Incorporating an Exercise Detection, Grading, and Hormone Dosing Algorithm Into the Artificial Pancreas Using Accelerometry and Heart Rate

Online Classification of Unstructured Free-Living Exercise Sessions in People with Type 1 Diabetes

Background: Managing exercise in type 1 diabetes is challenging, in part, because different types of exercises can have diverging effects on glycemia. The aim of this work was to develop a classification model that can classify an exercise event (structured or unstructured) as aerobic, interval, or resistance for the purpose of incorporation into an automated insulin delivery (AID) system. Methods: A long short-term memory network model was developed with real-world data from 30-min structured sessions of at-home exercise (aerobic, resistance, or mixed) using triaxial accelerometer, heart rate, and activity duration information. The detection algorithm was used to classify 15 common free-living and unstructured activities and relate each to exercise-associated change in glucose. Results: A total of 1610 structured exercise sessions were used to train, validate, and test the model. The accuracy for the structured exercise sessions in the testing set was 72% for aerobic, 65% for interval, and 77% for resistance. In addition, we tested the classifier on 3328 unstructured sessions. We validated the session-associated change in glucose against the expected change during exercise for each type. Mean and standard deviation of the change in glucose of -20.8 (40.3) mg/dL were achieved for sessions classified as aerobic, -16.2 (39.0) mg/dL for sessions classified as interval, and -11.6 (38.8) mg/dL for sessions classified as resistance. Conclusions: The proposed algorithm reliably identified physical activity associated with expected change in glucose, which could be integrated into an AID system to manage the exercise disturbance in glycemia according to the predicted class.

Artificial Intelligence and Machine Learning for Improving Glycemic Control in Diabetes: Best Practices, Pitfalls, and Opportunities

OBJECTIVE

Artificial intelligence and machine learning are transforming many fields including medicine. In diabetes, robust biosensing technologies and automated insulin delivery therapies have created a substantial opportunity to improve health. While the number of manuscripts addressing the topic of applying machine learning to diabetes has grown in recent years, there has been a lack of consistency in the methods, metrics, and data used to train and evaluate these algorithms. This manuscript provides consensus guidelines for machine learning practitioners in the field of diabetes, including best practice recommended approaches and warnings about pitfalls to avoid.

METHODS

Algorithmic approaches are reviewed and benefits of different algorithms are discussed including importance of clinical accuracy, explainability, interpretability, and personalization. We review the most common features used in machine learning applications in diabetes glucose control and provide an open-source library of functions for calculating features, as well as a framework for specifying data sets using data sheets. A review of current data sets available for training algorithms is provided as well as an online repository of data sources.

SIGNIFICANCE

These consensus guidelines are designed to improve performance and translatability of new machine learning algorithms developed in the field of diabetes for engineers and data scientists.

Detection of Meals and Physical Activity Events From Free-Living Data of People With Diabetes

BACKGROUND

Predicting carbohydrate intake and physical activity in people with diabetes is crucial for improving blood glucose concentration regulation. Patterns of individual behavior can be detected from historical free-living data to predict meal and exercise times. Data collected in free-living may have missing values and forgotten manual entries. While machine learning (ML) can capture meal and exercise times, missing values, noise, and errors in data can reduce the accuracy of ML algorithms.

METHODS

Two recurrent neural networks (RNNs) are developed with original and imputed data sets to assess detection accuracy of meal and exercise events. Continuous glucose monitoring (CGM) data, insulin infused from pump data, and manual meal and exercise entries from free-living data are used to predict meals, exercise, and their concurrent occurrence. They contain missing values of various lengths in time, noise, and outliers.

RESULTS

The accuracy of RNN models range from 89.9% to 95.7% for identifying the state of event (meal, exercise, both, or neither) for various users. "No meal or exercise" state is determined with 94.58% accuracy by using the best RNN (long short-term memory [LSTM] with 1D Convolution). Detection accuracy with this RNN is 98.05% for meals, 93.42% for exercise, and 55.56% for concurrent meal-exercise events.

