Using predictive analytics and big data to optimize pharmaceutical outcomes

Abstract

Purpose: The steps involved, the resources needed, and the challenges associated with applying predictive analytics in healthcare are described, with a review of successful applications of predictive analytics in implementing population health management interventions that target medication-related patient outcomes.

Summary: In healthcare, the term big data typically refers to large quantities of electronic health record, administrative claims, and clinical trial data as well as data collected from smartphone applications, wearable devices, social media, and personal genomics services; predictive analytics refers to innovative methods of analysis developed to overcome challenges associated with big data, including a variety of statistical techniques ranging from predictive modeling to machine learning to data mining. Predictive analytics using big data have been applied successfully in several areas of medication management, such as in the identification of complex patients or those at highest risk for medication noncompliance or adverse effects. Because predictive analytics can be used in predicting different outcomes, they can provide pharmacists with a better understanding of the risks for specific medication-related problems that each patient faces. This information will enable pharmacists to deliver interventions tailored to patients' needs. In order to take full advantage of these benefits, however, clinicians will have to understand the basics of big data and predictive analytics.

Conclusion: Predictive analytics that leverage big data will become an indispensable tool for clinicians in mapping interventions and improving patient outcomes.

Keywords: big data; medication management; pharmaceutical outcomes; population health management; predictive analytics.