MVP Health Care has discovered three key applications for machine learning and advanced analytics, including condensing medical record data, hyper-targeting, and assessing risk adjustment in Medicare Advantage. The tools offer increased efficiency and better patient outcomes, but data ownership and other barriers may pose a challenge. As machine learning and advanced analytics continue to evolve, regulatory agencies and healthcare stakeholders may need to adjust their processes.
MVP Health Care (MVP) has been exploring the benefits of using machine learning and advanced analytics solutions in its processes. This technology is used to predict trends and create future-oriented outputs based on historical data, to streamline payer processes and provide better outcomes for patients.
Patrick Roohan, vice president of quality and clinical analytics at MVP, highlighted three primary uses for machine learning and advanced analytics that MVP has explored: condensing medical record data, hyper-targeting, and assessing risk adjustment in Medicare Advantage. In each of these areas, machine learning and advanced analytics offer an opportunity for increased efficiency and better patient outcomes.
Condensing medical record data is one of the most important uses of machine learning and advanced analytics in healthcare. The digitization of medical records was critical to making healthcare processes more efficient, but it did not reduce the amount of information contained in a medical record. An EHR can contain hundreds of pages of patient data, and machine learning can be used to target and cut down on a review of that record. By applying machine learning and advanced analytics to the medical records of Medicare beneficiaries who do not appear to have reportable diagnoses, MVP identified that eight to ten percent of these individuals had undiagnosed conditions. This information can then be used to hyper-target individuals for interventions and perform more accurate risk adjustments.
Hypertargeting is a technique that MVP uses to address care gaps. MVP builds personas using a technique called clustering and organizes members with shared characteristics into populations. Then, MVP uses the personas to create hyper-targeted interventions for members. For example, MVP can hyper-target women over 40 who need mammography by developing personas for this population. Machine learning can inform MVP of the woman’s population based on her medical history. Once MVP has identified a member’s persona, the health plan can focus on assessing her barriers to accessing care. Hypertargeting for health insurance can leverage both healthcare data and social determinants of health data to inform its output.
Medicare Advantage risk adjustment is one of the primary motivations behind MVP’s expansion into machine learning. To achieve five-star quality across all of its Medicare Advantage plans, MVP employed machine learning and advanced analytics and assessed its care gaps. Using this technique, MVP was able to evaluate its performance. Roohan indicated that CMS will have to account for machine learning in the future because the tool will impact Medicare Advantage risk adjustment and similar processes.
While machine learning and advanced analytics can improve payer processes, health plans may encounter barriers to using these tools. One of the major challenges is knowing who owns the data, particularly when leveraging a network for data access. If data ownership or another barrier gets in the way of data access, the repercussions for payer operations and patients’ quality of care are significant.
