4.7 Article

Enhancing self-management in type 1 diabetes with wearables and deep learning

Related references

Note: Only part of the references are listed.
Article Computer Science, Information Systems

IoMT-Enabled Real-Time Blood Glucose Prediction With Deep Learning and Edge Computing

Taiyu Zhu et al.

Summary: This study proposes a new deep learning model and a wearable device to achieve real-time prediction of continuous blood glucose monitoring (CGM) and predictive hypoglycemia detection based on IoMT. The model achieved superior performance in blood glucose prediction accuracy and achieved the best results in hypoglycemia detection.

IEEE INTERNET OF THINGS JOURNAL (2023)

Article Health Care Sciences & Services

Deep transfer learning and data augmentation improve glucose levels prediction in type 2 diabetes patients

Yixiang Deng et al.

Summary: Accurate prediction of blood glucose variations in type 2 diabetes using deep-learning methods based on continuous glucose monitoring data helps improve glycemic control and quality of life for patients. The challenges of small dataset size and data imbalance are addressed through transfer learning and data augmentation techniques, resulting in high prediction accuracy and sensitivity for short-term glucose level predictions.

NPJ DIGITAL MEDICINE (2021)

Article Health Care Sciences & Services

Engineering digital biomarkers of interstitial glucose from noninvasive smartwatches

Brinnae Bent et al.

Summary: This study demonstrates the feasibility of using noninvasive and widely accessible methods, such as smartwatches and food logs, to continuously detect personalized glucose deviations and predict interstitial glucose values in real time with high accuracy. Additionally, methods for designing variables using data-driven and domain-driven approaches from noninvasive wearables for glucose prediction have been established.

NPJ DIGITAL MEDICINE (2021)

Article Computer Science, Information Systems

Basal Glucose Control in Type 1 Diabetes Using Deep Reinforcement Learning: An In Silico Validation

Taiyu Zhu et al.

Summary: This study proposes using deep reinforcement learning to improve blood glucose control in Type 1 diabetes patients, achieving significant progress in single-hormone and dual-hormone delivery strategies. The results demonstrate that this approach can effectively reduce hypoglycemia and increase the percentage of time patients spend in the target blood glucose range.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2021)

Review Computer Science, Information Systems

Deep Learning for Diabetes: A Systematic Review

Taiyu Zhu et al.

Summary: The field of diabetes management has seen significant advancements with the adoption of digital health technologies and the utilization of deep learning approaches. The review of literature highlights the successful applications of deep learning in diabetes diagnosis, glucose management, and the identification of diabetes-related complications.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2021)

Proceedings Paper Engineering, Electrical & Electronic

Blood Glucose Prediction in Type 1 Diabetes Using Deep Learning on the Edge

Taiyu Zhu et al.

Summary: Real-time blood glucose prediction using a novel deep learning framework achieved state-of-the-art performance with edge inference on a microcontroller unit. The personalized models built on glucose measurements from a CGM sensor and a recurrent neural network showed high clinical accuracy for predicting BG levels. The optimized framework minimized hardware usage and execution time for low power operations, showing potential for integration into wearable medical devices in diabetes care.

2021 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS) (2021)

Article Endocrinology & Metabolism

Feature-Based Machine Learning Model for Real-Time Hypoglycemia Prediction

Darpit Dave et al.

Summary: Innovative machine learning model developed for predicting hypoglycemia risk in youth with T1D based on CGM datasets, with high sensitivity and specificity. Model performance improved with inclusion of insulin and carbohydrate data for certain prediction horizons. Timely alerts of impending hypoglycemia may enable proactive measures to avoid severe hypoglycemia and achieve optimal glycemic control.

JOURNAL OF DIABETES SCIENCE AND TECHNOLOGY (2021)

Article Health Care Sciences & Services

Prediction and prevention of hypoglycaemic events in type-1 diabetic patients using machine learning

Josep Vehi et al.

HEALTH INFORMATICS JOURNAL (2020)

Article Endocrinology & Metabolism

Impact of Daily Physical Activity as Measured by Commonly Available Wearables on Mealtime Glucose Control in Type 1 Diabetes

Basak Ozaslan et al.

DIABETES TECHNOLOGY & THERAPEUTICS (2020)

Article Multidisciplinary Sciences

Re-epithelialization and immune cell behaviour in an ex vivo human skin model

Ana Rakita et al.

SCIENTIFIC REPORTS (2020)

Article Computer Science, Information Systems

GluNet: A Deep Learning Framework for Accurate Glucose Forecasting

Kezhi Li et al.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2020)

Article Computer Science, Information Systems

Convolutional Recurrent Neural Networks for Glucose Prediction

Kezhi Li et al.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2020)

Article Health Care Sciences & Services

Validity of the Empatica E4 Wristband to Measure Heart Rate Variability (HRV) Parameters: a Comparison to Electrocardiography (ECG)

Angela A. T. Schuurmans et al.

