Big Data in Health Care: Using Analytics to Identify and Manage High-Risk and High-Cost Patients
July 10, 2014
David Bates, Suchi Saria, Lucila Ohno-Machado, Anand Shah
As a result of greater adoption of electronic health records, health care organizations have increased opportunities to analyze and interpret large quantities of patient information, known as big data, to better manage high-risk and high-cost patients.
The July 2014 issue of the journal Health Affairs explores the promise of big data to improve health care. In one article, supported by CHCF, the authors examine six examples in which mining big data can improve care and reduce expenses in hospital settings:
Identifying high-cost patients can in turn determine which patients are most likely to benefit from interventions and which care plans can best improve care.
Using predictive algorithms to foresee potential readmissions can enable more precise interventions and care coordination after discharge.
Integrating triage algorithms into the clinical workflow can help manage staffing, patient transfers, and beds.
Some ICUs are using analytics to evaluate multiple data streams from patient monitors to predict whether a patient’s condition is likely to worsen.
By uncovering unique data patterns, such as prescription drug use and vital sign changes, other systems can help prevent renal failure, infections, and adverse drug events.
Data from multisite disease registries and clinical networks will help manage patients with chronic conditions that span more than one organ system.
While big data and analytics are powerful tools, the authors say more systematic evaluation is needed to move from potential to realization in many areas. And questions remain on how to regulate analytics and provide adequate patient privacy.
The complete article is available free of charge on the Health Affairs site through the link below.