Cedar Gate Debuts New Machine Learning Model

In the most recent release, version 12.2, of the Healthcare Benefits Analytics and Value-Based Care Analytics applications, Cedar Gate launched a new cholesterol screening compliance prediction machine learning model. According to the Centers for Disease Control and Prevention (CDC), nearly 94 million U.S. adults 20 or older have total cholesterol levels higher than 200 mg/dL. High cholesterol increases an individual’s risk of heart disease and stroke which are two leading causes of death in the U.S. Early detection as part of an annual screening can play an important role in reducing future cardiovascular risk.

Cedar Gate’s new machine learning model analyzes medical claims data and predicts the likelihood of members receiving their cholesterol screening within the next 12 months. The model identifies members between the ages of 19 and 39 who are less likely to obtain their annual cholesterol screening in the next year which enables prioritization of focused outreach initiatives to members who are surfaced by the machine learning model.

Studies have shown that high cholesterol can have long-term effects on heart health and because there are typically no obvious symptoms of high cholesterol levels, it is important for members to obtain their annual screening and know their numbers. Through direct outreach to members who are identified as having a low likelihood of getting screened, you can improve rate of compliance within your target population. Most members do not realize they have high cholesterol just by assessing how they feel. Establishing a baseline through an inexpensive lipid panel blood test is an effective method to bring awareness to otherwise unknown health risk factors. Once identified, members can be educated by their providers on Statin therapy and certain lifestyle changes to bring high cholesterol down to a healthy range, improving overall health and reducing the likelihood of future costly medical interventions.