The magnitude of poor adherence to medications for chronic conditions is striking. Of the approximately four billion prescriptions written each year, 20% are never filled, and when they are, only 50% are taken correctly. Poor medication adherence has been linked to an estimated 125,000 annual deaths, 10% of yearly hospital admissions, and up to $300 billion in annual economic impacts.
Learn how AI can help HCOs promote adherence as a part of routine clinical practice, increase patient engagement, and identify opportunities for improving patient outcomes. Discover how AI can help to regularly assess adherence, identify barriers to initiating or improving medication use (e.g., distance to nearest pharmacy), and identify patients where improved adherence can significantly reduce adverse events.
Data extracted from EHR clinical notes for conditions being diagnosed, monitored, or treated about important clinical concepts related to symptoms, test results, diagnoses and treatments.
Data extracted from health insurance pharmacy claims with details about each medication and its type, fill dates, days supply, pharmacy location, and prescribing clinician.
Captures a wide variety of data, including digital biomarkers, symptom trackers, vital signs, diet and exercise, weight, adherence trackers, sleep monitoring, self-assessments.
ClosedLoop generates explainable predictions using
thousands of auto-generated, clinically relevant contributing factors
The magnitude of poor adherence to medications for chronic conditions is striking. Of the approximately four billion prescriptions written each year, 20% are never filled and when they are, only 50% are taken correctly.¹ The price of poor medication adherence is similarly staggering. It has been linked to an estimated 125,000 annual deaths, 10% of yearly hospital admissions, and up to $300 billion in annual economic impacts.²⁻⁴ However, this burden is not inevitable.
Improving adherence can have a significant impact on costs and outcomes. For commercial populations, every $1 spent on medications reduced medical costs between $3-10 (depending on the condition) and for Medicare, the impact was even greater.⁵ In Medicaid populations, high adherence drove 8–26% fewer admissions and 3–12% fewer ER visits, again depending on the condition.⁶ Research has also shown that the benefits of better adherence accrue well before crossing an 80% threshold (often used to designate ‘good adherence’). They actually begin much sooner (e.g., at 40%) and grow as adherence rises. The same study also demonstrated that helping patients to initiate medications could possibly have an equal if not greater impact.
Medication adherence is a complex behavior influenced by several interacting factors that differ by patient, provider, medication, and condition.⁷𝄒⁸ In fact, systematic reviews have concluded there is no “best” intervention that is singularly effective.⁹⁻¹¹ Instead, success relied on being able to identify each patient’s needs and match them with the right intervention. Successful interventions varied, but common elements included face-to-face pharmacist consultations, addressing financial barriers, aiding habit formation (e.g., pill monitors and refill reminders), and using behavioral economic elements.
HCOs can leverage predictive analytics and AI to systematically promote adherence as a part of routine clinical practice. Exploiting AI-based models can enable clinicians to regularly assess each patient’s individual adherence, risk for specific adverse events, and barriers to care. This knowledge can facilitate personalized intervention efforts that address modifiable risk factors and account for the complexity and variable nature of medication adherence across different patients. Armed with predictive analytics, HCOs can readily identify the key opportunities in which improving adherence has the most potential to reduce risks and improve outcomes.
1. Neiman, Andrea B., et al. “CDC Grand Rounds: Improving Medication Adherence for Chronic Disease Management — Innovations and Opportunities.” MMWR. Morbidity and Mortality Weekly Report, vol. 66, no. 45, 17 Nov. 2017, pp. 1248–1251, DOI: http://dx.doi.org/10.15585/mmwr.mm6645a2. Accessed 24 Feb. 2021.
2. Brown, Marie T., Bussell, Jennifer K. “Medication Adherence: WHO Cares?” Mayo Clinic Proceedings, vol. 86, no. 4, Apr. 2011, pp. 304–314, DOI:10.4065/mcp.2010.0575. Accessed 24 Feb. 2021.
3. Kim, Jennifer, et al. “Medication Adherence: The Elephant in the Room.” US Pharmacist, vol. 43, no. 1, 19 Jan. 2018, pp. 30–34. Accessed 24 Feb. 2021.
4. NEHI “Taking Stock: Patient Medication Adherence and Chronic Disease Management.” Network for Excellence in Health Innovation, 10 Jun. 2020. Accessed 24 Feb. 2021.
5. Roebuck MC, Liberman JN, Gemmill-Toyama M, Brennan TA. Medication Adherence Leads To Lower Health Care Use And Costs Despite Increased Drug Spending. Health Affairs. 2011;30(1):91-99. doi:10.1377/hlthaff.2009.1087
6. Roebuck MC, Kaestner RJ, Dougherty JS. Impact of Medication Adherence on Health Services Utilization in Medicaid. Medical Care. 2018;56(3):1. doi:10.1097/mlr.0000000000000870
7. BA Briesacher, et al; Patients at-risk for cost-related medication nonadherence: a review of the literature. J Gen Intern Med. 2007;22:864-71.
8. Thinking Outside the Pillbox: A System-wide Approach to Improving Patient Medication Adherence for Chronic Disease; A NEHI Research Brief – August 2009
9. Medication Adherence Interventions: Comparative Effectiveness. Closing the Quality Gap: Revisiting the State of the Science: Evidence Report No. 208 (AHRQ Publication No. 12-E010-1)
10. M. Viswanathan, et al; Interventions to Improve Adherence to Self-administered Medications; Ann Inter Med; Sep 2012
11. Conn VS, Ruppar TM, Enriquez M, Cooper P. Medication adherence interventions that target subjects with adherence problems: Systematic review and meta-analysis. Research in Social and Administrative Pharmacy. 2016;12(2):218-246. doi:10.1016/j.sapharm.2015.06.001
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.