skip to main content


Title: Detection of Hypoglycemia and Hyperglycemia Using Noninvasive Wearable Sensors: ECG and Accelerometry
Background: Monitoring glucose excursions is important in diabetes management. This can be achieved using continuous glucose monitors (CGMs). However, CGMs are expensive and invasive. Thus, alternative low-cost noninvasive wearable sensors capable of predicting glycemic excursions could be a game changer to manage diabetes. Methods: In this article, we explore two noninvasive sensor modalities, electrocardiograms (ECGs) and accelerometers, collected on five healthy participants over two weeks, to predict both hypoglycemic and hyperglycemic excursions. We extract 29 features encompassing heart rate variability features from the ECG, and time- and frequency-domain features from the accelerometer. We evaluated two machine-learning approaches to predict glycemic excursions: a classification model and a regression model. Results: The best model for both hypoglycemia and hyperglycemia detection was the regression model based on ECG and accelerometer data, yielding 76% sensitivity and specificity for hypoglycemia and 79% sensitivity and specificity for hyperglycemia. This had an improvement of 5% in sensitivity and specificity for both hypoglycemia and hyperglycemia when compared with using ECG data alone. Conclusions: Electrocardiogram is a promising alternative not only to detect hypoglycemia but also to predict hyperglycemia. Supplementing ECG data with contextual information from accelerometer data can improve glucose prediction.  more » « less
Award ID(s):
2037383
NSF-PAR ID:
10352256
Author(s) / Creator(s):
; ; ; ; ; ; ;
Date Published:
Journal Name:
Journal of Diabetes Science and Technology
ISSN:
1932-2968
Page Range / eLocation ID:
193229682211163
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. In this paper, we provide an approach to data-driven control for artificial pancreas systems by learning neural network models of human insulin-glucose physiology from available patient data and using a mixed integer optimization approach to control blood glucose levels in real-time using the inferred models. First, our approach learns neural networks to predict the future blood glucose values from given data on insulin infusion and their resulting effects on blood glucose levels. However, to provide guarantees on the resulting model, we use quantile regression to fit multiple neural networks that predict upper and lower quantiles of the future blood glucose levels, in addition to the mean. Using the inferred set of neural networks, we formulate a model-predictive control scheme that adjusts both basal and bolus insulin delivery to ensure that the risk of harmful hypoglycemia and hyperglycemia are bounded using the quantile models while the mean prediction stays as close as possible to the desired target. We discuss how this scheme can handle disturbances from large unannounced meals as well as infeasibilities that result from situations where the uncertainties in future glucose predictions are too high. We experimentally evaluate this approach on data obtained from a set of 17 patients over a course of 40 nights per patient. Furthermore, we also test our approach using neural networks obtained from virtual patient models available through the UVA-Padova simulator for type-1 diabetes. 
    more » « less
  2. Introduction Blood sugar homeostasis relies largely on the action of pancreatic islet hormones, particularly insulin and glucagon. In a prototypical fashion, glucagon is released upon hypoglycemia to elevate glucose by acting on the liver while elevated glucose induces the secretion of insulin which leads to sugar uptake by peripheral tissues. This simplified view of glucagon and insulin does not consider the paracrine roles of the two hormones modulating the response to glucose of α- and β-cells. In particular, glucose-stimulated glucagon secretion by isolated α-cells exhibits a Hill-function pattern, while experiments with intact pancreatic islets suggest a ‘U’-shaped response. Methods To this end, a framework was developed based on first principles and coupled to experimental studies capturing the glucose-induced response of pancreatic α- and β-cells influenced by the two hormones. The model predicts both the transient and steady-state profiles of secreted insulin and glucagon, including the typical biphasic response of normal β-cells to hyperglycemia. Results and discussion The results underscore insulin activity as a differentiating factor of the glucagon secretion from whole islets vs . isolated α-cells, and highlight the importance of experimental conditions in interpreting the behavior of islet cells in vitro . The model also reproduces the hyperglucagonemia, which is experienced by diabetes patients, and it is linked to a failure of insulin to inhibit α-cell activity. The framework described here is amenable to the inclusion of additional islet cell types and extrapancreatic tissue cells simulating multi-organ systems. The study expands our understanding of the interplay of insulin and glucagon for pancreas function in normal and pathological conditions. 
    more » « less
  3. Societal Impact Statement Summary

    The recent trend in sedentary lifestyles and nutritionally‐imbalanced diets has elevated the prevalence of Type 2 diabetes in many parts of the world. Some pharmacological glycemic management can cause undesirable gastrointestinal side effects or hypoglycemia. Thus, there is a growing interest in safe glycemic management using dietary (poly)phenols.