JOURNAL OF MEDICAL SYSTEMS (2020)

Article Engineering, Electrical & Electronic

Determining Physical Activity Characteristics From Wristband Data for Use in Automated Insulin Delivery Systems

Mert Sevil et al.

IEEE SENSORS JOURNAL (2020)

Article Computer Science, Information Systems

Prediction of Adverse Glycemic Events From Continuous Glucose Monitoring Signal

Matteo Gadaleta et al.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2019)

Review Health Care Sciences & Services

Data-Driven Blood Glucose Pattern Classification and Anomalies Detection: Machine-Learning Applications in Type 1 Diabetes

Ashenafi Zebene Woldaregay et al.

JOURNAL OF MEDICAL INTERNET RESEARCH (2019)

Article Health Care Sciences & Services

Deep learning algorithm predicts diabetic retinopathy progression in individual patients

Filippo Arcadu et al.

NPJ DIGITAL MEDICINE (2019)

Article Health Care Sciences & Services

Open source automated insulin delivery: addressing the challenge

Nick Oliver et al.

NPJ DIGITAL MEDICINE (2019)

Article Endocrinology & Metabolism

Hypoglycemia

Jean-Francois Yale et al.

CANADIAN JOURNAL OF DIABETES (2018)

Article Health Care Sciences & Services

Artificial intelligence powers digital medicine

Alexander L. Fogel et al.

NPJ DIGITAL MEDICINE (2018)

Review Endocrinology & Metabolism

Insulin analogues in type 1 diabetes mellitus: getting better all the time

Chantal Mathieu et al.

NATURE REVIEWS ENDOCRINOLOGY (2017)

Article Endocrinology & Metabolism

International Consensus on Use of Continuous Glucose Monitoring

Thomas Danne et al.

DIABETES CARE (2017)

Article Computer Science, Interdisciplinary Applications

Enhancing automatic closed-loop glucose control in type 1 diabetes with an adaptive meal bolus calculator - in silico evaluation under intra- day variability

Pau Herrero et al.

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE (2017)

Article Endocrinology & Metabolism

Improved A1C Levels in Type 1 Diabetes with Smartphone App Use

Edmond A. Ryan et al.

CANADIAN JOURNAL OF DIABETES (2017)

Review Endocrinology & Metabolism

Continuous Glucose Monitoring: A Review of Successes, Challenges, and Opportunities

David Rodbard

DIABETES TECHNOLOGY & THERAPEUTICS (2016)

Review Endocrinology & Metabolism

The changing face of diabetes complications

Edward W. Gregg et al.

LANCET DIABETES & ENDOCRINOLOGY (2016)

Article Engineering, Chemical

Hypoglycemia Early Alarm Systems Based on Multivariable Models

Kamuran Turksoy et al.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2013)

Article Health Care Sciences & Services

Diabetes Self-Management Smartphone Application for Adults With Type 1 Diabetes: Randomized Controlled Trial

Morwenna Kirwan et al.

JOURNAL OF MEDICAL INTERNET RESEARCH (2013)

Article Computer Science, Information Systems

Multivariate Prediction of Subcutaneous Glucose Concentration in Type 1 Diabetes Patients Based on Support Vector Regression

Eleni I. Georga et al.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2013)

Article Engineering, Biomedical

A Glucose-Specific Metric to Assess Predictors and Identify Models

Simone Del Favero et al.

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING (2012)

Article Biochemical Research Methods

Classification with correlated features: unreliability of feature ranking and solutions

Laura Tolosi et al.

BIOINFORMATICS (2011)

Article Endocrinology & Metabolism

Artificial Neural Network Algorithm for Online Glucose Prediction from Continuous Glucose Monitoring

C. Perez-Gandia et al.

DIABETES TECHNOLOGY & THERAPEUTICS (2010)

Article Biochemical Research Methods

A continuous measure of phasic electrodermal activity

Mathias Benedek et al.

JOURNAL OF NEUROSCIENCE METHODS (2010)

Review Endocrinology & Metabolism

Bolus Calculator: A Review of Four Smart Insulin Pumps

Howard Zisser et al.

DIABETES TECHNOLOGY & THERAPEUTICS (2008)

Article Medicine, General & Internal

Continuous Glucose Monitoring and Intensive Treatment of Type 1 Diabetes

NEW ENGLAND JOURNAL OF MEDICINE (2008)