Cortex Intelligent Claims Improve Accuracy
Healthcare payers and providers are challenged to manage claims, remittance, and payment data across the claims adjudication and revenue cycle ecosystem. Payers are looking to AI for improvements in a number of areas: increase adjudication accuracy, automation rates, and speed; move towards real-time auto-adjudication; and, better manage fraud, waste & abuse (payment integrity).
Providers are leveraging AI in areas like denials management, debt risk advisory, claims edits and predictions, and clinical insights from claims data. Both payers and providers want to lower claim processing friction in order to reduce service inquiries, denials, adjustments, etc.
Intelligent claims models
CognitiveScale has deployed AI solutions in areas like predicting denials, bad debt risks, and adjudication exceptions (adjustments). Currently, we are working with large payors and their adjudication system vendors on deploying models pre-adjudication and during the exceptions management process to deploy models that focus on identifying duplicates and scoring rejects in an attempt to automate corrections. We have also deployed Machine Learning (ML) solutions for document intake, interpretation, and insights in support of claims processes.
Claim Insights based on temporal, multidimensional profiles
CognitiveScale’s Profile of One is a 360-degree, temporal, longitudinal view of key entities (Members, Patients, Providers, Consumers, Agents, Claims). Profiles form a foundation for personalized insights and proactive interventions, so in the case of a claim profile, CognitiveScale can enable advanced analysis of claims against prior claim history (temporal analysis), all of a provider’s other claims, various models (edits and validations, fraud detection), or against rules engines (pricing algorithms, best practices for waste detection).
A low-code, assembly line of Cortex Intelligent Claims solutions
CognitiveScale’s Cortex software enables clients to manage an assembly line for the development, deployment, management and optimization of numerous AI-powered solutions. In order to implement and scale claims-related use cases, models need to leverage multiple data sources. Models themselves are likely focused on specific information about the claims process, for example a specific edit or claim check, so there is the need to combine models, algorithms, and rule sets – and there are likely many of these that need to be deployed. Consequently, our clients are interested in an AI platform and toolset that can enable a level of model combination and orchestration that surpasses what adjudication engines or transaction processing edit/validation services can do.
Payment Integrity Use Cases
Payment integrity is a main focus area for a number of compelling AI use cases. From the algorithms and models that can help detect fraud, waste and abuse (FWA) to data aggregation and analytics tools, AI is positioned to improve detection, investigation and recovery processes – thereby reducing the amount of claims paid in error and the costs of investigations. At CognitiveScale, we are building out multiple AI-enabled solutions in support of more robust payment integrity initiatives.
Bad Debt Risk Management Case Study