CONCLUSIONS

The meal and exercise times detected by the RNN models can be used to warn people for entering meal and exercise information to hybrid closed-loop automated insulin delivery systems. Reliable accuracy for event detection necessitates powerful ML and large data sets. The use of additional sensors and algorithms for detecting these events and their characteristics provides a more accurate alternative.

The Type 1 Diabetes and EXercise Initiative: Predicting Hypoglycemia Risk During Exercise for Participants with Type 1 Diabetes Using Repeated Measures Random Forest

Objective: Exercise is known to increase the risk for hypoglycemia in type 1 diabetes (T1D) but predicting when it may occur remains a major challenge. The objective of this study was to develop a hypoglycemia prediction model based on a large real-world study of exercise in T1D. Research Design and Methods: Structured study-specified exercise (aerobic, interval, and resistance training videos) and free-living exercise sessions from the T1D Exercise Initiative study were used to build a model for predicting hypoglycemia, a continuous glucose monitoring value <70 mg/dL, during exercise. Repeated measures random forest (RMRF) and repeated measures logistic regression (RMLR) models were constructed to predict hypoglycemia using predictors at the start of exercise and baseline characteristics. Models were evaluated with area under the receiver operating characteristic curve (AUC) and balanced accuracy. Results: RMRF and RMLR had similar AUC (0.833 vs. 0.825, respectively) and both models had a balanced accuracy of 77%. The probability of hypoglycemia was higher for exercise sessions with lower pre-exercise glucose levels, negative pre-exercise glucose rates of change, greater percent time <70 mg/dL in the 24 h before exercise, and greater pre-exercise bolus insulin-on-board (IOB). Free-living aerobic exercises, walking/hiking, and physical labor had the highest probability of hypoglycemia, while structured exercises had the lowest probability of hypoglycemia. Conclusions: RMRF and RMLR accurately predict hypoglycemia during exercise and identify factors that increase the risk of hypoglycemia. Lower glucose, decreasing levels of glucose before exercise, and greater pre-exercise IOB largely predict hypoglycemia risk in adults with T1D.

Integrating metabolic expenditure information from wearable fitness sensors into an AI-augmented automated insulin delivery system: a randomised clinical trial

BACKGROUND

Exercise can rapidly drop glucose in people with type 1 diabetes. Ubiquitous wearable fitness sensors are not integrated into automated insulin delivery (AID) systems. We hypothesised that an AID can automate insulin adjustments using real-time wearable fitness data to reduce hypoglycaemia during exercise and free-living conditions compared with an AID not automating use of fitness data.

METHODS

Our study population comprised of individuals (aged 21-50 years) with type 1 diabetes from from the Harold Schnitzer Diabetes Health Center clinic at Oregon Health and Science University, OR, USA, who were enrolled into a 76 h single-centre, two-arm randomised (4-block randomisation), non-blinded crossover study to use (1) an AID that detects exercise, prompts the user, and shuts off insulin during exercise using an exercise-aware adaptive proportional derivative (exAPD) algorithm or (2) an AID that automates insulin adjustments using fitness data in real-time through an exercise-aware model predictive control (exMPC) algorithm. Both algorithms ran on iPancreas comprising commercial glucose sensors, insulin pumps, and smartwatches. Participants executed 1 week run-in on usual therapy followed by exAPD or exMPC for one 12 h primary in-clinic session involving meals, exercise, and activities of daily living, and 2 free-living out-patient days. Primary outcome was time below range (<3·9 mmol/L) during the primary in-clinic session. Secondary outcome measures included mean glucose and time in range (3·9-10 mmol/L). This trial is registered with ClinicalTrials.gov, NCT04771403.

FINDINGS

Between April 13, 2021, and Oct 3, 2022, 27 participants (18 females) were enrolled into the study. There was no significant difference between exMPC (n=24) versus exAPD (n=22) in time below range (mean [SD] 1·3% [2·9] vs 2·5% [7·0]) or time in range (63·2% [23·9] vs 59·4% [23·1]) during the primary in-clinic session. In the 2 h period after start of in-clinic exercise, exMPC had significantly lower mean glucose (7·3 [1·6] vs 8·0 [1·7] mmol/L, p=0·023) and comparable time below range (1·4% [4·2] vs 4·9% [14·4]). Across the 76 h study, both algorithms achieved clinical time in range targets (71·2% [16] and 75·5% [11]) and time below range (1·0% [1·2] and 1·3% [2·2]), significantly lower than run-in period (2·4% [2·4], p=0·0004 vs exMPC; p=0·012 vs exAPD). No adverse events occurred.

