Healthcare is moving from Medicare Fee for Service (FFS) to quality payment models.
There has been a shift in our healthcare system, whereby providers are being rewarded for better care, not more care. This transition from fee-for-service to value-based care is not only changing how patients are cared for, but also how providers are measured on their performance.
At the heart of this new framework are the quality payment programs: MIPS (the Merit-Based Incentive Payment System) and APMs (Alternative Payment Models), which incentivize providers to take ownership for high-quality and cost-efficient care. Though there are distinct differences between the two models, both are aimed at measuring quality, gauging resource use, clinical practice improvement activities, and meaningful use of electronic medical records (EMRs). Additionally, both models rely on risk adjustment, a pervasive practice impacting all reimbursement paths in value-based care.
In a nutshell, risk adjustment is a method used by CMS (the Centers for Medicare & Medicaid Services) to adjust payments according to the health conditions of the covered population. By incorporating risk, CMS is able to make more accurate payments for care to enrollees with differences in expected costs. To determine each patient’s risk-adjusted payment, risk scores are calculated. Risk scores measure individual beneficiaries’ relative risk; they are comprised of an enrollee’s health status and demographic characteristics. A patient with a risk score of 1.0 incurs average Medicare costs. A patient with a risk score greater than 1.0 is likely to have higher costs. Conversely, a score of less than 1.0 means the patient will have costs below average.
HCC (Hierarchical Condition Category) coding is the key to success across value-based care populations because under-coding or under-documentation results in a lower risk score, and thus underpayment for the care that was provided. On the other hand, over-coding can result in heavy penalties when audits occur. Coding completely and accurately is both complicated and time-consuming,especially with the many types of disparate data available: medical claims, pharmacy claims, self-reported health risk assessments, medical record documentations, and more.
To succeed in value-based care, providers need to be able to parse through tens of thousands of lines of structured and unstructured data, identify diagnoses, enter a valid code, and ensure that the diagnosis is substantiated, all while maneuvering through abbreviations, shorthand, and considering whether the diagnosis is currently relevant to code for or not. In addition to the upside, providers must also consider the downside as well: namely, compliance. This is why so many have turned to natural language processing (NLP) technology, to not only help streamline the risk adjustment process, but also to mitigate compliance risks by addressing previously claimed codes without substantiating evidence.
Leveraging a mix of data acquisition, NLP, and risk analytics can significantly increase incremental revenue. For example, using our NLP-enabled workflow, Provider Group X was able to increase their performance by going from 5 percent in capture improvement and $3.7 million in additional code value in 2013 to 11 percent capture improvement and $13.7 million additional code value in 2016. Another example is of a provider-sponsored health plan that saw a fourfold increase in coder capacity, 23.6 percent PMPY, and $650,000 incremental revenue increase after adopting NLP.
Technology impacts all aspects of risk adjustment performance, from workflow to revenue, from analytics and reporting to compliance. An EHR data acquisition solution and clinically trained NLP engine can help provide point-of-care notification to close diagnosis gaps, identify suspect conditions, facilitate queries, aid physician engagement and education, and more, helping providers succeed in value-based care.