US 12,478,731 B2
Systems and methods for a data driven framework for actionable feedback in insulin management for type 1 diabetic subjects on artificial pancreas
Sandeep Gupta, Tempe, AZ (US); Ayan Banerjee, Tempe, AZ (US); and Yogish C. Kudva, Rochester, MN (US)
Assigned to Arizona Board of Regents on behalf of Arizona State University, Tempe, AZ (US); and Mayo Foundation for Medical Education and Research, Rochester, MN (US)
Appl. No. 17/913,108
Filed by Arizona Board of Regents on behalf of Arizona Stat, Tempe, AZ (US); and Mayo Foundation for Medical Education and Research, Rochester, MN (US)
PCT Filed Mar. 19, 2021, PCT No. PCT/US2021/023205
§ 371(c)(1), (2) Date Sep. 20, 2022,
PCT Pub. No. WO2021/188929, PCT Pub. Date Sep. 23, 2021.
Claims priority of provisional application 62/992,813, filed on Mar. 20, 2020.
Prior Publication US 2023/0138746 A1, May 4, 2023
Int. Cl. A61M 5/172 (2006.01); A61M 5/142 (2006.01); G06F 16/27 (2019.01); G16H 10/40 (2018.01); G16H 10/65 (2018.01); G16H 20/17 (2018.01)
CPC A61M 5/1723 (2013.01) [A61M 5/142 (2013.01); G06F 16/27 (2019.01); G16H 10/65 (2018.01); A61M 2230/201 (2013.01)] 27 Claims
OG exemplary drawing
 
1. A system, comprising:
a closed-loop control system including a continuous glucose monitor (CGM) operable to measure and output CGM records and including an insulin pump operable to output a plurality of insulin records, wherein the closed-loop control system is operable for operation in an “auto mode” (AP) and a “manual mode” (SAP);
at least one processor in communication with a memory and operable for execution of a plurality of modules, the plurality of modules comprising:
a data synchronization module for synchronizing insulin records and the CGM records;
an exit record parser module in operative association with the insulin pump for identifying instances of AP exits performed by the closed-loop control system and for annotating one or more reasons for each instance of AP exits;
a consensus and interval segmentation module operable to segment synchronized CGM records and insulin records into a plurality of sub-segments;
an AP/SAP segmentation module in communication with the consensus and interval segmentation module and the exit record parser module, the AP/SAP segmentation module operable to divide each sub-segment of the plurality of sub-segments based on their associated AP mode or SAP mode indicated by the exit record parser module to output fully segmented data; and
a metrics extraction engine operable to derive a plurality of metrics of the fully segmented data provided by the AP/SAP segmentation module according to a decision-making framework.