As the healthcare industry transitions from fee-for-service to fee-for-value, and to team-based care models that require a high degree of care coordination (such as PCMH), a more holistic, 360 degree view of the patient is needed. Over time, this patient view will be built not only from traditional data types such as claims data and healthcare data (e.g. from the EHR), but also non-traditional data types such as patient or member sentiment data from social networks. So what new approaches are needed to respond to this changing data landscape?
Organizations need to be able to apply analytics to Big Data; data from varied repositories that exist structured, semi-structured and unstructured form. Solutions that enable this need to be high performance, horizontally scalable, and balanced across compute, network and storage domains (e.g. to mitigate impact of I/O bottlenecks). High-performance analytics software, with capabilities such as natural language processing, machine learning, and rich visualization also enable these Big Data solutions.
The paper also describes 5 steps for getting started with Big Data:
1. Work with business units to articulate opportunities
2. Get up to speed on technology
3. Develop use cases
4. Identify gaps between current and future state capabilities
5. Develop a test environment
Payment reform and care models that foster a patient-centric approach have the potential to transform healthcare. Analytics solutions that break down traditional data silos to develop a complete view of the patient, enable effective outreach programs, and promote collaboration across the continuum of care will be the technical foundation of this transformation.
Are any of you deploying Big Data or advanced analytics solutions in your organizations? Please feel free to share your observations and experiences below. You can follow me on Twitter @CGoughPDX.