Like private insurers, public payers such as Medicaid and Medicare expect to see evidence that particular tests, therapies and treatments provide value. Value-based programs run by the Centers for Medicare and Medicaid Services (CMS), however, tend to measure value in a unique way. Many of these programs look for reduction or lack: evidence that particular events are not occurring. This makes it challenging to demonstrate value to public payers.
To do so, pharmaceutical and healthcare providers must often show data that isn’t there or that tracks events that did not happen. Here’s how the right approach, backed by the right digital tools, can bring that value to light.
CMS’s Focus on Reduction as a Measure of Value
Of the five original value-based programs launched by CMS, two focus directly on non-events:
- The Hospital Readmissions Reduction Program (HRRP), launched in 2012, focuses on “reduc[ing] avoidable readmissions,” or increasing the number of patients who do not return to the hospital after receiving care.
- The Hospital-Acquired Condition Reduction Program (HAC) “encourages hospitals to…reduce the number of conditions people experience from their time in a hospital.” In this way, it focuses on conditions (such as pressure sores and hospital-acquired infections) that do not occur.
Other CMS value-based programs, like the Hospital Value-Based Purchasing (VBP) program, also incorporate value measures that focus on non-events. These may include medical errors that do not occur during treatment or waste that does not occur due to the efficient use of resources.
Efforts to improve tracking of hospital readmissions and similar events increased with the release of the HRRP and other value-based programs. In a study published in BMC Research Notes, researchers Ronald J. Lagoe, Diane S. Nanno and Mary E. Luziani explored “quantitative tools such as definitions, risk estimation, and tracking of patients” incorporated into hospital software for the purpose of preemptively addressing potential readmissions.
Any data point chosen to demonstrate value has only limited value without context. When demonstrations of value focus on events that don’t happen, context is essential in order to highlight data points that would otherwise be invisible — such as the number of people who don’t experience adverse side effects from a medication.
“Value-based care means looking comprehensively at patient care to identify gaps and opportunities for improvement,” says Lee Sacks, executive vice president and chief medical officer at Advocate Health Care. Identifying those gaps requires context. Context demands data.
Tracking and Demonstrating Non-Events
CMS provides guidelines for tracking data points related to occurrences of targeted events, such as hospital readmissions. Yet these guidelines often track non-events by incorporating a large amount of peripheral data — the information surrounding a non-event that makes its absence apparent.
For instance, Medicare’s Plan All-Cause Readmission (PCR) measure examines “the number of acute inpatient stays during the measurement year that were followed by an unplanned acute readmission for any diagnosis within 30 days.” The surrounding data is the total number of acute inpatient stays. This data is necessary both to identify readmissions within the 30-day window and to contextualize those readmissions among patients who were not readmitted.
Identifying gaps, openings and non-events in healthcare events requires large quantities of data. Managing healthcare data remains one of the biggest challenges of the 21st century. Artificial intelligence and machine learning are offering new ways to manage this information within single comprehensive platforms — allowing healthcare researchers and providers to better demonstrate value by illuminating positive outcomes.
One example of such a project is a machine learning algorithm developed by researchers at the University of Washington at Tacoma. The algorithm uses a dataset derived from millions of cardiac care patients to assign each new patient a score. That score determines their likelihood of needing to be readmitted to the hospital after inpatient cardiac care.
The researchers found their data needs were staggering. “We had to understand what congestive heart failure means and how it is different from cardiac heart failure, for example. We were able to develop a set of qualitative and quantitative measures that are important for diagnosing and understanding the disease,” says Ankur Teredesai, director of the UW Tacoma Center for Data Science and one of the researchers on the project.
Technology’s Role in Demonstrating Non-Events
Conventional means of healthcare data management make this process difficult or impossible. Incorporating AI and machine learning into a comprehensive, interoperable platform, however, allows healthcare researchers and providers to track all the data necessary to report what doesn’t happen and thus to demonstrate value to public payers.
How do you track what doesn’t happen?
By tracking the data around key events, rare disease researchers and healthcare providers can illuminate instances in which key events did not happen. Taking a holistic approach to data through a comprehensive digital platform can help these healthcare industry participants make a strong case for value in the terms public payers seek.
Images by: mangostar/©123RF.com, fizkes/©123RF.com