Big data means different things for different industries. The definition also differs within an organization, across departments and management layers within IT and business. Within IBM, big data spans four dimensions: volume, velocity, variety and veracity. At The Big Data Institute (TBDI), big data is a “term applied to voluminous data objects that are variety in nature – structured, unstructured or a semi-structured, including sources internal or external to an organization, and generated at a high degree of velocity with an uncertainty pattern, that does not fit neatly into traditional, structured, relational data stores and requires strong sophisticated information ecosystem with high performance computing platform and analytical capabilities to capture, process, transform, discover and derive business insights and value within a reasonable elapsed time.”
In my previous post, “Using Big Data Analytics in Healthcare,” I had covered the use cases for healthcare providers. Now let us cover the typical use cases for healthcare payers.
Clinical Data analysis for improved predictable outcomes
Payer health plans and insurance companies can significantly reduce the cost of care by reducing readmission, improving outcomes and proactively monitoring patients. There is a huge amount of existing clinical data that resides within an organization and myriads of unstructured data coming at a rapid pace. Big data technology is the right platform to process these complex events and data to provide clinical insights to payer organization. Areas that can be immediately addressed by big data solutions include:
- Longitudinal analysis of care across patients and diagnoses; time sequencing
- Cluster analysis around influencers on treatment
- Analyze clinical notes (multi-structured data); no longer limited by dimensional sentiment of a relational database
- Analyze click stream data and clinical outcomes; look for patterns, trends to evaluate quality of care
- Clinical outcomes can be integrated with financial information to understand performance
Claims Fraud Detection
Although no precise dollar amount can be determined, some authorities contend that insurance fraud constitutes a $100-billion-a-year problem. The United States Government Accountability Office (U.S. GAO) estimates that $1 out of every $7 spent on Medicare is lost to fraud and abuse. Examples of fraud and abuse are:
- Billing for services, procedures, and/or supplies that were not provided
- Misrepresentation of what was provided; when it was provided; the condition or diagnosis; the charges involved; and/or the identity of the provider recipient
- Providing unnecessary services or ordering unnecessary tests
- Billing separately for procedures that normally are covered by a single fee
- Charging more than once for the same service
- Upcoding: charging for a more complex service than was performed; this usually involves billing for longer or more complex office visits
- Miscoding: using a code number that does not apply to the procedure
- Kickbacks: receiving payment or other benefit for making a referral
With Health Information Exchanges playing a pivotal role in real-time information sharing, payer organizations will have the power of information to proactively detect fraud using pattern analysis, graph analysis of cohort networks and social media insights.
Like any industry, payer organizations such as health insurance companies are battling to win member business. Companies are monitoring members, prospects behavior on their websites and social media.
Payer Sentiment Analysis
Similar to provider sentiment analysis, members are sharing their experience about insurance benefits, customer service experience through social channels – Facebook, Twitter and other social media. These experiences through comments, tweets, blogs and surveys can be mined for gaining rich insights to improve quality of services.
Call Center Analysis
Payer organizations are capturing information from call centers using call recording. These call records provide valuable information on:
- staffing model – by demographic preferences, hours of services
- member feedback using voice pattern and recognition
- member experience using metrics – average speed to answer, abandonment rate, dropped calls, unable to reach member
While this is the tip of the iceberg for the healthcare payer industry use cases for big data, there are lots of unique opportunities specific to your line of business, organization and department. Most healthcare organizations have begun their journey along a data analysis continuum. Assessing and prioritizing the initiatives for big data based on value is key to success and will have significant impact on your organization in years to come.
IBM has a team of experienced consultants and leading products and solutions that can help cross-organization teams assess data sources, develop a roadmap and strategy, and implement a flexible and scalable big data platform with clinical and advanced analytics capabilities.
You can start small, but remember to Think Big.