Algorithm-Enabled, Personalized Glucose Management for Type 1 Diabetes at the Population Scale: Prospective Evaluation in Clinical Practice

Abstract

Background The use of continuous glucose monitors (CGMs) is recommended as the standard of care by the American Diabetes Association for individuals with type 1 diabetes (T1D). Few hardware-agnostic, open-source, whole-population tools are available to facilitate the use of CGM data by clinicians such as physicians and certified diabetes educators. Objective This study aimed to develop a tool that identifies patients appropriate for contact using an asynchronous message through electronic medical records while minimizing the number of patients reviewed by a certified diabetes educator or physician using the tool. Methods We used consensus guidelines to develop timely interventions for diabetes excellence (TIDE), an open-source hardware-agnostic tool to analyze CGM data to identify patients with deteriorating glucose control by generating generic flags (eg, mean glucose [MG] >170 mg/dL) and personalized flags (eg, MG increased by >10 mg/dL). In a prospective 7-week study in a pediatric T1D clinic, we measured the sensitivity of TIDE in identifying patients appropriate for contact and the number of patients reviewed. We simulated measures of the workload generated by TIDE, including the average number of time in range (TIR) flags per patient per review period, on a convenience sample of eight external data sets, 6 from clinical trials and 2 donated by research foundations. Results Over the 7 weeks of evaluation, the clinical population increased from 56 to 64 patients. The mean sensitivity was 99% (242/245; SD 2.5%), and the mean reduction in the number of patients reviewed was 42.6% (182/427; SD 10.9%). The 8 external data sets contained 1365 patients with 30,017 weeks of data collected by 7 types of CGMs. The rates of generic and personalized TIR flags per patient per review period were, respectively, 0.15 and 0.12 in the data set with the lowest average MG (141 mg/dL) and 0.95 and 0.22 in the data set with the highest average MG (207 mg/dL). Conclusions TIDE is an open-source hardware-agnostic tool for personalized analysis of CGM data at the clinical population scale. In a pediatric T1D clinic, TIDE identified 99% of patients appropriate for contact using an asynchronous message through electronic medical records while reducing the number of patients reviewed by certified diabetes care and education specialists by 43%. For each of the 8 external data sets, simulation of the use of TIDE produced fewer than 0.25 personalized TIR flags per patient per review period. The use of TIDE to support telemedicine-based T1D care may facilitate sensitive and efficient guideline-based population health management.

Remote glucose monitoring is feasible for patients and providers using a commercially available population health platform

“…As in our study, this group employed RPM in a pediatric population with T1D all of whom used Dexcom CGM devices, although their population was newly diagnosed with T1D whereas ours was not (17)(18)(19). Other differences include that our study followed a smaller patient cohort (36 versus 89) for a shorter time (6 versus 12 months) with less frequent outreach (monthly versus weekly).…”

“…Their RPM program resulted in a 8.8% increase in time-in-range and 0.58% decrease in HbA1c for participants after 12 months in comparison to a non-randomized, historical control group ( 17 , 19 ), which is similar to the results we observed for the highest GMI quartile of our study population after 6 months. Their studies report RPM provider time as varying from 1.3 to 4.5 minutes per patient per week ( 17 , 18 ). While this time investment is comparable to our study’s 2.9 to 7.6 minutes per patient per month, their program demonstrated greater efficiency due to more frequent review (1.3-4.5 versus 2.9-7.6 minutes per patient per outreach period ).…”

“…Improvements in glycemic control have been previously documented for adult populations enrolled in a commercial RPM program (15,16), although these involved use of intermittent BGM (rather than CGM) and the majority of participants had type 2 rather than type 1 diabetes. The most pertinent existing literature to compare to our study comes from a single institution which has developed and deployed a homegrown population health platform to analyze CGM data remotely and identify pediatric T1D patients meeting high-risk criteria in order to enable outreach by clinical staff (17)(18)(19).…”

Advancements and future directions in the teamwork, targets, technology, and tight control—the 4T study: improving clinical outcomes in newly diagnosed pediatric type 1 diabetes

“…Our team has continued to iterate and improve on the features of the dashboard. This Timely Interventions for Diabetes Excellence (TIDE) tool is a unique, open-source dashboard that has algorithm-enabled prioritization of participants who would benefit from remote CGM data review and dose adjustments by a CDCES to apply precision medicine on a population health basis [29 ▪ ,30]. It serves as an automated decision-support tool that uses CGM data to support setting personalized goals and identify a need for insulin dose adjustments in between quarterly visits.…”

Adding glycemic and physical activity metrics to a multimodal algorithm-enabled decision-support tool for type 1 diabetes care: Keys to implementation and opportunities

“…An open-source algorithm-enabled care model providing patient prioritization, called Timely Interventions for Diabetes Excellence (TIDE), was developed at Stanford to support clinicians and Certified Diabetes Care and Education Specialists (CDCES) at Stanford Children’s Pediatric diabetes clinic ( 14 – 16 ). The current TIDE care model facilitates population-level algorithm-enabled remote patient monitoring (RPM) based on continuous glucose monitoring (CGM) data ( 15 ).…”