Written by Anastasiia Kelley, Data Analyst at careviso
Finding the Problem Areas of Machine-Readable Files
Recent U.S. healthcare regulations, such as the Hospital Price Transparency Rule, require that medical insurance companies and hospitals release their pricing information in machine-readable formats. These formats, which include JSON, XML, or CSV files, are structured to ensure that healthcare cost data and negotiated rates are openly accessible to the public, not tucked away in obscurity.
However, in looking through the available Machine-Readable Files (MRFs), we found widespread issues. We quickly learned that the data was often confusing, fragmented, or simply incorrect, posing significant challenges for those seeking to use this information effectively.
How We’re Solving Data Drawbacks
To solve these issues, we implemented a series of technological solutions. We built specialized parsers for each type of file, robust enough to manage and interpret the large amount of data released by insurers, as well as the various file formats
Our approach involved more than just building parsers. Beginning with a comprehensive analytical framework, we used our in-depth industry experience to pinpoint and work through the data’s shortcomings. We soon discovered that using a uniform strategy for each insurer’s files did not produce the accurate dataset we wanted. From this discovery, we quickly realized that each payer requires a unique approach to understand which, of the many variations, is the accurate price for a certain provider and item.
With that in mind, we built multiple scripts that automate the process of gathering and analyzing the unique framework for each payer and created a proprietary validation process to ensure the accuracy of the data we parsed. We then used the data we processed from the hospital files, which tends to be more consistent and less confusing, despite being less standardized across the different hospitals.
This process enables us to unify two independent data points to find recurring patterns, confirm data accuracy, and identify the most reliable pricing information for each provider from the payer files. The result of this detailed process is a vetted, reliable dataset- free from inaccuracies and redundancies. An additional advancement from our method is the ability to assign accuracy scores to each payer, which symbolizes the reliability of their data.
Our Commitment to Price Transparency
From working with large, complicated datasets, we recognized the importance of data timeliness. Since insurers are mandated to update their MRFs monthly, we re-evaluate the data regularly, applying the established protocols to spot and record any changes. This continuous refinement ensures we consistently deliver the most precise dataset possible from each payer’s MRF.
Our dedication to simplifying healthcare pricing has led to significant advancements in decoding complex machine-readable files. As we continue to refine and enhance our methods, careviso remains committed to clarifying healthcare cost information.
careviso is a healthcare technology company supporting everyone involved in diagnostic testing. We created a proprietary platform for payors, physicians, and laboratories that improves patient care through streamlined workflows. By automating the impossible we’re solving the most complex problems in the healthcare industry: prior authorizations and financial transparency.