INTERPRETATION

AIDs can integrate exercise data from smartwatches to inform insulin dosing and limit hypoglycaemia while improving glucose outcomes. Future AID systems that integrate exercise metrics from wearable fitness sensors may help people living with type 1 diabetes exercise safely by limiting hypoglycaemia.

FUNDING

JDRF Foundation and the Leona M and Harry B Helmsley Charitable Trust, National Institutes of Health, National Institute of Diabetes and Digestive and Kidney Diseases.

Reducing the Cost of Diabetes Care with Telemedicine, Smartphone, and Home Monitoring

The effect of an increasing diabetes population has resulted in escalated costs and overburdened physicians. The increase in cost is not due to the disease per se, but because of its largely preventable complications. Patient-friendly technologies are proven to significantly reduce complications and thereby cost, but seldom practised. Telemedicine is increasingly being utilized in diabetology to improve access to health care, quality of care, and clinical/psychosocial outcomes in patients with diabetes (PWD). In PWD, patient-physician interactions are essential for improving health outcomes and preventing long-term complications. Smartphones are one of the basic modalities for telemedicine application. Mobile phone messaging applications, including text messaging and multimedia message service, could offer a convenient and cost-effective way to support desirable health behaviors. There are diabetes-related mobile apps mainly focusing on self-management of diabetes, lifestyle modification, and medication adherence motivation. With the widespread availability of high-speed Internet, remote monitoring has also become popular. Home monitoring of blood glucose and blood pressure, wearable devices, and continuous glucose monitoring also play a vital role in bringing down the long‑term vascular complications of diabetes and thereby reduce the overall cost and improve the quality of life of patients. There are hundreds of tech platforms for diabetes management, of which only a few with proven efficacy and safety are recommended by physicians.

Enabling fully automated insulin delivery through meal detection and size estimation using Artificial Intelligence

We present a robust insulin delivery system that includes automated meal detection and carbohydrate content estimation using machine learning for meal insulin dosing called robust artificial pancreas (RAP). We conducted a randomized, single-center crossover trial to compare postprandial glucose control in the four hours following unannounced meals using a hybrid model predictive control (MPC) algorithm and the RAP system. The RAP system includes a neural network model to automatically detect meals and deliver a recommended meal insulin dose. The meal detection algorithm has a sensitivity of 83.3%, false discovery rate of 16.6%, and mean detection time of 25.9 minutes. While there is no significant difference in incremental area under the curve of glucose, RAP significantly reduces time above range (glucose >180 mg/dL) by 10.8% (P = 0.04) and trends toward increasing time in range (70-180 mg/dL) by 9.1% compared with MPC. Time below range (glucose <70 mg/dL) is not significantly different between RAP and MPC.

Modeling the effect of glucagon on endogenous glucose production in type 1 diabetes: On the role of glucagon receptor dynamics

This paper validates a glucoregulatory model including glucagon receptors dynamics in the description of endogenous glucose production (EGP). A set of models from literature are selected for a head-to-head comparison in order to evaluate the role of glucagon receptors. Each EGP model is incorporated into an existing glucoregulatory model and validated using a set of clinical data, where both insulin and glucagon are administered. The parameters of each EGP model are identified in the same optimization problem, minimizing the root mean square error (RMSE) between the simulation and the clinical data. The results show that the RMSE for the proposed receptors-based EGP model was lower when compared to each of the considered models (Receptors approach: 7.13±1.71 mg/dl vs. 7.76±1.45 mg/dl (p=0.066), 8.45±1.38 mg/dl (p=0.011) and 8.99±1.62 mg/dl (p=0.007)). This raises the possibility of considering glucagon receptors dynamics in type 1 diabetes simulators.

