CitiusTech Blog



    Ramanan Seshadri on Jul 01, 2015

    With the evolving Affordable Care Act reforms and widespread digitization of healthcare data, payers are likely to make significant investments in analytics and business intelligence.

    Quality measurement is becoming more complex
    Reporting of quality measures continues to generate interest, and health plans have to evolve their systems to manage changing measure sets and introduce new measures from various federal and commercial institutions (National Committee for Quality Assurance and Centers for Medicare & Medicaid Services). NCQA, for example, has proposed eight new measures, edits to three existing measures, and changes to three guidelines, for Healthcare Effectiveness Data and Information Set (HEDIS) 2016.

    Likewise, the 2016 publication from CMS for Medicare Advantage plans to stop bonus payments to plans having a STAR rating that is less than four, making it even more necessary for health plans to achieve a higher STAR rating next year.

    To effectively measure, report and improve quality scores, payers need to leverage enterprise analytics that help them unify and process clinical and financial data from multiple sources. These tools will help analyze provider performance, benchmark quality scores against peers and identify areas of improvement. In addition, payers should be able to perform population stratification, risk profiling, assess physician performance and report gaps-in-care.

    FWA (fraud, waste and abuse) is gaining prominence
    Claims fraud is not new to the payer industry. Every year, fraudulent claims cost billions of dollars to payers, with issues ranging from ineligible payments to inappropriate treatment claims. In its 2015 Outlook on Healthcare Fraud, the Bureau of National Affairs expects an increase in fraud investigations around false claims, insurance exchanges, healthcare executive involvement, data breaches and cyber security.

    Claims fraud has been difficult to control over the years, partly because access to longitudinal patient records was limited to providers. For example, there may be cases where patients were billed for services not provided or where providers were administering tests and treatments that are not medically required. With access to claims data only, payers have no way to identify such cases of fraud, unless they can map claims with actual patient records.

    In cases where data may have been available to payer organizations or investigators, existing analytics technology and processes are generally not equipped to deal with the sheer volume of patient data that had to be processed.

    However, the increased focus on healthcare interoperability, and recent innovations in technology like big data and cloud computing, now allow health plans and investigators address these challenges to a great extent—to identify abnormal medical event sequences, track duplicate claims, profile claimants with higher probability of FWA and analyze unstructured data.

    Key technology challenges
    With disintegrated, legacy technology environments, organizations face multiple hurdles. For one, advanced payer analytics solutions will need to ingest data from various third-party entities such as physicians, hospitals, labs and other ancillary sources in order to be effective. Current payer IT setups is hardly geared to aggregate, manage and analyze clinical data from such sources.

    There is also the challenge of adapting to changing regulations, especially in areas like HEDIS compliance. Organizations would need analytics and reporting tools that can continuously adapt to changing measure sets, while providing performance comparisons and benchmarks against these configurable goals.

    In addition, technologies like big data and predictive analytics can be effectively leveraged only when payers are able to build a tightly integrated portfolio of healthcare tools and accelerators to manage huge volumes of large structured and unstructured healthcare data sets. Accelerators should be configurable to ingest data from a variety of source systems such electronic health records (EHR), picture archiving communication systems (PACS), practice management software (PMS), biometric devices, mobile apps, social media, etc. using industry standard transport mechanisms (e.g. REST, MLLP, XDS, DICOM).

    Of course, in the new information environment that includes mobile and cloud technology, with greater exposure to external data and systems, organizations need to increase their focus on data security and encryption, data privacy, user and access management, interoperability (Health Level Seven International and Fast Healthcare Interoperability Resource) and clinical terminology support.

  • CitiusTech Payer Team

Post a Comment

Your email address will not be published. Required fields are marked*

  • Name *
  • Email *
  • Comment *
  • Enter Verification Code *

  • Captcha
    can't read? refresh