5 Big Data Strategies for Actionable Health Care Insights

Total health care spending in the U.S. is expected to reach $3.3 trillion by 2015. As the health care industry continues to move toward value-based care models, such as accountable-care organizations (ACOs) and patient-centered medical homes, data-driven technologies are playing an increasingly important role in helping bend that cost curve. According to McKinsey, Big Data analytics has the potential to save the U.S. an estimated $300 to $450 billion per year.

More specifically, data-driven technologies that help health care organizations address challenges related to population health and decision support, including hospital readmission rates, care coordination, disease prevention and patient adherence, are predicted to make up approximately 60 to 70 percent of cost savings. As risk-bearing entities begin to realize the value of data analytics tools, they are shifting from simply collecting data to really understanding the data and making it actionable at the point of care. Having immediate access to this critical patient information allows clinicians to deliver the right interventions to the right patients at the right time.

In this slideshow, Healthline shares five strategies for leveraging Big Data analytics to turn health data into actionable insights and improved outcomes.

Leveraging Big Data for Better Health Care

Click through for five strategies for leveraging Big Data analytics to turn health data into actionable insights and improved outcomes, as identified by Healthline.

Aggregate patient data from disparate sources

Health-care organizations often utilize numerous systems across multiple facilities, including EHRs, administrative systems and claims processing systems. It is critical to capture relevant data from all these disparate sources into a single, centralized location.

Unlock the value of unstructured data

More than 80 percent of today’s health data remains in unstructured formats, such as free-text physician notes, patient histories and hospital admission notes. Unstructured data, combined with structured data, will provide a more accurate, complete view of the patient’s health.

Look beyond clinical data

Patient data outside of clinical data could hold valuable insights into the patient, including psycho-social, socioeconomic and environmental factors. This might include factors such as the patient’s employment status, living situation, marital status and sleeping patterns.

Identify High Risk Patients

Predictive models and advanced rules help classify patients based on relevant patient data, enabling health-care organizations to more effectively identify gaps in care and high-risk patients who need intervention. An instance where this can have a large potential impact on improving outcomes is identifying patients who are at high risk for hospital readmissions.

Present Dashboard View of Data

Being able to view all the stratified patient data in a unified dashboard, classified by cohorts, allows clinicians to target scarce resources to deliver the right interventions to the right patients at the right time.