’s possible predictability. These determinations were later verified by a physician for accuracy. This was further reflected on Northwest(NW) Hospital data, which is a relatively smaller hospital with a focus on inpatient/outpatient patients. Each patient was categorized on the nature of their high expenditure. This work's importance is in how to consider predictive models moving forward. Assuming modeling will always have the solution to predict high-cost patients is misguided. Instead, understanding the underlying dynamic of the patient's cause is a better target. The conclusions made in this study can help better guide models to be more cognizant in how they approach predicting high-cost patients.