Non-invasive method for blood glucose monitoring using ECG signal

Introduction: Tight glucose monitoring is crucial for diabetic patients by using a Continuous Glucose Monitor (CGM). The existing CGMs measure the Blood Glucose Concentration (BGC) from the interstitial fluid. These technologies are quite expensive, and most of them are invasive. Previous studies have demonstrated that hypoglycemia and hyperglycemia episodes affect the electrophysiology of the heart. However, they did not determine a cohort relationship between BGC and ECG parameters.

Material and method: In this work, we propose a new method for determining the BGC using surface ECG signals. Recurrent Convolutional Neural Networks (RCNN) were applied to segment the ECG signals. Then, the extracted features were employed to determine the BGC using two mathematical equations. This method has been tested on 04 patients over multiple days from the D1namo dataset, using surface ECG signals instead of intracardiac signal.

Results: We were able to segment the ECG signals with an accuracy of 94% using the RCNN algorithm. According to the results, the proposed method was able to estimate the BGC with a Mean Absolute Error (MAE) of 0.0539, and a Mean Squared Error (MSE) of 0.1604. In addition, the linear relationship between BGC and ECG features has been confirmed in this paper.

Conclusion: In this paper, we propose the potential use of ECG features to determine the BGC. Additionally, we confirmed the linear relationship between BGC and ECG features. That fact will open new perspectives for further research, namely physiological models. Furthermore, the findings point to the possible application of ECG wearable devices for non-invasive continuous blood glucose monitoring via machine learning.

Design of a Real-Time Physical Activity Detection and Classification Framework for Individuals With Type 1 Diabetes

BACKGROUND

Managing glycemia during and after exercise events in type 1 diabetes (T1D) is challenging since these events can have wide-ranging effects on glycemia depending on the event timing, type, intensity. To this end, advanced physical activity-informed technologies can be beneficial for improving glucose control.

METHODS

We propose a real-time physical activity detection and classification framework, which builds upon random forest models. This module automatically detects exercise sessions and predicts the activity type and intensity from tri-axial accelerometer, heart rate, and continuous glucose monitoring records.

RESULTS

Data from 19 adults with T1D who performed structured sessions of either aerobic, resistance, or high-intensity interval exercise at varying times of day were used to train and test this framework. The exercise onset and completion were both predicted within 1 minute with an average accuracy of 81% and 78%, respectively. Activity type and intensity were identified within 2.38 minutes and from the exercise onset. On participants assigned to the test set, the average accuracy for activity type and intensity classification was 74% and 73%, respectively, if exercise was announced. For unannounced exercise events, the classification accuracy was 65% for the activity type and 70% for its intensity.

CONCLUSIONS

The proposed module showed high performance in detection and classification of exercise in real-time within a minute of exercise onset. Integration of this module into insulin therapy decisions can help facilitate glucose management around physical activity.

Machine Learning and Smart Devices for Diabetes Management: Systematic Review

(1) Background: The use of smart devices to better manage diabetes has increased significantly in recent years. These technologies have been introduced in order to make life easier for patients with diabetes by allowing better control of the stability of blood sugar levels and anticipating the occurrence of dangerous events (hypo/hyperglycemia), etc. That being said, the main objectives of the self-management of diabetes is to improve the lifestyle and life quality of patients with diabetes; (2) Methods: We performed a systematic review based on articles that focus on the use of smart devices for the monitoring and better management of diabetes. The search was focused on keywords related to the topic, such as “Diabetes”, “Technology”, “Self-management”, “Artificial Intelligence”, etc. This was performed using databases, such as Scopus, Google Scholar, and PubMed; (3) Results: A total of 89 studies, published between 2011 and 2021, were included. The majority of the selected research aims to solve a diabetes management problem (e.g., blood glucose prediction, early detection of risk events, and the automatic adjustment of insulin doses, etc.). In these studies, wearable devices were used in combination with artificial intelligence (AI) techniques; (4) Conclusions: Wearable devices have attracted a great deal of scientific interest in the field of healthcare for people with chronic conditions, such as diabetes. They are capable of assisting in the management of diabetes, as well as preventing complications associated with this condition. Furthermore, the usage of these devices has improved illness management and quality of life.

