Neural Networks With Gated Recurrent Units Reduce Glucose Forecasting Error Due to Changes in Sensor Location
Authors' conclusion
We observe that GRU NNs can mitigate error in glucose prediction due to differences in CGM location.
Study context
- Population
- Participants with T2D wearing blinded continuous glucose monitors (CGMs) (FreeStyle Libre Pro-Abbott) on both arms for 12 weeks
- Participants
- 13 participants
- Comparison
- GRU NN vs time-delay feedforward NN for glucose forecasting across CGM sensor locations
- Outcome
- Glucose prediction error due to sensor location changes
Methodological detailsblinded CGMs on both arms
- Blinded CGMs on both arms
Main finding
As reported in the abstract
- GRU neural networks (NNs) did not produce significantly different errors in glucose prediction due to sensor location changes
- P < .05
Original publication
Neural Networks With Gated Recurrent Units Reduce Glucose Forecasting Error Due to Changes in Sensor Location. J Diabetes Sci Technol. Published 4 June 2022. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →