Unleash the benefits of Quality Improvement excellence in healthcare

‍Health plan quality bonuses declined $1 billion in 2024 from a record $13 billion the previous year due to the sunsetting of pandemic era policies. Fragmented systems and manual processes further drain staff and financial resources. A tight HEDIS schedule leaves little bandwidth for health plan quality improvement teams to find solutions that improve efficiency, productivity and accuracy.

As value-based care (and particularly NCQA) moves to digital measures and patient-centered care, health plans need better strategies for data management and analysis to improve patient outcomes and simplify HEDIS compliance. Increasingly, AI solutions are helping value-based care plans overcome five of the most common barriers to quality improvement excellence in healthcare.  

5 Key Challenges in Healthcare Quality Improvement  

1. Data Ingestion and Document Routing

Challenge: Healthcare organizations struggle to efficiently process and digitize medical records from diverse sources and formats, including EMRs, bulk uploads, faxes, and SFTP transfers, as well as different file types. Manual sorting and routing of incoming medical documents is time-consuming and error-prone, leading to delays in processing and potential misclassification of critical clinical information.

Solution: Medical record retrieval solutions need to aggregate clinical data from multiple sources into a unified patient profile. AI-powered technology can digitize data, analyze it, and automatically abstract clinical evidence to the correct chase, shortening the time between retrieval and clinical review.  

2. Provider Outreach for Medical Records

Challenge: Providers get overwhelmed with requests for additional documentation, clarification on existing records, and time-consuming quality measure reporting processes. These interruptions increase the administrative burden on providers, reducing time for patient care. Provider abrasion also impacts medical record retrieval, slowing down chart collection when every day matters during HEDIS.  

Solution: Multi-channel medical record retrieval with automated provider outreach can streamline chart collection, as can centralized portals for providers or their third-party vendors to securely upload files. By simplifying chart retrieval for providers, clinicians can focus more on patient care, experience fewer interruptions, and benefit from a more efficient quality measure reporting system. Payers accelerate medical record collection and pivot more quickly to abstraction.

3. Extracting Value from Unstructured Data

Challenge: Quality Improvement abstractors struggle to efficiently extract critical medical evidence among unstructured clinical notes from a mountain of medical data. Manually navigating patient records to decode information across different chart sections creates a significant operational bottleneck.

Solution: Cutting-edge data processing solutions integrate natural language processing (NLP), clinical heuristics, and machine learning (ML) to decode unstructured medical data from multiple sources. AI-powered systems analyze medical documentation faster and more accurately than humans and can be trained to handle complex date formats and contextual nuances.

4. Clinical Data Abstraction

Challenge: Manual review of large volumes of medical records is time-consuming and prone to human error. Abstractors often struggle to efficiently find relevant clinical information among diverse and unstructured documents, which can delay data processing or lead to inaccurate reporting.

Solution: AI solutions built for value-based care can function as a virtual extension of the abstraction team. AI mines lengthy medical records and extracts relevant clinical evidence, collating insights into a user-friendly, enterprise-grade interface with built-in automated workflows and HEDIS engine integrations.  

5. Evolving Toward Year-Round Quality

Challenge: Many organizations need seasonal hires for HEDIS, and far fewer have the capacity for multiple abstraction teams to run a year-round quality strategy. Quality leaders typically only have the last quarter of the year to identify care gaps through clinical review and complete the outreach needed to get members seen so providers can close gaps in care. Appointment requests at the end of the year limit the time to deliver preventive services and necessary patient interventions. This can lead to missed opportunities and subpar HEDIS compliance.

Solution: A year-round quality workflow supported by an AI-powered platform can address these issues. This technology can continuously ingest and process medical records from various sources, automatically extracting and validating relevant clinical evidence for multiple measures any time of year. This enables real-time quality monitoring and improvement, transforming the end-of-year annual review process into a year-round proactive care strategy.

The Path Forward

Health plans will need innovative solutions to improve efficiency and productivity as value-based care grows. For more information about how AI is transforming quality improvement in value-based care, download our latest guide “5 Barriers to Excellence in Quality Improvement and How to Solve Them.”