Integrating Multiple Inputs Into an Artificial Pancreas System: Narrative Literature Review

Background

Type 1 diabetes (T1D) is a chronic autoimmune disease in which a deficiency in insulin production impairs the glucose homeostasis of the body. Continuous subcutaneous infusion of insulin is a commonly used treatment method. Artificial pancreas systems (APS) use continuous glucose level monitoring and continuous subcutaneous infusion of insulin in a closed-loop mode incorporating a controller (or control algorithm). However, the operation of APS is challenging because of complexities arising during meals, exercise, stress, sleep, illnesses, glucose sensing and insulin action delays, and the cognitive burden. To overcome these challenges, options to augment APS through integration of additional inputs, creating multi-input APS (MAPS), are being investigated.

Objective

The aim of this survey is to identify and analyze input data, control architectures, and validation methods of MAPS to better understand the complexities and current state of such systems. This is expected to be valuable in developing improved systems to enhance the quality of life of people with T1D.

Methods

A literature survey was conducted using the Scopus, PubMed, and IEEE Xplore databases for the period January 1, 2005, to February 10, 2020. On the basis of the search criteria, 1092 articles were initially shortlisted, of which 11 (1.01%) were selected for an in-depth narrative analysis. In addition, 6 clinical studies associated with the selected studies were also analyzed.

Results

Signals such as heart rate, accelerometer readings, energy expenditure, and galvanic skin response captured by wearable devices were the most frequently used additional inputs. The use of invasive (blood or other body fluid analytes) inputs such as lactate and adrenaline were also simulated. These inputs were incorporated to switch the mode of the controller through activity detection, directly incorporated for decision-making and for the development of intermediate modules for the controller. The validation of the MAPS was carried out through the use of simulators based on different physiological models and clinical trials.

Conclusions

The integration of additional physiological signals with continuous glucose level monitoring has the potential to optimize glucose control in people with T1D through addressing the identified limitations of APS. Most of the identified additional inputs are related to wearable devices. The rapid growth in wearable technologies can be seen as a key motivator regarding MAPS. However, it is important to further evaluate the practical complexities and psychosocial aspects associated with such systems in real life.

Quantifying the impact of physical activity on future glucose trends using machine learning

Prevention of hypoglycemia (glucose <70 mg/dL) during aerobic exercise is a major challenge in type 1 diabetes. Providing predictions of glycemic changes during and following exercise can help people with type 1 diabetes avoid hypoglycemia. A unique dataset representing 320 days and 50,000 + time points of glycemic measurements was collected in adults with type 1 diabetes who participated in a 4-arm crossover study evaluating insulin-pump therapies, whereby each participant performed eight identically designed in-clinic exercise studies. We demonstrate that even under highly controlled conditions, there is considerable intra-participant and inter-participant variability in glucose outcomes during and following exercise. Participants with higher aerobic fitness exhibited significantly lower minimum glucose and steeper glucose declines during exercise. Adaptive, personalized machine learning (ML) algorithms were designed to predict exercise-related glucose changes. These algorithms achieved high accuracy in predicting the minimum glucose and hypoglycemia during and following exercise sessions, for all fitness levels.

Incorporating Glucose Variability into Glucose Forecasting Accuracy Assessment Using the New Glucose Variability Impact Index and the Prediction Consistency Index: An LSTM Case Example

BACKGROUND

In this work, we developed glucose forecasting algorithms trained and evaluated on a large dataset of free-living people with type 1 diabetes (T1D) using closed-loop (CL) and sensor-augmented pump (SAP) therapies; and we demonstrate how glucose variability impacts accuracy. We introduce the glucose variability impact index (GVII) and the glucose prediction consistency index (GPCI) to assess the accuracy of prediction algorithms.

METHODS

A long-short-term-memory (LSTM) neural network was designed to predict glucose up to 60 minutes in the future using continuous glucose measurements and insulin data collected from 175 people with T1D (41,318 days) and evaluated on 75 people (11,333 days) from the Tidepool Big Data Donation Dataset. LSTM was compared with two naïve forecasting algorithms as well as Ridge linear regression and a random forest using root-mean-square error (RMSE). Parkes error grid quantified clinical accuracy. Regression analysis was used to derive the GVII and GPCI.

