Neural Physiological Model: A Simple Module for Blood Glucose Prediction

Gu, Kang; Dang, Ruoqi; Prioleau, Temiloluwa

doi:10.1109/embc44109.2020.9176004

Cited by 12 publications

(6 citation statements)

References 17 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The following study introduces NPE into the LSTM model to process the influence of physiological events on blood glucose events. The RMSE of 30 min improved to 17.8 mg/dL, which is the second best in our collection [17].…”

Section: Potential Factors That Can Influence the Accuracymentioning

confidence: 64%

See 1 more Smart Citation

A comparison of various deep learning models on blood glucose management of type 1 diabetes: A brief review

Jiang,

Yang

2023

ACE

View full text Add to dashboard Cite

Type 1 diabetes has become one of the most common chronic diseases nowadays because patients pancreas cannot produce sufficient insulin, which helps the blood sugar to enter the cells, which will cause them to build up in the bloodstream and leads to complications and dis-eases. Therefore, a basal-bolus insulin therapy that contains daily insulin injections has be-come routine for patients with type 1 diabetes to help regulate the blood sugar level. To better monitor the blood glucose level, digital health monitors are becoming the trending method for type 1 diabetes patients. Meanwhile, all the data generated by the digital monitoring devices made researchers realize that deep learning algorithms could be implanted to help the device better predict a patients blood sugar levels. In this paper, we aim to present a review of testing several state-of-the-art deep-learning models on blood glucose prediction. We have identified a literature search and focused on the deep-learning algorithms for glucose management. After detailed explanations of each model, we employ them on one mutual dataset to identify the direct prediction results of each model and compare the pros and cons of these models accord-ing to the results report. While all these models have the most advanced frameworks, the lack of feature varieties and data availability becomes their limitations. However, followed by the increased focus on the digital health field, these challenges might soon get resolved, which leads to more comprehensive models that could be further deployed in clinical conditions.

show abstract

Section: Potential Factors That Can Influence the Accuracymentioning

confidence: 64%

“…First, introducing NPE into traditional machine learning models can improve accuracy by strengthening the model's response to special physiological events [17]. The existing deep learning models rely on feature selection by deep learning itself.…”

Section: Future Opportunitiesmentioning

confidence: 99%

A comparison of various deep learning models on blood glucose management of type 1 diabetes: A brief review

Jiang,

Yang

2023

ACE

View full text Add to dashboard Cite

show abstract

“…In the dataset with six subjects in 2018, various machine learning algorithms for BGL prediction, such as XGBoost, were compared [43]. In addition, the proposed method is compared with state-of-the-art deep learning methods, including convolutional neural networks (CNN) [44], dilated recurrent neural networks (DRNN) [20], artificial neural networks (ANN) [45], stack long short-term memory (StackLSTM) [21], the fusion of neural physiological encoder (NPE) and long short-term memory (LSTM) [46], and an improved deep learning model for BGL prediction (GluNet) [47]. In the experiments conducted using the 2018 dataset with six subjects, the proposed model achieved the lowest RMSE and MAE for a 30-minute PH.…”

Section: Datasetmentioning

confidence: 99%

AWD-stacking: An enhanced ensemble learning model for predicting glucose levels

Yang,

Chen,

Huang

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Accurate prediction of blood glucose levels is essential for type 1 diabetes optimizing insulin therapy and minimizing complications in patients with type 1 diabetes. Using ensemble learning algorithms is a promising approach. In this regard, this study proposes an improved stacking ensemble learning algorithm for predicting blood glucose level, in which three improved long short-term memory network models are used as the base model, and an improved nearest neighbor propagation clustering algorithm is adaptively weighted to this ensemble model. The OhioT1DM dataset is used to train and evaluate the performance of the proposed model. This study evaluated the performance of the proposed model using the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Matthews Correlation Coefficient (MCC) as the evaluation metrics. The experimental results demonstrate that the proposed model achieves an RMSE of 1.425 mg/dL, MAE of 0.721 mg/dL, and MCC of 0.982 mg/dL for a 30-minute prediction horizon(PH), RMSE of 3.212 mg/dL, MAE of 1.605 mg/dL, and MCC of 0.950 mg/dL for a 45-minute PH; and RMSE of 6.346 mg/dL, MAE of 3.232 mg/dL, and MCC of 0.930 mg/dL for a 60-minute PH. Compared with the best non-ensemble model StackLSTM, the RMSE and MAE were improved by up to 27.92% and 65.32%, respectively. Clarke Error Grid Analysis and critical difference diagram revealed that the model errors were within 10%. The model proposed in this study exhibits state-of-the-art predictive performance, making it suitable for clinical decision-making and of significant importance for the effective treatment of diabetes in patients.

show abstract

“…The proposed Glycolyzer solution leveraged heatmap visualization for illustrating a collection of meals and hierarchical clustering for [66] and data-driven insights on behavioral factors that affect diabetes [50]. In addition, there is ample research on algorithms for blood glucose prediction to support development of closed-loop artificial pancreas systems [21,31,36,53,63]. Unlike the aforementioned literature, this work aims to develop a solution to help end-users (e.g., clinicians) find hidden patterns of poor management from wearable device data to inform adjustments in treatment plans, as needed.…”

Section: Decision-support Tools In Diabetes Carementioning

confidence: 99%

GlucoMine

Bartolome

Shah

Prioleau

2021

Proc. ACM Interact. Mob. Wearable Ubiquitous Technol.

Self Cite

View full text Add to dashboard Cite

The growing popularity of wearable devices for continuous sensing has made personal health data increasingly available, yet methods for data interpretation are still a work in progress. This paper investigates potential under-utilization of wearable device data in diabetes management and develops an analytic approach - GlucoMine - to uncover individualized patterns in extended periods of such data to support and improve care. In addition, we conduct a user study with clinicians to assess and compare conventional tools used for reviewing wearable device data in diabetes management with the proposed solution. Using 3-6 months of continuous glucose monitor (CGM) data from 54 patients with type 1 diabetes, we found that: 1) the recommended practice of reviewing only short periods (e.g., the most recent 2-weeks) of CGM data based on correlation analysis is not sufficient for finding hidden patterns of poor management; 2) majority of subjects (96% in this study) had clinically-recognized episodes of recurrent adverse glycemic events observable from analysis of extended periods of their CGM data; 3) majority of clinicians (89% in this study) believe there is benefit to be gained in having an algorithm for extracting patterns of adverse glycemic events from longer periods of wearable device data. Findings from our user study also provides insights, including strengths and weakness of various data presentation tools, to guide development of better solutions that improve the use of wearable device data for patient care.

show abstract

Neural Physiological Model: A Simple Module for Blood Glucose Prediction

Cited by 12 publications

References 17 publications

A comparison of various deep learning models on blood glucose management of type 1 diabetes: A brief review

A comparison of various deep learning models on blood glucose management of type 1 diabetes: A brief review

AWD-stacking: An enhanced ensemble learning model for predicting glucose levels

GlucoMine

Contact Info

Product

Resources

About