We are proud to announce Eliza® Member Engagement is now part of Cotiviti!
Learn More
Effectively identify members with suspected but potentially undocumented conditions
Starting your risk adjustment program with the best possible suspect list is key to optimizing risk-adjustable revenues. However, finding the right subset of members to pursue for risk-adjustable but undocumented conditions can be a challenge.
Cotiviti's Suspect Analytics solution helps identify members with potentially undocumented conditions appropriate for retrospective targeting. Our advanced analytical models leverage machine learning to provide our clients with a nuanced examination of their data, predicting which members have the highest probability of missing or incomplete conditions. We identify tens of thousands of pattern associations with a level of variety, granularity, and detail that would be virtually impossible to derive using more traditional clinical methods.
Leverage the latest developments in machine learning and advanced algorithms to effectively create your chase list
Identify charts with higher potential value
Reduce the administrative time and resources required to manage and analyze data
We complete Suspect Analytics for all members using multiple sources of data to identify gaps in documentation and care. However, we only recommend opportunities with value, along with the best options to capture those opportunities. Our solution is powered by advanced analytics and machine learning, using a well-balanced mix of clinical rules and artificial intelligence-based algorithms that yields approximately 30 percent more potential revenue per chart than traditional approaches. We aggregate, quickly assess, and integrate large volumes of data to create suspect recommendations that are tailored in partnership with you.
We mine data from prior risk adjustment history, diagnoses from past medical and drug claims, laboratory results, durable medical equipment usage, and medical procedures for evidence of missing conditions. By interpreting complex patterns across multiple data sources, we identify higher value conditions and help our clients optimize risk-adjustment revenue. Based on the potential clinical and financial impact, we identify and rank members with the highest probability of having missing or incomplete diagnosis codes.
Our approach considers different levels of investment for each member based on a proprietary value scoring model, providing a recommended path to reducing coding and care gaps.
With more than 20 years of experience in risk adjustment, Cotiviti understands the complexity of running a successful risk adjustment program and the importance of a suspecting methodology that will yield the best revenue result.
Cotiviti uses machine learning in our Suspect Analytics algorithms to ensure the most robust opportunity identification on behalf of our clients. Powered by business rules and Cotiviti’s deep analytics, our solution leads the industry in identifying and stratifying the best opportunities to optimize accuracy, compliance, and appropriate reimbursement for clients.
Continuously evolving to meet the requirements of health plans, we are a risk adjustment partner you can trust.
Retrospective
Medical records identified for coding with Suspect Analytics yielded an average 1.11 HCCs per chart, with a 17 percent incremental realization rate.
Prospective
Members identified for In-Home Assessments with Suspect Analytics yielded an average 1.26 HCCs per assessment, with a 39 percent incremental realization rate.
Medical records identified for coding with Suspect Analytics yielded an average 1.11 HCCs per chart, with a 17 percent incremental realization rate.
Members identified for In-Home Assessments with Suspect Analytics yielded an average 1.26 HCCs per assessment, with a 39 percent incremental realization rate.
Suspect Analytics is part of Cotiviti’s Risk Adjustment solution suite.