RESULTS

The LSTM had highest accuracy and best GVII and GPCI. RMSE for CL was 19.8 ± 3.2 and 33.2 ± 5.4 mg/dL for 30- and 60-minute prediction horizons, respectively. RMSE for SAP was 19.6 ± 3.8 and 33.1 ± 7.3 mg/dL for 30- and 60-minute prediction horizons, respectively; 99.6% and 97.6% of predictions were within zones A+B of the Parkes error grid at 30- and 60-minute prediction horizons, respectively. Glucose variability was strongly correlated with RMSE (R≥0.64, P < 0.001); GVII and GPCI demonstrated a means to compare algorithms across datasets with different glucose variability.

CONCLUSIONS

The LSTM model was accurate on a large real-world free-living dataset. Glucose variability should be considered when assessing prediction accuracy using indices such as GVII and GPCI.

Establishing a Global Standard for Wearable Devices in Sport and Exercise Medicine: Perspectives from Academic and Industry Stakeholders

Millions of consumer sport and fitness wearables (CSFWs) are used worldwide, and millions of datapoints are generated by each device. Moreover, these numbers are rapidly growing, and they contain a heterogeneity of devices, data types, and contexts for data collection. Companies and consumers would benefit from guiding standards on device quality and data formats. To address this growing need, we convened a virtual panel of industry and academic stakeholders, and this manuscript summarizes the outcomes of the discussion. Our objectives were to identify (1) key facilitators of and barriers to participation by CSFW manufacturers in guiding standards and (2) stakeholder priorities. The venues were the Yale Center for Biomedical Data Science Digital Health Monthly Seminar Series (62 participants) and the New England Chapter of the American College of Sports Medicine Annual Meeting (59 participants). In the discussion, stakeholders outlined both facilitators of (e.g., commercial return on investment in device quality, lucrative research partnerships, and transparent and multilevel evaluation of device quality) and barriers (e.g., competitive advantage conflict, lack of flexibility in previously developed devices) to participation in guiding standards. There was general agreement to adopt Keadle et al.'s standard pathway for testing devices (i.e., benchtop, laboratory, field-based, implementation) without consensus on the prioritization of these steps. Overall, there was enthusiasm not to add prescriptive or regulatory steps, but instead create a networking hub that connects companies to consumers and researchers for flexible guidance navigating the heterogeneity, multi-tiered development, dynamicity, and nebulousness of the CSFW field.

Fault Tolerant Strategies for Automated Insulin Delivery Considering the Human Component: Current and Future Perspectives

Automated Insulin Delivery (AID) are systems developed for daily use by people with type 1 diabetes (T1D). To ensure the safety of users, it is essential to consider how the human factor affects the performance and safety of these devices. While there are numerous publications on hardware-related failures of AID systems, there are few studies on the human component of the system. From a control point of view, people with T1D using AID systems are at the same time the plant to be controlled and the plant operator. Therefore, users may induce faults in the controller, sensors, actuators, and the plant itself. Strategies to cope with the human interaction in AID systems are needed for further development of the technology. In this paper, we present an analysis of potential faults introduced by AID users when the system is under normal operation. This is followed by a review of current fault tolerant control (FTC) approaches to identify missing areas of research. The paper concludes with a discussion on future directions for the new generation of FTC AID systems.

A Hybrid Automata Approach for Monitoring the Patient in the Loop in Artificial Pancreas Systems

The use of automated insulin delivery systems has become a reality for people with type 1 diabetes (T1D), with several hybrid systems already on the market. One of the particularities of this technology is that the patient is in the loop. People with T1D are the plant to control and also a plant operator, because they may have to provide information to the control loop. The most immediate information provided by patients that affects performance and safety are the announcement of meals and exercise. Therefore, to ensure safety and performance, the human factor impact needs to be addressed by designing fault monitoring strategies. In this paper, a monitoring system is developed to diagnose potential patient modes and faults. The monitoring system is based on the residual generation of a bank of observers. To that aim, a linear parameter varying (LPV) polytopic representation of the system is adopted and a bank of Kalman filters is designed using linear matrix inequalities (LMI). The system uncertainty is propagated using a zonotopic-set representation, which allows determining confidence bounds for each of the observer outputs and residuals. For the detection of modes, a hybrid automaton model is generated and diagnosis is performed by interpreting the events and transitions within the automaton. The developed system is tested in simulation, showing the potential benefits of using the proposed approach for artificial pancreas systems.

