Memorandum
Clinical decision support software for optimizing pump settings; 12-month, real-world use; Quality Improvement funded by Helmsley will test new diabetes solutions
T1D Exchange today announced a partnership with DreaMed to provide the FDA cleared DreaMed Advisor Pro to six clinics as part of T1D Exchange’s Quality Improvement Collaborative (QIC). Advisor Pro is an AI-based, clinical decision support software for optimizing pump settings based on CGM data – an especially great move considering very high pump penetration in the Exchange (63% as of DT&T data earlier this year) and growing CGM use (30%).
The QIC, funded by The Helmsley Charitable Trust, is comprised of a data platform of 30,000 individuals, as well as 11 US diabetes centers. The initiative brings together physicians and educators to improve care using quality improvement methods aimed at filling the gap between innovation and uptake. Small changes are implemented in individual clinics, allowing successes to then be disseminated across the network and scaled. We think this could be highly impactful, given the concerning state of T1D outcomes and clear potential to share lessons learned.
After 12 months of use, T1D Exchange and DreaMed will analyze patient outcomes to better understand Advisor Pro’s real-world efficacy. According to the press release, Advisor Pro will be positioned as tool to help particularly high-risk patients achieve glycemic control; we’d imagine teenagers and adolescents will be a key group, given mean A1c levels >9% now.
We can’t wait to see how this AI-based decision support solution will help physicians optimize pump therapy more quickly and automatically (and perhaps remotely), ideally freeing up time for more face-to-face troubleshooting.
T1D Exchange announced a separate agreement to use Glooko’s diabetes management platform to incorporate anonymized diabetes device data into the QIC. Raw device data will be linked to EMR data, providing a richer dataset. We expect this could help validate time-in-range and BeyondA1c endpoints (e.g., linking time-in-range with hospitalizations, healthcare utilization); better understanding the real-world impact of different technologies; and doing more granular comparisons between products, patient groups, and clinics.
These are both important moves to leverage real-world diabetes device data and algorithms to improve clinical care – what’s working and how can we do more of that (Bright Spots)? What’s not working and why?
QIC is actively recruiting additional US diabetes centers that specialize in treating type 1 diabetes. Current members of the QIC include:
-
Barbara Davis Center for Diabetes/Children’s Hospital Colorado
-
Baylor College of Medicine/Texas Children’s Hospital
-
Cincinnati Children’s Hospital
-
C.S. Mott Children’s Hospital, U of Michigan Hospitals-Michigan Medicine
-
The Joslin Diabetes Center – SUNY Upstate Medical University
-
Lucile Packard Children’s Hospital/Stanford
-
Nationwide Children’s Hospital
-
Penn Rodebaugh Diabetes Center, Penn Medicine
-
University of Missouri, Kansas City/ Children’s Mercy Kansas City
-
Wayne State University
--by Maeve Serino, Adam Brown, and Kelly Close