December 16, 2019 (Nashville, TN) – Advent Health Partners, Inc. has unveiled an additional module for the CAVO® medical record review technology platform that intakes itemized bills (IBs) and auto-converts them into sortable and filterable data. Instead of sifting through information within PDFs, reviewers easily find information, make accept/reject decisions by line, and utilize real-time, auto-summed totals for adjustments and charges.
Health plans – both national and regional – are successfully achieving productivity gains almost immediately following end-user training. Further, by finding decision data more quickly and not transcribing adjustment lines, user organizations are substantially increasing review volumes.
“Advent’s mission is to continuously improve efficiencies within the medical record review process, always focusing on appropriate reimbursement,” stated chief executive officer Mark Thienel. “The foundation of our unique ability to solve review challenges for both health plans and providers is our team’s blend of clinical subject matter experts with technology engineers and data scientists. This combination enables development prioritization of the functionality that most increases review productivity for the most common use cases – while simultaneously planning for future machine learning and NLP initiatives.”
Additionally, Advent continues to enhance the CAVO® platform’s core functionality, including the latest “word expansion” feature. With capabilities based on industry-standard vocabularies, reviewers can build more complex searches with only a few clicks of related clinical terms and drug names, resulting in more comprehensive searches with less time and query logic. Plus, non-clinicians can easily expand searches with more data points impacting review decisions.
With the rollout of the IB Reviews module and word expansion feature, CAVO® continues to transform the medical record review process by increasing productivity while also laying the groundwork for machine learning and NLP initiatives for predictive modeling and automation.