Identification of Movements and Postures Using Wearable Sensors for Implementation in a Bi-Hormonal Artificial Pancreas System

BACKGROUND

Closed loop bi-hormonal artificial pancreas systems, such as the artificial pancreas (AP™) developed by Inreda Diabetic B.V., control blood glucose levels of type 1 diabetes mellitus patients via closed loop regulation. As the AP™ currently does not classify postures and movements to estimate metabolic energy consumption to correct hormone administration levels, considerable improvements to the system can be made. Therefore, this research aimed to investigate the possibility to use the current system to identify several postures and movements.

METHODS

seven healthy participants took part in an experiment where sequences of postures and movements were performed to train and assess a computationally sparing algorithm.

RESULTS

Using accelerometers, one on the hip and two on the abdomen, user-specific models achieved classification accuracies of 86.5% using only the hip sensor and 87.3% when including the abdomen sensors. With additional accelerometers on the sternum and upper leg for identification, 90.0% of the classified postures and movements were correct.

CONCLUSIONS

The current hardware configuration of the AP™ poses no limitation to the identification of postures and movements. If future research shows that identification can still be done accurately in a daily life setting, this algorithm may be an improvement for the AP™ to sense physical activity.

Dual-hormone artificial pancreas for management of type 1 diabetes: Recent progress and future directions

Over the last few years, technological advances have led to tremendous improvement in the management of type 1 diabetes (T1D). Artificial pancreas systems have been shown to improve glucose control compared with conventional insulin pump therapy. However, clinically significant hypoglycemic and hyperglycemic episodes still occur with the artificial pancreas. Postprandial glucose excursions and exercise-induced hypoglycemia represent major hurdles in improving glucose control and glucose variability in many patients with T1D. In this regard, dual-hormone artificial pancreas systems delivering other hormones in addition to insulin (glucagon or amylin) may better reproduce the physiology of the endocrine pancreas and have been suggested as an alternative tool to overcome these limitations in clinical practice. In addition, novel ultra-rapid-acting insulin analogs with a more physiological time-action profile are currently under investigation for use in artificial pancreas devices, aiming to address the unmet need for further improvements in postprandial glucose control. This review article aims to discuss the current progress and future outlook in the development of novel ultra-rapid insulin analogs and dual-hormone closed-loop systems, which offer the next steps to fully closing the loop in the artificial pancreas.

Activity detection and classification from wristband accelerometer data collected on people with type 1 diabetes in free-living conditions

This paper introduces methods to estimate aspects of physical activity and sedentary behavior from three-axis accelerometer data collected with a wrist-worn device at a sampling rate of 32 [Hz] on adults with type 1 diabetes (T1D) in free-living conditions. In particular, we present two methods able to detect and grade activity based on its intensity and individual fitness as sedentary, mild, moderate or vigorous, and a method that performs activity classification in a supervised learning framework to predict specific user behaviors. Population results for activity level grading show multi-class average accuracy of 99.99%, precision of 98.0 ± 2.2%, recall of 97.9 ± 3.5% and F1 score of 0.9 ± 0.0. As for the specific behavior prediction, our best performing classifier, gave population multi-class average accuracy of 92.43 ± 10.32%, precision of 92.94 ± 9.80%, recall of 92.20 ± 10.16% and F1 score of 92.56 ± 9.94%. Our investigation showed that physical activity and sedentary behavior can be detected, graded and classified with good accuracy and precision from three-axial accelerometer data collected in free-living conditions on people with T1D. This is particularly significant in the context of automated glucose control systems for diabetes, in that the methods we propose have the potential to inform changes in treatment parameters in response to the intensity of physical activity, allowing patients to meet their glycemic targets.

