The Significance of Data and Data Analytics in Health Insurance OrganizationsSubmitted by admin on Sat, 2017-05-13 02:59
Research has shown that the global healthcare analytics market is growing at a Compound Annual Growth Rate (CAGR) of over 25% and is expected to reach 25 Billion Dollars by the year 2022. The astronomical and continuously rising costs of medication, coupled with the struggle to effectively provide quality care, is driving this focus towards analytics solutions. Thus, the erstwhile primarily descriptive decision-making is being replaced by the very much in demand predictive analytic models.
The Healthcare industry has been in a constant state of flux, particularly in recent times. The Affordable Health Care Act, Health Insurance Exchanges, ICD-10 adoption, spurt of Accountable Care Organizations (ACO) and the changes dictated by the Centers for Medicare and Medicaid Services (CMS) mean that Payers have to adopt new technology to augment their traditional operation models. Health Insurance organizations are under tremendous pressure to improve patient outcomes and reduce cost. Analyzing and leveraging the large amounts of data at their disposal is crucial to determine next steps in the right direction.
Many organizations have already moved in the right directions with Data Warehouse models and Data Analytics solutions. However, further adaptation is required, as they must utilize disparate data from new sources in combination with the pre-existing sources and types of data:
Insurance Claims Data: Traditionally, Insurance Claims data has been housed in a variety of stores, with a mix of legacy, client server and internet. IMS and DB2 databases are still prevalent in home grown systems, with flat files and VSAM files housing some information. Much of this data is translated and stored in traditional Relational structures like DB2, Oracle, SQL Server and EDI Data is predominantly stored in XML or parsed into databases. There may be additional complexity in the proprietary structures of Payer product systems like Trizetto’s FACETS, IKA Systems, NASCO and others.
Membership Data: Membership data is typically stored in either the main or other platforms like MetaVance, FACETS, or legacy. Feeds are routed in from the CMS, Federal Employee Programs (FEP), State Medicaid systems and other sources. Drug usage, data and trends are obtained from Pharmacy Vendors. Furthermore, it is necessary to integrate Medco and MedImpact data for studies.
Provider Data: Provider data is traditionally housed separately. It is imperative to be able to fully understand this data in order to utilize it for strategic analytics. Network management data, provider agreements, fee schedules, credentials, contract information for reimbursement models and the demographics of the service population must be obtained as they will play a key role in assessing outcomes.
Benefits and Medical Records: Benefits information is typically complex and difficult to decipher, however, when analyzed, can provide valuable insights into a number of areas for the Payer and Provider. Electronic Health Records (EHR) and Electronic Medical Records (EMR) data is also not structured because they are sourced from a variety of vendors and system formats. In these situations, consolidation and standardization of data is vital.
Customer and Case Data: Among other data that needs to be captured and analyzed are Customer Service calls, Case Management recordings, and IVR system data. Call center data can provide insight that can be further used to determine current trends and to predict upcoming trends. In spite of widespread digitalization, there are still a lot of paper records wherein OCR systems data and digitized images need to be utilized.
Internet Data: Finally, an invaluable source of medical data is sourced from new age internet. Patient trends, reviews and healthcare websites need to be scoured, in addition to utilizing ratings, quality of services, patient experiences, and consumer reports on a variety of healthcare services and organizations. There is a multitude of Internet data available at government and independent consumer websites, all of which is important to include in comprehensive analytics.
Whether real time or batch mode, all of the previously discussed types of data must be gathered, scrubbed and organized for analysis. The inherent importance of data lies in its ability to drive decision-making through strategically executed analytics.
There are several benefits to descriptive and predictive analytics. In the case of Health Insurance companies, payer analytics and consumer analytics must both be considered to provide full-cycle insight towards the following objectives:
Cost Reduction: Payers can derive information that will help drive down their overhead, improve first pass rates for claims processing and increase operational efficiency. Additionally, analytics would help with implementing the appropriate physician incentives, network discounts, optimal fee schedules and accurate pricing models. Finally, through data, they can target the high cost demographic areas and physician groups and focus on improving health to drive down costs.
Improvement of Quality of Care: Identifying patient trends allows for improving the quality of care to consumers, while simultaneously controlling costs to provide more care for less money. Predictive logarithms can be utilized to direct decision-making, enabling savings in time and efficiencies.
Identification and Elimination of Fraud / Revenue Cycle Management: The analysis of all the aforementioned data can help to identify and reduce billing errors, as well as erroneous and duplicate claims. Anomalies in claims submission vs. patient diagnoses and inaccuracies in drug prescriptions can be detected, and claims over-payments can be identified. Potential problems and errors can be assessed to proactively troubleshoot.
Increased Consumer Engagement: Consumer analytics can provide direction to target marketing dollars in the right areas. The outcomes of consumer retention and increased closure rate of New Member acquisition can be anticipated using predictive analytics strategies. Demographic and regions analytics will enable targeted product services, and allow for focus on better care giving for severe cases. Utilizing predictive modeling in rating and underwriting to derive optimal pricing for consumers will also enhance the ability to engage patients before acute conditions develop and costs spiral out of control.
We have discussed but a few of the broader benefits of using Analytics in the healthcare industry. With the large datasets from the growth of the web, medical records and biological advances, machine learning can be utilized to develop algorithms that can focus on numerous minute problems and provide solutions to them. It is essential to utilize the vast amount and types data obtained through the technological advances over several years to now benefit human care. The opportunities are infinite, and the effective use of this technology can keep expanding the boundaries of our efforts.