Health care cost containment through big data analytics
A four-pronged approach to transform payment integrity
By Shaun Barry, Director, Global Security Intelligence Practice
Everyone’s worried about exploding health care costs – and no wonder. In many countries, health care costs are skyrocketing for companies, governments and citizens, making it increasingly difficult for people to access timely, quality care. The result, of course, is poorer health outcomes.
What’s driving the exploding cost of health care?
In most cases, cost containment in health care has been a struggle due to lack of program integrity, which encompasses:
- Prevention. Monitoring payment system operations, performing medical reviews and educating providers and beneficiaries.
- Detection. Implementing analytical tools, such as risk-based predictive modeling to detect improper payment trends.
- Recovery. Collaborating with program integrity partners (such as the US Department of Justice) to recover funds through restitution, fines, penalties, damages and program suspensions.
- Visibility and accountability. Visualizing data and developing performance measures to evaluate outcomes and accurately track, report and share program integrity information.
When you have weaknesses in one or more of these areas, it leads to unacceptably high levels of fraud, waste, abuse and corruption – and makes health care cost containment impossible to achieve. In the US, for example, many sources estimate that fraud, waste and abuse are involved in 3 percent of private sector payments and 10-15 percent of public sector payments. Waste, abuse and errors are estimated to affect 15-30 percent of total health care costs, as well as 20 percent of Medicare payments, according to CMS.
These trends are not exclusive to the US. The global average loss rate for health care is 6.19 percent. Based on the global health care expenditure for 2013 (US$7.35 trillion, GBP 4.83 trillion or EUR 5.65 trillion), that equates to $455 billion in losses.
And the damage caused by program integrity breaches goes beyond financial losses and spiraling health care costs. Breaches can also put payers at constant risk for noncompliance, financial losses (including fraud) and more. It can erode customer and investor confidence in the business – and in the case of government programs, result in taxpayer distrust and frustration at perceived rampant fraud and waste. And, finally, it makes it difficult for payers to proactively take the right steps to optimize health care costs and outcomes, or even determine how and what to change.
Combating and preventing identity fraud in healthcare
Identity theft cases are rising in the health care industry and they have only become more prevalent with COVID-19. Join us and review the emerging challenges in combating and preventing identity theft in health care and government programs. Explore the current government and health care fraud landscape, presenting analytical strategies for recognizing false identities and preventing ID fraud.
The nuts and bolts of effective health care cost containment
One thing is clear: If payers – both public and private – continue managing program integrity as usual, prices will continue to spiral out of control. But through the strategic use of advanced analytics and data management, payers can contain health care costs by proactively uncovering hidden fraud, waste, abuse and corruption before it’s too late. Advanced data management and analytics enable systematic, end-to-end program integrity for fraud prevention and elimination of wasteful, duplicate and unnecessary administrative processes and medical care.
Out with the old, manual way of working with data …
It’s generally acknowledged that approximately 80 percent of the work within health care payer organizations is spent on search and discovery efforts, such as identifying relevant information, searching multiple data sources, formatting data for a specific tool, processing, and applying analytical techniques within a tool. Just 20 percent is focused on usable analytics – for example, applying specific tradecraft and vetting information. And as noted earlier, even with these efforts, payers are failing to contain health care costs.
… and in with the new, analytics-driven approach
In contrast, strategic use of data management solutions – which aggregate and cleanse structured and unstructured data for a single version of the truth – and advanced analytics can reverse this trend. These solutions can automate the work of aggregating, preparing and integrating data, freeing investigators to spend 80 percent of their time on practical analysis to reveal, for example:
- Provision of unnecessary services or billing for services not rendered.
- The unbundling or upgrading of services.
- Fictitious providers and billing agents.
- False referrals and illegal kickbacks.
- Patterns of human error and operational inefficiency, which together are emerging as the No. 1 source of financial losses for payers.
Components of a comprehensive advanced analytics infrastructure
To achieve this, payers need a program integrity platform that combines support for core disciplines in a single, complete, enterprise platform for effective health care cost containment. As shown in the figure below, these disciplines include:
- Data management. This normalizes and incorporates multiple data sets to create a single source of truth. From this, you can create usable, integrated outputs (such as reports) or results with utmost confidence in the findings.
- Behavioral analytics. Use the most modern analytic techniques – such as link analysis and data visualization – to identify true fraud, risk and abuse early and maximize revenue lift.
- Claim analytics. Use advanced claim analytics at the line-item claim level to understand whether a claim is legitimate and if it should be paid before it’s too late. Users can answer questions such as: Is this claim coded correctly and properly submitted? Should it be paid? Should it be moved to an SIU for further handling?
- Clinical targeting. Help identify where and when waste, fraud and abuse might be happening by understanding the medical necessity of claims. This is particularly valuable when detecting waste and abuse – for example, when providers are overcharging or conducting unnecessary procedures to increase revenues. You can use clinical targeting to uncover short stay and readmit trends, conduct ER reviews, assess levels of care and identify unusually expensive claims.
Elements of a complete program integrity solution.
Furthermore, outcome-based analytics can compare costs across different service delivery settings (such as fee-for-service, managed care and carve-outs) by integrating all MCO data, forecasting budgets, analyzing by delivery setting or member, and more. This enables payers to drive outcomes in ways that influence policy, member health, provider effectiveness and cost-effectiveness. Users can also calculate future cost trending data to assist with budget projections and proactively take steps to contain health care costs.
Lastly, a comprehensive program integrity solution should use technology that supports an artificial intelligence approach. After large amounts of data are cleansed, aggregated and analyzed, an AI system can recognize resulting patterns so that new inputs begin to steer decision making based on emerging trends represented by both historical and new data.
What to look for in a platform
Armed with the right comprehensive, enterprise-level platform with end-to-end support for data management, behavioral analytics, claim analytics and clinical targeting, you can finally win the health care cost containment battle.
Recommended reading
- Article Intelligent policing: Data visualization helps crack down on crimeLearn how data visualization can give police real-time views of locations enriched with other data to help them make intelligent, fact-based decisions.
- Article Shut the front door on insurance application fraud!Fraudsters love the ease of plying their trade over digital channels. Smart insurance companies are using data from those channels (device fingerprint, IP address, geolocation, etc.) coupled with analytics and machine learning to detect insurance application fraud perpetrated by agents, customers and fraud rings.
- Article 4 strategies that will change your approach to fraud detectionAs fraudulent activity grows and fighting fraud becomes more costly, financial institutions are turning to anti-fraud technology to build better arsenals for fraud detection. Discover four ways to improve your organization's risk posture.
- Article Know your blind spots in tax fraud preventionTax agencies sometimes miss fraud that's happening right under their noses – despite robust external fraud prevention efforts. Find out where traditional tax fraud prevention and detection efforts fall short, and how analytics can change that.
Ready to subscribe to Insights now?
SAS® Viya™
Make analytics accessible to everyone and bridge the talent gap in your organization