Your prospective risk adjustment team that are reviewers, whether clinical staff or coders on Clinical Documentation Improvement (CDI) teams, plays a critical role in value-based care program success. But this important contribution requires a huge operational undertaking.

Ahead of scheduled patient visits, teams are tasked with reviewing large volumes of data spread across multiple health records to find relevant insights on clinical conditions for provider evaluation. During the visit, clinicians have to quickly make clinical decisions with the available information and properly document and code the patient encounter. After visits, reviewers need to quickly evaluate all the information captured during the patient encounter to ensure appropriate documentation and accurate codes have been captured for billing purposes. It’s a race against the clock to resolve any gaps or questions with providers before claims are submitted to the payer.

Manual, time-consuming prospective workflows can result in errors and missed opportunities to identify and proactively treat patient conditions, impacting reimbursement and care quality. Additionally, inefficient processes make it challenging to scale risk adjustment activities to support the entire patient population in value-based care programs. As the demand rises for at-risk payment structures, your reviewers need tools and workflows to grow with your program needs.

The great news is that artificial intelligence (AI) is evolving rapidly to support risk adjustment activities—and it can streamline your end-to-end prospective process. Using AI to surface insights from various data sources and intelligent workflows, teams can review patient charts faster, accurately surface conditions for providers to evaluate during visits, and identify documentation gaps faster to support value-based care initiatives at scale.

Here are eight ways AI-powered workflows can help your prospective risk adjustment team work smarter and faster during pre-visit, point-of-care, and concurrent reviews.

1. Prioritize the Chart Prep Queue with AI-Powered Insights
   • Problem: In a typical pre-visit workflow, reviewers are given a set of patient charts to review—without an easy way to prioritize them. They can start reviewing charts for patients with the soonest appointment dates, but knowing which charts to review first for a given patient is a guessing game.
   • Solution: With AI-powered workflows, charts are surfaced for review in priority order based on the appointment date, provider, and suspected and recaptured conditions within the documentation. If time is short, your team can start with the charts with the most flagged conditions for review to prioritize efforts.
2. Review Patient Charts Faster During Pre-Visit Planning
   • Problem: Pre-visit chart prep is a complex process involving manual reviews of structured and unstructured data and mentally-taxing toggling between different tabs within an EHR. This manual workflow can slow your reviewers down and introduce errors such as missed conditions or inaccurate suspects.
   • Solution: Instead of reading through individual charts in hopes of finding relevant insights, your team can review a longitudinal patient record. With AI-powered workflows, they’re guided directly to specific locations where HCC evidence is found within the patient’s record. Reviewers can quickly look at charts once without jumping between EHR screens or multiple systems with side-by-side chart review and annotation of potential HCCs and ICDs in one view, increasing accuracy and decreasing duplicate work.
3. Evaluate More Charts Ahead of Patient Visits
   • Problem: When appointment volume is high, teams are tasked with so many reviews that it can be tough to get through pre-visit prep for every patient who needs it. As value-based care programs become more ubiquitous, scaling pre-visit review efforts to support more patients will limit how the team can keep up with demand.
   • Solution: By streamlining the pre-visit chart prep process with AI, each reviewer can do more in less time. With highlighted clinical insights tied to specific HCCs or ICDs, reviewers can quickly assess charts for evidence of new and recaptured conditions. Additional embedded tools like ICD lookups and manual code entry can further speed up the chart prep process. This intelligent, targeted approach to pre-visit reviews allows teams to scale their efforts across patient populations and programs with less friction.
4. Streamline Handoffs Between Reviewers and Supervisors
   • Problem: The handoff between reviewers and supervisors can be slow and convoluted in a manual pre-visit chart prep process. When questions or issues arise, your team must coordinate with disconnected communication tools or live conversations and then translate decisions back into your chart prep workflow. This can cause delays in the process and introduce potential inaccuracies.
   • Solution: A centralized, AI-powered pre-visit workflow helps reviewers and supervisors collaborate more efficiently. Your supervisors can review the same set of AI-identified conditions and supporting evidence reviewers looked at so they know precisely what prompted initial decisions, and leveraging a side-by-side view makes comparing suspect conditions, reviewer annotations, and evidence within charts quick and easy. Your QA team can work through a prioritized, centralized queue to review the most pressing condition suspects before upcoming patient visits.
5. Make It Easy for Providers to Evaluate Recaptures and Suspected Conditions
   • Problem: Recaptured and suspected diagnoses are often delivered from the review team to providers in a standalone list, with limited information from claims, or in a confusing spot within the EHR. Clinicians are frustrated when they have to look outside their workflow and need more evidence to trust the insights.
   • Solution: An AI-powered process provides clinicians with a curated set of recaptured and suspected conditions with evidence that increases their confidence along with having within their desired workflow. As a result, they can assess diagnosis gaps quickly and capture appropriate codes at the point-of-care and supporting documentation all within the EHR. This ensures your team has fewer downstream issues to resolve during concurrent reviews.
6. Focus Concurrent Review Efforts on the Most Important Encounters
   • Problem: After completing patient visits, your team must review encounter data and resolve any documentation discrepancies with providers before the billing team can submit claims. When appointment and patient volumes are high, your review team can be flooded with charts to review, creating bottlenecks and increasing the risk of inaccuracies.
   • Solution: With AI-powered workflows, reviewers can prioritize recent patient encounters that are most likely to need additional review based on the date of service and potential documentation issues flagged by AI models. This ensures your team spends time on the highest value reviews and mitigates compliance risk if some encounters can’t be evaluated before the claims submission window closes.
7. Use AI to Surface Potential Documentation Gaps and Questions
   • Problem: Reviewers must read through encounter data manually after-patient encounters to uncover missing or inaccurate diagnoses and documentation issues. Reviewers could manage multiple spreadsheets and other manual inputs to manage the concurrent review process. This time-consuming, error-prone process is difficult to scale when the number of patients and appointments increases over time.
   • Solution: An AI-driven concurrent workflow empowers your reviewers to evaluate conditions and encounter notes as soon as an appointment is completed. Instead of reading through every piece of documentation looking for potential issues, teams review a targeted list of AI-predicted diagnoses that may be missing and potentially unsubstantiated diagnoses that may need additional documentation from the provider.
8. Close Post-Visit Communication Gaps with Automated Workflows
   • Problem: Closing potential diagnosis and documentation gaps within the short window between a patient encounter and claims submission can be stressful. Once your reviewers reach out to clinicians to obtain missing information, they often have to follow up multiple times to confirm the provider has taken action—or check the EHR repeatedly to see if anything has changed. Additionally, tracking which encounters are ready for billing and which ones are waiting for additional information can be challenging to follow without a centralized platform.
   • Solution: With AI-powered workflows, reviewers can close communication gaps and finalize encounters for claims submission more quickly. Instead of manually sending a note to providers, reviewers can query them directly in the EHR as part of their post-visit review workflow. With a centralized review platform, your team can automatically track encounter statuses and filter encounters to inform provider follow-ups.

Accelerate Your Prospective Risk Adjustment Program with AI
Prospective risk adjustment programs have never been more critical—and the right technology can significantly impact your team of reviewers’ productivity and accuracy. AI-powered intelligence and simplified workflows can help your team prep charts before patient visits more effectively, surface valuable insights to providers at the point of care, and confirm conditions and documentation faster during concurrent reviews. The result? Complete risk capture, accurate reimbursement, and improve clinical quality across value-based care programs.

Explore how Apixio’s AI-powered Prospective Risk Adjustment Suite can support your prospective risk adjustment program from pre-visit planning to point-of-care diagnosis capture and concurrent reviews.