About This Webinar
Millions of people rely on health plan provider directories to find their doctors. However, according to recent research published in JAMA by researchers at HiLabs in conjunction with the University of Colorado, more than 80% of doctors had directory inaccuracies in key data elements. One bizarre result of these inaccuracies in aggregate is the creation of ‘ghost networks.’ Ghost networks are doctors listed in provider directories but in reality are not accepting new patients or are unavailable for other reasons.
Ghost networks are very common and they make it hard for consumers to pick health plans. Consumers may be making their decision to choose a health plan based on the doctors available near them, but they would be misled by the presence of ghost physician entries. As Congress is urged to address ghost networks, health insurance providers must proactively solve this problem by using technology to address what is fundamentally a data quality problem.
Advanced machine learning algorithms and AI can be trained to automatically identify and prune ghost physician entries. And the results can be surprisingly good for health plans, physicians, and patients. HiLabs has worked with many health plans insurance providers using its AI algorithms in conjunction with a variety of internal and external data sources to solve this problem. One surprising result that has come out of this work is that improving provider directory accuracy actually increases network adequacy scores for health plans. We will describe in detail how you can achieve these results.
Attendees Will Learn About
- The definition and root causes of ghost networks
- Congressional proposals to address ghost networks
- Technology solutions to resolve ghost networks
- Strategies to increase network adequacy
