Learn How

Learn how AI can help HCOs to appropriately prescribe CGM devices, improve glucose management for patients with type 2 diabetes on intensive insulin regimens, and reduce the incidence of adverse glycemic events. Discover how AI can predict individual patients at the greatest risk for adverse glycemic events, surface their specific risk factors, and provide tailored insights to help determine who will benefit most from CGM.

Automatically ingest data from dozens of health data sources including...

Unstructured Clinical Notes

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.

e-Prescribing Data

Data from electronic prescriptions detailing key information about medications, dosage, patient instructions for frequency and timing, and available refills.

Lab Test Results

Data about important risk markers from tests used for diagnosis, monitoring therapy, or screening, with details about specific results and abnormal indicators.

Closedloop icon with a line

ClosedLoop generates explainable predictions using

thousands of auto-generated, clinically relevant contributing factors

Clark Dunkin
51-Year-Old Male
Risk of hypoglycemia-related ED visit in the next 6 months
Risk Score Percentile
Impact on Risk  |  Contributing Factor
+26% | # of Hypoglycemic Plasma Glucose Concentration Readings (1M)
+23% | Daily Insulin Use
225 units / day
+16% | HbA1C Level (3M)
+13% | # of Unplanned Admissions (12M)

What is Continuous Glucose Monitoring?

Diabetes affects approximately 34 million adults in the U.S. and is responsible for a total estimated cost of $327 billion annually.¹𝄒² Deficient glycemic control substantially contributes to this burden and is a leading cause of adverse glycemic events, emergency department (ED) utilization, and hospitalization for diabetics. Patients with type 2 diabetes (90% of diabetics) have traditionally used finger prick blood meters to manage glucose, but these tools can only reflect glucose levels when they are taken and provide a limited number of daily readings.³𝄒⁴ Continuous glucose monitoring (CGM) presents an opportunity to overcome these limitations and significantly improve glucose management for patients on intensive insulin regimens. In contrast to finger prick meters, CGM devices can provide more than 280 glucose readings daily.⁴ This enables users at high risk for acute exacerbation to assess glucose variability, identify trends in real-time, and better engage in glucose management. 

Why It Matters

CGM use notably reduces the incidence of adverse glycemic events and all-cause hospitalization in type 2 diabetics on rapid-acting insulin therapy. A recent study found that just 45 days of CGM use decreased the incidence rate of acute diabetes-related events by more than half when compared to the six months prior to CGM.⁵ CGM use was also associated with more than a 40% reduction in hospitalizations for infections, renal disease, and liver disease. In another study of a diabetic population treated with insulin, a year of CGM use was found to decrease the percentage of diabetes-related hospital admissions by 66%.⁶

CGM use may also result in a greater reduction of adverse glycemic events than expected, as such events are severely underreported. In a recent survey of diabetics on glucose-lowering medications, 11.7% reported one or more severe hypoglycemic events requiring assistance in the past year, but only 0.8% had a documented hypoglycemia-related ED visit or hospitalization in the same timeframe.⁷  

AI Presents an Opportunity

Yet, 90% of type 2 diabetics receive their care from a primary care physician (PCP), and many PCPs are only beginning to familiarize themselves with the technology.³ If they are to have confidence prescribing an expensive CGM device in limited supply, they must be able to ensure its usage is appropriate. They need the ability to predict which insulin intensive patients are at the greatest risk for acute diabetic exacerbations and unplanned hospitalizations.

AI is ideally positioned to help healthcare organizations (HCOs) pinpoint individual patients at the greatest risk for adverse glycemic events. Predictive analytics can identify the highest risk patients on intensive insulin regimens, surface their specific risk factors, and provide tailored insights to help determine who will benefit most from CGM. Further, AI can surface and consolidate the information needed for CGM authorization requirements, and can leverage CGM data to help HCOs proactively evaluate and refine insulin-based therapy. 

Did You Know...

  • 30 million adults in the U.S. are affected by type 2 diabetes³ 
  • 90% of type 2 diabetics receive their care from a PCP³
  • 280+ glucose readings occur daily from a CGM device⁴
  • A roughly 2x greater drop in A1C levels (a measure of avg. blood glucose) was achieved with CGM compared to traditional finger prick methods³
Citations & Footnotes

1. CDC. “National Diabetes Statistics Report, 2020.” U.S. Department of Health and Human Services, Centers for Disease Control and Prevention, 18 Feb. 2020. 

2. American Diabetes Association. “Economic Costs of Diabetes in the U.S. in 2017.” Diabetes Care, vol. 41, no. 5, 22 Mar. 2018, pp. 917-928. doi.org/10.2337/dci18-0007.

3. Palmer, Katie. “Demand is growing for continuous glucose monitoring for type 2 diabetes. Primary care doctors need to prepare.” STAT, 30 June 2021. https://www.statnews.com/2021/06/30/continuous-glucose-monitoring-type-2-diabetes-primary-care/. Accessed 15 July 2021.

4. Brown, Greg. “What’s a CGM (Continuous Glucose Monitor) and How Do I Choose One?” Healthline, 30 Sep. 2020. https://www.healthline.com/diabetesmine/what-is-continuous-glucose-monitor-and-choosing-one. Accessed 15 July 2021.

5. Bergenstal, M. Richard, et al. “Flash CGM Is Associated With Reduced Diabetes Events and Hospitalizations in Insulin-Treated Type 2 Diabetes.” Journal of the Endocrine Society, vol. 5, no. 4, 2 Feb. 2021. https://doi.org/10.1210/jendso/bvab013. Accessed 15 July 2021.

6. Marion, Fokket, et al. “Improved well-being and decreased disease burden after 1-year use of flash glucose monitoring (FLARE-NL4).” BMJ Open Diabetes Research & Care, vol. 7, no. 1, 9 Dec. 2019. DOI: 10.1136/bmjdrc-2019-000809. Accessed 14 July 2021.

7. Karter, J. Andrew, et al. “Surveillance of Hypoglycemia—Limitations of Emergency Department and Hospital Utilization Data.” JAMA Internal Medicine, vol 178, no. 7, 1 July 2018, pp. 987-988. DOI: 10.1001/jamainternmed.2018.1014. Accessed 14 July 2021.

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.

Pat Wang
President & CEO, Healthfirst

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.

David Klebonis
Chief Operating Officer, PBACO

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.

Cheryl Lulias
President & Executive Director, MHN

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.

Christer Johnson
Chief Analytics Officer, Healthfirst

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.

Dr. Jason Fish
Chief Medical Officer & SVP, Southwestern Health Resources

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.

Phillip Bruns
Chief Technology Officer, CareATC

Learn What ClosedLoop Can Do for Your Organization

The industry’s best collection of customizable predictive models for common healthcare use cases.

Talk To An Expert