AI Automatically Determines Insulin Dosing for Improved Blood Sugar Control in Hospitalized Patients

Hospitalized patients with complex dietary restrictions frequently experience hyperglycemia, or elevated blood sugar levels, which affects about one-quarter to one-half of such patients, potentially leading to severe complications, especially in those with existing diabetes. Managing blood sugar in a hospital environment is difficult due to factors like varying caloric intake, changes in organ function due to kidney or liver issues, surgical procedures, infections, and the challenges associated with intensive glucose monitoring and insulin management. To address these issues, researchers have devised a self-adjusting subcutaneous insulin algorithm (SQIA) that autonomously determines insulin doses, thereby reducing both hyperglycemia and hypoglycemia incidences and cutting down the frequency with which doctors need to issue new insulin orders.

Developed by medical experts at the University of California San Francisco (UCSF, San Francisco, CA, USA), the SQIA is an integrated calculator integrated into the medication administration record (MAR) within the electronic medical record system. Since its full implementation from September 2020 to September 2023, the SQIA has been utilized for thousands of patients subjected to dietary restrictions such as nothing by mouth (NPO), continuous tube feeds (TF), or intravenous nutrition (TPN). When physicians prescribe rapid-acting insulin under these nutritional conditions, they can opt to use the SQIA or traditional insulin (CI) dosing orders. The SQIA requires physicians to input just an initial insulin dose, which the algorithm then adjusts automatically, whereas the CI approach necessitates manual updating of insulin doses as needed.

During insulin administration, nurses input the patient's current glucose level into the MAR, and the SQIA calculates the new insulin dose based on previous insulin and glucose levels, as well as the current glucose reading. Ongoing adjustments to the algorithm and user interface, based on feedback from nurses, pharmacists, and physicians, have enhanced its precision in titrating the correct insulin dose. The research demonstrated that SQIA significantly reduced the number of insulin orders written by physicians by more than twelve times compared to CI dosing. It led to higher insulin doses in NPO and TPN diets, with a decrease in severe hyperglycemia rates and no increase in hypoglycemia, suggesting that CI orders might under-treat some patients. Moreover, the incidence of severe hyperglycemia continued to decline throughout the study, indicating ongoing improvements in SQIA's efficacy. Currently, SQIA is the preferred insulin ordering method at UCSF hospitals, chosen for about 80% of eligible patients by doctors.

“Our findings suggest that typical insulin inertia seen in adjusting insulin doses in many institutions would be overcome by an automated algorithm like the SQIA that reduces physician workload,” said UCSF endocrinologist Robert J. Rushakoff, MD, MS.

Related Links:
UCSF

Visit expo >

Gold Member

STI Test

Vivalytic Sexually Transmitted Infection (STI) Array

Flocked Fiber Swabs
Puritan® patented HydraFlock®

New

Gel-Based Electrode Arrays

Quik-Cap

New

Tablet Cart

Tryten S2