As health plans transition from retrospective reviews to prospective gap closure initiatives, our AI-powered clinical workflow suite enables health plans and providers to ‘code and document it right the first time’ prior to claims submission.

• Attain net-new RAF capture by surfacing undiagnosed conditions that are mined from unstructured clinical data via EHR workflows
• Enhance care plan effectiveness and a clinician’s time in-treatment with more complete risk capture and patient documentation inclusive of all comorbidities
• NLP assisted post encounter view to ensure completeness and accuracy prior to claims submission

Provide visibility and oversight of the overall risk adjustment processes. Using AI-powered insights, we enable health plans to monitor progress and closely monitor retrieval, coding and submissions progress relative to their targets and SLAs

• Leverage granular operational insights into campaign progress, coder productivity, QA and encounter submissions / SLA performance
• Gain more visibility into strategy performance as it relates to gap closure, suspected RAF vs actual RAF to better meet/ exceed revenue targets
• Utilize insights for prospective initiatives like provider education and risk contracting performance management

Edifecs’ Encounter Management delivers a consolidated platform that ensures the accuracy, completeness, and timeliness of encounter data submissions across all managed care programs and lines of business. Health plans are able to manage all aspects of RAPS/EDPS submission and reconciliation, state-specific Medicaid encounters, dual-eligibles and the Marketplace (via the Edge Server) without the IT cost and complexity of operating multiple systems. Integrated exception management workflows enable the rapid correction and re-submission of rejected encounters. Best-in-class services and hosting options ensure program performance and compliance.

• Streamline Medicare Advantage RAPS and EDPS submissions and reconciliation to improve first-pass rate accuracy, visibility, and tracking
• Leverage state-specific managed Medicaid encounter modules, complete with companion guides and business rules, to address individual state requirements
• Operationalize configurations to support both dependent and non-dependent "duals" models across states as well as Edge Server submissions for both state and FFM models

Our market leading NLP-enabled coding and claims validation workflow application enables health plans to improve coding accuracy and efficiency of their retrospective, concurrent, and prospective review processes.

• Increase risk capture by 20-30% by accurately identifying HCCs that are commonly missed or coded improperly during manual reviews
• Improve coder productivity and efficiency by 2x-4x through an NLP-enabled coding workflow
• Highly configurable to support varying coding configurations and processes
• Minimize compliance and audit risk with two-way coding reviews

A comprehensive chart retrieval and management solution enabling health plans to not only reduce the cost and duplication of chart requests across the enterprise, but to also migrate from manual, resource intensive medical record retrieval to an automated, digital retrieval process:

• Improve chart retrieval efficiency through an AI-enabled chart retrieval workflow solution
• Reduce duplication and provider abrasion by unifying chart retrieval activities across risk adjustment, quality, care management and other departments
• Increase automation and reduce retrieval cost by migrating towards electronic medical retrieval
• Implement a unified retrieval and coding platform to gain more insight into your end-end risk adjustment campaign performance

A modular AI-enabled suspecting solution that analyzes clinical and claims data to uncover HCCs that otherwise get overlooked in a claims-only suspecting process Findings come from a combination of disparate data sources to identify unrecognized conditions, or undocumented instances of complexity, or comorbidity. In each case, a possible suspect is determined through the blending of criteria that includes available data points and assessment through rules-based and complex logic.

• Generate a more complete and accurate list of suspected conditions with both administrative and clinical data for provider validation
• Throttle suspect volume with confidence scoring, suppression, and filtering at both the global and local level, including care specialization condition targeting
• Confirm up to 20-25% more valid conditions to gain up to a +10% RAF value