    In this study, (poly)phenol‐rich extracts of 476 apple accessions from Canada's Apple Biodiversity Collection (ABC) and six major apple (poly)phenols were assessed for in vitro antidiabetic properties against the activities of α‐glucosidase, α‐amylase, and dipeptidyl peptidase‐4 (DPP‐4) and the formation of advanced glycation end products (AGE).

    Apple (poly)phenol extracts varied in their antidiabetic activities in a dose‐dependent manner. High (poly)phenol‐containing apples demonstrated that their total phenolic contents (TPC) were inversely correlated with the IC50values of α‐glucosidase, α‐amylase, and AGE formation, but not DPP‐4. Concentrations of major (poly)phenol compounds such as procyanidin B2, phloridzin, and epicatechin in apples were significantly inversely correlated with IC50values of α‐glucosidase in the high (poly)phenol‐containing apples.

    High TPC apples are not suitable for marketing for fresh fruit consumption due to bitterness and astringency; however, these apples show potential to use in the development of value‐added functional food ingredients or nutraceuticals for blood glucose management. The high TPC apple, “S23‐03‐749,” an advanced breeding line of dessert apple, presents a novel option as a specialty apple cultivar for the dietary management of glycemia.

     
    more » « less
  4. Objective Sudden unexpected death in epilepsy (SUDEP) is the leading cause of epilepsy-related mortality. Although lots of effort has been made in identifying clinical risk factors for SUDEP in the literature, there are few validated methods to predict individual SUDEP risk. Prolonged postictal EEG suppression (PGES) is a potential SUDEP biomarker, but its occurrence is infrequent and requires epilepsy monitoring unit admission. We use machine learning methods to examine SUDEP risk using interictal EEG and ECG recordings from SUDEP cases and matched living epilepsy controls. Methods This multicenter, retrospective, cohort study examined interictal EEG and ECG recordings from 30 SUDEP cases and 58 age-matched living epilepsy patient controls. We trained machine learning models with interictal EEG and ECG features to predict the retrospective SUDEP risk for each patient. We assessed cross-validated classification accuracy and the area under the receiver operating characteristic (AUC) curve. Results The logistic regression (LR) classifier produced the overall best performance, outperforming the support vector machine (SVM), random forest (RF), and convolutional neural network (CNN). Among the 30 patients with SUDEP [14 females; mean age (SD), 31 (8.47) years] and 58 living epilepsy controls [26 females (43%); mean age (SD) 31 (8.5) years], the LR model achieved the median AUC of 0.77 [interquartile range (IQR), 0.73–0.80] in five-fold cross-validation using interictal alpha and low gamma power ratio of the EEG and heart rate variability (HRV) features extracted from the ECG. The LR model achieved the mean AUC of 0.79 in leave-one-center-out prediction. Conclusions Our results support that machine learning-driven models may quantify SUDEP risk for epilepsy patients, future refinements in our model may help predict individualized SUDEP risk and help clinicians correlate predictive scores with the clinical data. Low-cost and noninvasive interictal biomarkers of SUDEP risk may help clinicians to identify high-risk patients and initiate preventive strategies. 
    more » « less
  5. Postprandial hyperglycemia (PPHG) is detrimental to health and increases risk of cardiovascular diseases, reduced eyesight, and life-threatening conditions like cancer. Detecting PPHG events before they occur can potentially help with providing early interventions. Prior research suggests that PPHG events can be predicted based on information about diet. However, such computational approaches (1) are data hungry requiring significant amounts of data for algorithm training; and (2) work as a black-box and lack interpretability, thus limiting the adoption of these technologies for use in clinical interventions. Motivated by these shortcomings, we propose, DietNudge 1 , a machine learning based framework that integrates multi-modal data about diet, insulin, and blood glucose to predict PPHG events before they occur. Using data from patients with diabetes, we demonstrate that our model can predict PPHG events with up to 90% classification accuracy and an average F1 score of 0.93. The proposed decision-tree-based approach also identifies modifiable factors that contribute to an impending PPHG event while providing personalized thresholds to prevent such events. Our results suggest that we can develop simple, yet effective, computational algorithms that can be used as preventative mechanisms for diabetes and obesity management. 
    more » « less