Chart Review
NLP-Assisted Abstraction for Year Round Prospective HEDIS®
Manual abstraction is inefficient, costly, and difficult to scale. As NCQA’s digital quality initiatives ramp up to include year-round review beyond the sample, you can use Chart Review to preserve and improve HEDIS® scores, Star ratings, and quality bonus points, achieving year-round prospective review without increasing staff.
Chart Review is an intelligent HEDIS® abstraction workflow tool that uses natural language processing to support every aspect of HEDIS® review.
First, Chart Review’s NLP strategically prioritizes an entire gap list, surfacing gaps with sufficient, HEDIS®-specific evidence to close. Next, at the individual gap level, Chart Review guides abstractors directly to HEDIS®-specific evidence in the medical record and provides closure guidance at the point of investigation. Abstractors mark the evidence they’ve found, complete a Measure Worksheet with a few clicks, and set the gap’s status to show that it’s been reviewed or confirmed.
Finally, Chart Review sends documentation of closed gaps and required codes to your HEDIS® engine and provides auditing support in the form of downloadable original PDFs, activity logs, and closure codes.
Where the Data Comes From
Chart Review uses Astrata’s Constellation Data Platform to extract NLP insights. Constellation ingests digital PDFs and text from a variety of sources (1) and consolidates them in a single platform for use with multiple services via flexible APIs (2). NLP insights derived from the data are added t0 your own Gap List data (3) and surface in Chart Review as an NLP-prioritized gap list (4).
Where the Data Goes
When an abstractor closes a gap in Chart Review (5) the system transmits a pseudoclaim file back to your HEDIS® engine (6), where it can be used like any other claims data for your reporting and integrations (7). Chart Review retains original PDF member documents, activity logs, and gap-closure details for audit support.
Key Benefits
Increased Efficiency
Chart Review uses NLP to prioritize gap lists and bring abstractors directly to relevant evidence in the medical record, dramatically increasing their efficiency.
Standardization
Standardization: Advanced NLP analytics hunt down missed opportunities for gap closure, helping professional abstractors and providers abstract to the top of what the HEDIS® spec allows.
Full Audit Support
Astrata partners with a national auditing firm to pre-review our technology.
Portability
Chart Review is highly configurable, works with all leading HEDIS® engines, and can be configured to meet your output requirements.
Complete Gaplist Generating Workflow Tool
Designed with and for Quality professionals, Chart Review can support many different year-round review management strategies, from top-down management to a more agile approach.
Reporting
Comprehensive reporting tools help Quality Managers monitor abstractor accuracy and efficiency, and give Quality Directors topsight into which measures to address in evolving a plan of attack during the measurement year.
NLP Tuning & Monitoring
NLP works best when it’s tuned to your environment. Astrata’s clinical informatics team trains the system on your data and monitors it proactively to ensure its accuracy (and alert you if abstractors are applying stricter standards than the spec allows). Within Chart Review, abstractors can submit one-click or detailed feedback on whether NLP surfaced the correct document to close a gap.
CMS Star, Medicaid, QRS, and Custom Measures
Astrata’s Engineers design NLP specifically for HEDIS® and other measures used in governmental programs. Not sure if we can support a measure you need? Ask us!
Strategic Topsight & Opportunity Reporting
The same algorithms Chart Review uses to point abstractors directly to Hits (records where the NLP has found evidence to close a gap) can consolidate all of your system’s data into an NLP Opportunity Report, showing you exactly how many hits are waiting to be closed, by measure and line of business. Using these insights, you can fully grasp the universe of your data, and understand exactly where to aim your abstraction, outreach, and other quality efforts.