Why the study?
Recent advances in diabetes technologies and continuous self-collected health data have made machine learning popular for capturing hypoglycemia, hyperglycemia, and glycemic variability despite complex blood glucose dynamics.
Design
Review
Authors
Loading...
Current methods using theoretical thresholds may be unreliable in T1D; leaves open personalized modeling to address patient variation.
Current machine learning approaches for blood glucose anomaly detection in Type 1 diabetes rely on theoretical thresholds, highlighting a need for personalized models that account for patient variation over time.
Woldaregay et al. (2019) studied this question.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: