Interested in improving your STARS/HEDIS and risk adjustment performance?
At RISE West: Learn how analytics can help you improve your chase list quality and drive better STARS/HEDIS performance.
Population health management leader Arcadia.io will be exhibiting at RISE West in Booth #8. We're offering one-on-one consultations with Debbie Conboy, a leading expert on risk adjustment, and an Arcadia team of subject matter experts on solving key challenges within the risk and quality space.
Drive better STARS/HEDIS performance with predictive analytics
STARS/HEDIS quality performance is a major focus for most health plans, but it can be challenging to improve quality gap identification, closure, and documentation across a provider network. One strategy is to combine clinically integrated data with predictive analytics to help providers find the patients most likely to engage and close a quality gap.
Innovative health plans around the country are helping their providers use analytics to better focus their resources. Traditional population segmentation relies on morbidity or utilization data, but members can also be scored and segmented based on their likelihood to engage, i.e., how impactable are they by the provider? These predictive impactability scores can help identify members most likely to close a gap, and can be used to feed automated outreach campaigns.
Improve your chase list for a better ROI on your risk adjustment program
Most health plans have a risk adjustment program in place. The key to program success is having a quality chase list – but most industry statistics estimate that only 20-30% of a given chase list is actionable. So how can you improve the quality of your chase list and stop wasting money on ineffective chart reviews?
Arcadia has EHR and claims data for 60 million lives in our clinical benchmark database, including pharmacy data. This expansive data set enables Arcadia data scientists to develop sophisticated approaches for leveraging integrated EHR data to find very granular indicators that a patient has a specific condition. For example, by using data science to identify relationships and patterns between conditions we can improve predictions about whether a patient has a given undocumented condition. By building these insights into our risk adjustment applications, we help health plans improve chase list quality and overall risk adjustment performance.