Posts Tagged ‘lab data’

Guest Post: Lab Data is the Missing Link in Healthcare Risk Adjustment

June 19th, 2018 by Jason Bhan, MD

Data informing risk adjustment programs is critical under value-based healthcare reimbursement models.

For health plans, value-based care means a continuous need to innovate and improve their risk adjustment, clinical quality, and care management programs. Unless payers identify and receive the correct amount of reimbursement, it is difficult for them to invest appropriately into member care programs for better outcomes while remaining financially successful.

The data informing risk adjustment programs are critical, as they build the foundation for accurate member risk stratification. In that respect, those data sources are directly related to the correct amount of reimbursement payers receive and can invest in proactive care management. In other words, high-quality clinical data delivered quickly enough for a plan to get a member into a care management program early enough is important to the health of the member and the business. The approach leads to improved clinical outcomes and reduced costs in emergency room visits, hospitalizations and chronic condition management.

Lab Data: An Untapped Resource

To achieve such clinical granularity, at scale, plans can turn to diagnostics—or lab—data. Lab data drives approximately 70 percent of medical decisions and, unlike claims data, is available in near real-time. It also provides an unrivaled level of specificity for clinical conditions. When lab data is integrated into plans’ claims- and chart-based programs, it enables earlier, more comprehensive and accurate clinical insights to benefit care management of both existing and new members. Utilizing the same information that clinicians use to make decisions, within the same timeframe, provides a powerful and unique opportunity to intervene and impact a patient’s health.

What Can Lab Data Do for You?

Expanding and improving their clinical data supply with diagnostics data can help health plans to:

  • Provide historical insights on members where claims are unavailable to improve risk adjustment. For new enrollees, this enables the health plan to get new members into the appropriate care/disease management programs from day one.
  • Serve as an early detection system for care management of all enrollees. Plans can identify patients in need of additional or alternative therapy from lab data earlier than from any other data source. For existing members, the detailed results uncover needs that may have been overlooked based on a claims analysis alone.
  • Identify high-risk members for case management and provider interventions from lab data. Optimized risk adjustment aligns reimbursements to health status, enabling the plan to more heavily invest in member care programs.

Applying AI Solutions

When it comes to gaining actionable insights from diagnostics data, plans can benefit from partnering with healthcare artificial intelligence (AI) specialists in the field. Healthcare AI organizations use techniques such as machine learning and natural language processing—coupled with massive computational power—on big data sets, to make sense out of non-standard, complex, and heterogeneous data.

Healthcare AI, when applied to diagnostics clinical lab data, improves risk stratification by identifying diagnoses earlier in the year versus waiting for the claim or searching charts. Rich in clinical details, it presents a more complete picture of the member’s health. Better risk stratification leads to better care management programs; and successful programs have been shown to reduce costs by targeting those most likely to benefit and keeping intervention costs low.

Dr. Jason Bhan

About the Author: Jason Bhan, MD, is co-founder and Chief Medical Officer at Prognos, an innovator in applying AI to clinical lab diagnostics. More than half of the Prognos team is made of engineers, data scientists, and clinicians. Prognos aims to increase the usefulness of disparate healthcare data to better inform clinical decisions and ultimately improve patient outcomes.