Neural Networks With Gated Recurrent Units Reduce Glucose Forecasting Error Due to Changes in Sensor Location

• Published in: Journal of diabetes science and technology Vol. 18; no. 1; p. 124
• Main Authors: Tucker, Aaron P, Erdman, Arthur G, Schreiner, Pamela J, Ma, Sisi, Chow, Lisa S
• Format: Journal Article
• Language: English
• Published: United States 01.01.2024
• Subjects: Blood Glucose; Blood Glucose Self-Monitoring - methods; Diabetes Mellitus, Type 2; Forecasting; Glucose; Humans; Neural Networks, Computer; gated recurrent unit; glucose forecast; continuous glucose monitoring; neural network
• ISSN: 1932-2968
• DOI: 10.1177/19322968221100839

Continuous glucose monitors (CGMs) have become important tools for providing estimates of glucose to patients with diabetes. Recently, neural networks (NNs) have become a common method for forecasting glucose values using data from CGMs. One method of forecasting glucose values is a time-delay feedforward (FF) NN, but a change in the CGM location on a participant can increase forecast error in a FF NN. In response, we examined a NN with gated recurrent units (GRUs) as a method of reducing forecast error due to changes in sensor location. We observed that for 13 participants with type 2 diabetes wearing blinded CGMs on both arms for 12 weeks (FreeStyle Libre Pro-Abbott), GRU NNs did not produce significantly different errors in glucose prediction due to sensor location changes ( < .05). We observe that GRU NNs can mitigate error in glucose prediction due to differences in CGM location.