Every year, approximately 25% of the U.S. population gains, loses, or changes their source of health insurance coverage. This “churn” not only increases member acquisition and administrative costs, it can also destabilize care continuity and contribute to worse health outcomes. High levels of churn also disincentivize long-term investments in health promotion, particularly for SDoH efforts.
Learn how AI can help HCOs to reduce churn, address the needs of members likely to churn, and improve member engagement. Discover how AI can help predict which members are most likely to leave, identify specific factors that evince high risk of churning, and assess complex member data to provide insights that support outreach efforts and improved member health.
Data extracted from health insurance medical claims with details about dates and place of service, diagnosis codes, key procedures, use of medical equipment, and provider specialties.
Data about important risk markers from tests used for diagnosis, monitoring therapy, or screening, with details about specific results and abnormal indicators.
Data from health plans, clinics and service providers that capture details about service interactions, billing and payment, technical issues, and complaints.
ClosedLoop generates explainable predictions using
thousands of auto-generated, clinically relevant contributing factors
Churn is a term used to describe when a person gains, loses, or changes their source of health insurance coverage. It is a dynamic that has plagued the insurance industry for decades and is usually considered an inevitable challenge. Every year, approximately 25% of the U.S. population switches out of their health plan.¹ For people covered by Medicaid, churn is markedly higher. Medicaid’s complex eligibility requirements cause 50% of beneficiaries to lose coverage within 12 months of signing up, which can have particularly adverse effects on children.²
Churn clearly increases member acquisition and administrative costs. What fewer people realize is the extent to which it also destabilizes care continuity and contributes to worse health outcomes. Churn has been shown to reduce medication adherence (more than 33% of people who change coverage skip doses or stop taking their medication altogether), disrupt continuity of care, and patients with coverage interruptions have more emergency department (ED) use and hospitalizations.¹⁻³ A study of diabetics showed fivefold greater use of acute care services after coverage interruption compared to before the interruption regardless of age, sex, or diabetic complications.⁴
High levels of churn also disincentivize long-term investments for innovative programs like Geisinger’s “Farmacy” or Boston Medical Center's housing investments.⁵𝄒⁶ When executives know most coverage will only be held for a year or two, such investments make less sense, especially if the targeted population has churned into another plan where the ‘return’ ends up helping a competitor.
Improving patient engagement can help to achieve loyalty.⁷ Organizations that actively promote a person’s health can also gain their loyalty, an advantage that may prove difficult for competitors to dislodge. This can also create an enormous cost-of-care advantage. Engaged patients have better outcomes, irrespective of health status, age, sex, or income. They are less likely to have unmet medical needs, delay care, have clinical indicators outside the normal range, be hospitalized or use the ED. Moreover, their healthcare costs are 8–21% lower than their unengaged counterparts.⁸
Fortunately, predictive analytics can help healthcare organizations (HCOs) reduce churn and retain their member and patient populations. AI-based models can predict individuals likely to disenroll and surface key factors to help understand why. These insights allow teams to craft personalized retention communication plans, and make retention initiatives a more integral part of care management efforts to promote engagement and improve health.
1. Sommers BD, Gourevitch R, Maylone B, Blendon RJ, Epstein AM. Insurance Churning Rates For LowIncome Adults Under Health Reform: Lower Than Expected But Still Harmful For Many. Health Affairs. 2016;35(10):1816-1824. doi:10.1377/hlthaff.2016.0455
2. Swartz K, Short PF, Graefe DR, Uberoi N. Reducing Medicaid Churning: Extending Eligibility For Twelve Months Or To End Of Calendar Year Is Most Effective. Health Affairs. 2015;34(7):1180-1187. doi:10.1377/hlthaff.2014.1204
3. Banerjee R, Ziegenfuss JY, Shah ND. Impact of discontinuity in health insurance on resource utilization. BMC Health Services Research. 2010;10(1). doi:10.1186/1472-6963-10-195
4. Rogers MAM, Lee JM, Tipirneni R, Banerjee T, Kim C. Interruptions In Private Health Insurance And Outcomes In Adults With Type 1 Diabetes: A Longitudinal Study. Health Affairs. 2018;37(7):1024-1032. doi:10.1377/hlthaff.2018.0204
5. Feinberg A, Slotkin J, Hess A, Erskine A. How Geisinger Treats Diabetes by Giving Away Free, Healthy Food. Harvard Business Review. Published online October 25, 2017. https://hbr.org/2017/10/how-geisinger-treats-diabetes-by-giving-away-free-healthy-food
6. BMC. Boston Medical Center to Invest $6.5 Million in Affordable Housing to Improve Community Health and Patient Outcomes, Reduce Medical Costs. Boston Medical Center. Published December 7, 2017. https://www.bmc.org/news/press-releases/2017/12/07/boston-medical-center-invest-65-million-affordable-housing-improve
7. Heath S. Patient Experience Drives Patient Loyalty Over Standard Marketing. PatientEngagementHIT. Published online December 18, 2018. Accessed March 25, 2021. https://patientengagementhit.com/news/patient-experience-drives-patient-loyalty-over-standrad-marketing
8. Hibbard JH, Greene J, Overton V. Patients With Lower Activation Associated With Higher Costs; Delivery Systems Should Know Their Patients’ “Scores.” Health Affairs. 2013;32(2):216-222. doi:10.1377/hlthaff.2012.1064
ClosedLoop is an exciting and important partner in our strategy to develop timely predictive insights through operationalized AI solutions that will drive member engagement and better health outcomes.
Our partnership with ClosedLoop adds the depth of AI to more accurately identify those patients who are most likely to benefit from our primary care interventions as well to evaluate these interventions and make more relevant and timely modifications to improve their effectiveness.
We are extremely impressed with the predictive modeling capabilities the ClosedLoop platform has delivered. The ClosedLoop team has exceeded all defined goals and benchmarks set to date and we anticipate a substantial return on our investment as these predictions are operationally deployed.
We’re able to store and operationalize analytics directly from ClosedLoop. That’s driving real value—it’s accelerated the implementation of key insights into clinical workflows and it allows us to more easily account for all of the different factors that influence intervention decisions.
At SWHR, our patient-centered network is committed to innovative care models that are value-based, high-quality, and data-driven. Because of our partnership with ClosedLoop, we’re better able to identify and act on the most impactful opportunities for our physician partners to improve patient results and reduce unnecessary costs.
We compared the ClosedLoop predicted spend to the spend predicted by a leading rules-based risk prediction engine and found that 75% of the time ClosedLoop was closer, and in most cases significantly closer, to the actual spend.
Using predictive analytics to supplement clinician-driven referrals has helped me identify more patients more quickly for complex case management. I have greater assurance knowing this tool is helping me find patients most in need of my care.
ClosedLoop stood out from other AI firms in that they offered not only a usable, flexible analytics platform but extensive healthcare expertise.