The ever-evolving Healthcare Effectiveness Data and Information Set (HEDIS) metrics are continuing to demand Medicare Advantage (MA) organization’s attention to improve patient care while reducing costs for the overall healthcare ecosystem.
Healthcare payers either earn great incentives or get penalized while submitting risk adjustment factor (RAF) scores, also known as, RAF scores to the Centers for Medicare & Medicaid (CMS)1 for Medicare patients.
Artificial intelligence (AI) is a modern adaption to automate medical chart review and audit workflow, allowing a centralized HCC coding workflow for improved accuracy and efficiency.
Advantages of AI solutions in Risk Adjustment for Healthcare
Currently, the buzzword on the Internet, AI, uses computer algorithms to understand patients’ chart history and make predictions allowing a retrospective approach to fill gaps in care.
AI also enables the healthcare payers to eliminate the conventional workflow and automates the repetitive, labor-intensive process of chart review and audit for risk score derivation.
Healthcare payers can also analyze a large amount of unstructured data with enhanced precision while identifying unreported HCC codes.
- Seamless direct electronic health record (EHR) retrieval
- Intelligent chart review workflow
- Real-time dashboard.
Advantages of AI in Risk Adjustment coding for Healthcare
MA organizations usually have to depend on providers for retrieving Medicare patients’ records to identify and validate accurate HCC diagnosis codes to the CMS for reimbursements.
Now, performing risk adjustment coding workflow through multiple sources can be time-taking, repetitive, and error-prone.
An AI–Powered risk adjustment solution can allow medical coders, and healthcare payers to focus on the high-risk member first, ensuring better population health care.
This technology also improves chart review productivity with quality, while reducing the amount of data you medical coders enter initially.
– Automate recapture of existing conditions, extracting and prioritizing of charts
– HCC auto-code suggestions based on prior captured conditions
– Analyses for all types of reports including unstructured patient health data
– Presenting data from machine learning (ML) formats to natural language
– Optical character recognition converting image files to text
– Recognize missing Hierarchical Condition Category (HCC) conditions
– Prompts suspect clinical conditions
– Customizes HCC coding workflow.
How AI solutions are improving chart review and chart audit workflow?
Retrospective chart review, also known as medical records review, is an approach designed in which pre-recorded patient data are used as a solution for one or more questions as defined by the National Library of Medicine.2
A retrospective chart review and audit solutions are allowing MA organizations and health care payers with:
– First-Level-Review (FLR) and optionally Second-Level-Review (SLR) to validate the medical coder’s findings
– Claim comparison to get the final HCC summary & RAF score calculation
– Identifying HCC diagnosis codes missing from the original claim
– Capturing severe HCC codes based on evidence
– Mitigating Risk Adjustment Data Validation (RADV) with the substantiated HCCs, unsubstantiated HCCs, and unreported HCCs
– Ensuring accurate HCC code and RAF scores submission to the CMS.
AI-based risk adjustment coding solution software is allowing MA organizations, and health care payers to strike the balance between accuracy and performance.
Transitioning from a conventional risk adjustment workflow to a modern, AI-Driven solution will empower the many benefits covered in this article.
The global natural language processing market is expected to increase rapidly in the coming years, resulting in over $43 billion in 2025.3