Continuous glucose monitors (CGMs) are prone to faults termed pressure-induced sensor attenuations (PISAs), particularly when the user rolls over on the sensor during sleep. PISAs result in false, low blood glucose readings, leading to undesirable pump shutoffs and an increased risk of hyperglycemia. Data from an outpatient trial with PISA glucose readings labeled for 1125 nights was used. Machine learning methods such as decision trees, support vector machines, neural networks, random forest, and gradient-boosted machine models are compared against each other and with a previously reported rules-based algorithm for PISA detection on the same data set. The best-performing gradient-boosted machine model is further improved using the developed start-PISA model. Model interpretation methods are used to confirm that PISA behavior is wellcaptured and provides insights into decision-making.
Background: Artificial pancreas (AP) systems reduce the treatment burden of Type 1 Diabetes by automatically regulating blood glucose (BG) levels. While many disturbances stand in the way of fully closed-loop (automated) control, unannounced meals remain the greatest challenge. Furthermore, different types of meals can have significantly different glucose responses, further increasing the uncertainty surrounding the meal. Methods: Effective attenuation of a meal requires quick and accurate insulin delivery because of slow insulin action relative to meal effects on BG. The proposed Variable Hump (VH) model adapts to meals of varying compositions by inferring both meal size and shape. To appropriately address the uncertainty of meal size, the model divides meal absorption into two disjoint regions: a region with coarse meal size predictions followed by a fine-grain region where predictions are fine-tuned by adapting to the meal shape. Results: Using gold-standard triple tracer meal data, the proposed VH model is compared to three simpler second-order response models. The proposed VH model increased model fit capacity by 22% and prediction accuracy by 12% relative to the next best models. A 47% increase in the accuracy of uncertainty predictions was also found. In a simple control scenario, the controller governed by the proposed VH model provided insulin just as fast or faster than the controller governed by the other models in four out of the six meals. While the controllers governed by the other models all delivered at least a 25% excess of insulin at their worst, the VH model controller only delivered 9% excess at its worst. Conclusions: The VH Model performed best in accuracy metrics and succeeded over the other models in providing insulin quickly and accurately in a simple implementation. Use in an AP system may improve prediction accuracy and lead to better control around mealtimes.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.