In the complex world of risk adjustment, health plans rely on suspect analytics to identify members with possibly undocumented conditions that could yield additional revenue. However, traditional suspecting approaches that rely solely on clinical rules may yield only the “low-hanging fruit” of hierarchical condition categories (HCCs). Rapid advancements in machine learning technology have produced a better approach to suspect analytics—one that gives health plans a more predictable revenue cycle and the potential for substantially higher return on investment.
I hope you can join me for our on-demand webinar titled, “Data patterns and predictive magic: how to improve suspecting and chart valuations.” I’ll reveal pre- and post-analytics that underscore the power of a clinically driven machine learning approach to suspecting. By the end of the webinar, you’ll understand how:
- A clinical approach to suspecting complements machine learning algorithms
- Revenue and ROI can increase using predictive analytics
- Clinical knowledge is critical in making these new models more effective
Don’t miss this opportunity to enhance your suspecting and chart valuation efforts.