In 2023 and beyond, health plans’ very survival will become increasingly reliant upon unique insights driven by accurate member data. As healthcare transforms, payers will increasingly incentivize providers to share health record data for quality reporting and to collect clinical data to improve population health, care management, and risk adjustment.

Healthcare risk management uses clinical and administrative systems, processes, and reports to identify, monitor, assess, mitigate, and prevent risks. While healthcare organizations can proactively protect patient safety — risk management has become a far more daunting task. Now it must account for the growing influence of new healthcare technologies, increased cyberthreats, ever-changing regulatory requirements, and reimbursement protocols.

Today’s risk managers have a much tougher task as they must navigate an ever-changing healthcare landscape. Most healthcare organizations have an established and ongoing risk management plan in place to help them identify, manage, and mitigate risk. Yet, access to clinical data remains elusive.

Data science is critical for comprehensive healthcare planning

Healthcare technologies have the potential to become incredibly effective catalysts for lowering costs and expediting clinical and non-clinical actions, but it’s the payer’s responsibility to realize the full potential of these solutions.

Technology is not a silver bullet. Before it can work, payers must develop and then apply robust data models to positively — and routinely — impact member health. By integrating data science directly into a unified platform, health plans can get a global view of their members. This gives them valuable, readily identifiable sources of data they can quickly leverage to improve not just data models, but health outcomes, where they can anticipate and help prevent future health issues.

Good data science requires a great variety of data that can be speedily mined for rich insights. Payers and providers who have that data science resource can prioritize the next steps in long-term care planning.

To establish a more holistic, data science-centric view of its members — and predictive models that can chart better health outcomes for them — health plans must eliminate the insular data and personnel silos within their organizations.

Streamlining data collection processes is the way to improve them

The above challenges demonstrate why overcoming IT constraints and minimizing respondent and organizational resistance is so necessary to capture and interpret high-quality data. Integration of data systems can streamline data collection and simplify data reporting, so that individuals won’t need to self-identify race, ethnicity, and language during every health encounter. But until that integration happens, health plans can improve their data collection processes by enhancing legacy health IT systems, implementing staff training, and educating patients and communities about why it’s important to collect these data.

Today, the data that gives insight into a person’s health, and the care and quality of the healthcare received, is scattered across tens if not hundreds of systems, and some is not captured at all. While many health plans have begun sorting the relevant data from the junk, the systems, reporting activities and people using the data remain disconnected.

A recent survey found that most payers use abstracts from medical records, claims data and enrollment data. But leading organizations said they are starting to use EMR feeds, (rather than scanned records) to capture diagnoses for risk adjustment and identify quality improvement opportunities.

Streamlining and improving the efficiency of data collection and dissemination processes is possible — and necessary, since payers usually don’t coordinate. Moreover, the data from these programs may not be in regulatory compliance: the current category model from CMS explains about 11 percent of variation in Medicare spending.

Enterprise-wide systems, engagement programs can increase efficiencies

Health plans can move towards digital transformation by organizing more efficiently around their current systems. Hence, many health plans invest in enterprise-wide systems to better understand where the data is, overhauling current processes to optimize data flow and adopting new technologies to further enhance performance.

Since health plans are treading water in a vast ocean of frequently unconnected, disorganized data, their teams should consider pulling data from new sources. Towards that end, creating an enterprise view could shift the way teams access, process, and use data; teams should rework their processes so they can capture data that gives them a global member view.

For example, a risk adjuster who captures a new diabetic code for someone with a heart condition can immediately send the code to the care management team supporting that individual.

Health plans can also build programs to engage clinicians and provider organizations. By developing clinical data analytics that yield insights into treatment, their prescribing, referral, and coding partners can help health plans begin to understand and influence how clinicians practice and submit data to inform these programs. This data can then be used to create strong financial incentives and clinician engagement programs.

Health and financial data can give health plans a competitive advantage in managing patient care or financial outcomes — and a strategic advantage for managing compliance risk. As organizations retool data collection and use processes, they should also enhance the data collected for their compliance programs. Compliance teams can use much of the same underlying data being collected, aggregated, and analyzed for patient care or financial performance to better manage compliance risk. Accordingly, compliance leaders should be engaged early in the data transformation process to provide input into what and where relevant data may be available, and to help design processes, dashboards, and reports to best use the data to manage compliance risks.

The future is promising for better risk management

Moving forward, it’s possible, even likely, that newer and better ways to collect, integrate and interpret data will create a more responsive and interconnected healthcare ecosystem that results in healthier communities and more consistently effective risk management — and gives healthcare organizations that anticipate this future the competitive advantage to establish a leadership position in the industry. Three trends are worth noting here.

1. Healthcare will be sensor-driven, where multiple owners gather and store massive amounts of generated data and, when appropriate, make it available. The degree of interoperability involved in extracting the data from health plans, providers, and government regulators, as well as from digital giants, retailers, and consumers, will seamlessly integrate these disparate data sources and applied advanced analytics. That will produce real-time insights that improve the patient experience and drive the delivery of “always on” care.
2. While health plans can implement new data techniques to reduce submission errors in the short term, by 2040 there may be less need for risk adjustment. The remaining risk would account for accidents that would still need to be predicted, measured, and adjusted for. Models based on comprehensive and timely data that gives a complete picture for every patient might be even more accurate and dependable.
3. Today’s population health and care management programs, which largely manage people who are susceptible to greater need of health care, will probably evolve into disease prevention programs. That’s because many of these patients are difficult to find and track and they tend to experience only low to moderate improvements in outcomes. Instead, healthcare organizations could develop business models in the future that emphasize sustaining well-being through predictive technologies and comprehensive data on each patient.

Solving the data quality problem supports quality healthcare decision-making

Health plans are challenged to ensure the quality and integrity of encounter data. Generating and ensuring clean, accurate, and compliant encounters for CMS and HHS submissions is often a cumbersome process. It requires coordination among all the stakeholders, plus multi-disciplinary, highly technical expertise to identify, correct, and manage encounter fallouts and errors.

To ensure that its member risk burden is accurately represented, a health plan must have the right tools and processes for monitoring encounter data, isolating anomalies, and address any errors in a timely and efficient manner.

Breaking down risk management into its critical fundamentals can help payers focus their efforts most efficiently. By embracing big data best practices, they can ensure accurate, compliant, and positive risk adjustment payments, create strong provider engagement, and enhance the health and wellness of their members.

Achieving this goal, however, requires a solution to a core, fundamental problem: the need for, and lack of quality, actionable data at the point of service. This challenge threatens the progress of interoperability and data sharing, particularly when the data lives in different EMR systems.

While some of the biggest names in healthcare IT have tried to tackle the problem, it remains unsolved — not because the available technology isn’t capable, but rather because the data is fundamentally flawed where and when it’s ingested. Simply put, the data quality is questionable, and since data is the foundation for decision making, risk management decisions — and decisions impacting so many other healthcare system functions — may be flawed, too.

Verinovum’s Enterprise Data Curation platform uniquely solves the data quality problem between disparate systems. The key difference – and the reason it works – is that Verinovum starts curating data at the point of ingestion. The platform cleans and standardizes data in real time as EMR systems receive new information, allowing ongoing analysis of disease trends, treatment paradigms, and emerging symptom assessments. The Verinovum solution can be aligned with COVID-19, as well as other disease specific models including CHF, diabetes, and COPD. Learn more here.