Physical Activity and Psychological Stress Detection and Assessment of Their Effects on Glucose Concentration Predictions in Diabetes Management

OBJECTIVE

Continuous glucose monitoring (CGM) enables prediction of the future glucose concentration (GC) trajectory for making informed diabetes management decisions. The glucose concentration values are affected by various physiological and metabolic variations, such as physical activity (PA) and acute psychological stress (APS), in addition to meals and insulin. In this work, we extend our adaptive glucose modeling framework to incorporate the effects of PA and APS on the GC predictions.

METHODS

A wristband conducive of use by free-living ambulatory people is used. The measured physiological variables are analyzed to generate new quantifiable input features for PA and APS. Machine learning techniques estimate the type and intensity of the PA and APS when they occur individually and concurrently. Variables quantifying the characteristics of both PA and APS are integrated as exogenous inputs in an adaptive system identification technique for enhancing the accuracy of GC predictions. Data from clinical experiments illustrate the improvement in GC prediction accuracy.

RESULTS

The average mean absolute error (MAE) of one-hour-ahead GC predictions with testing data decreases from 35.1 to 31.9 mg/dL (p-value = 0.01) with the inclusion of PA information, and it decreases from 16.9 to 14.2 mg/dL (p-value = 0.006) with the inclusion of PA and APS information.

CONCLUSION

The first-ever glucose prediction model is developed that incorporates measures of physical activity and acute psychological stress to improve GC prediction accuracy.

SIGNIFICANCE

Modeling the effects of physical activity and acute psychological stress on glucose concentration values will improve diabetes management and enable informed meal, activity and insulin dosing decisions.

Dual-Hormone Closed-Loop System Using a Liquid Stable Glucagon Formulation Versus Insulin-Only Closed-Loop System Compared With a Predictive Low Glucose Suspend System: An Open-Label, Outpatient, Single-Center, Crossover, Randomized Controlled Trial

OBJECTIVE

To assess the efficacy and feasibility of a dual-hormone (DH) closed-loop system with insulin and a novel liquid stable glucagon formulation compared with an insulin-only closed-loop system and a predictive low glucose suspend (PLGS) system.

RESEARCH DESIGN AND METHODS

In a 76-h, randomized, crossover, outpatient study, 23 participants with type 1 diabetes used three modes of the Oregon Artificial Pancreas system: 1) dual-hormone (DH) closed-loop control, 2) insulin-only single-hormone (SH) closed-loop control, and 3) PLGS system. The primary end point was percentage time in hypoglycemia (<70 mg/dL) from the start of in-clinic aerobic exercise (45 min at 60% VO_2max) to 4 h after.

RESULTS

DH reduced hypoglycemia compared with SH during and after exercise (DH 0.0% [interquartile range 0.0-4.2], SH 8.3% [0.0-12.5], P = 0.025). There was an increased time in hyperglycemia (>180 mg/dL) during and after exercise for DH versus SH (20.8% DH vs. 6.3% SH, P = 0.038). Mean glucose during the entire study duration was DH, 159.2; SH, 151.6; and PLGS, 163.6 mg/dL. Across the entire study duration, DH resulted in 7.5% more time in target range (70-180 mg/dL) compared with the PLGS system (71.0% vs. 63.4%, P = 0.044). For the entire study duration, DH had 28.2% time in hyperglycemia vs. 25.1% for SH (P = 0.044) and 34.7% for PLGS (P = 0.140). Four participants experienced nausea related to glucagon, leading three to withdraw from the study.

CONCLUSIONS

The glucagon formulation demonstrated feasibility in a closed-loop system. The DH system reduced hypoglycemia during and after exercise, with some increase in hyperglycemia.

A single-blind, randomised, crossover study to reduce hypoglycaemia risk during postprandial exercise with closed-loop insulin delivery in adults with type 1 diabetes: announced (with or without bolus reduction) vs unannounced exercise strategies

AIMS/HYPOTHESIS

For individuals living with type 1 diabetes, closed-loop insulin delivery improves glycaemic control. Nonetheless, maintenance of glycaemic control during exercise while a prandial insulin bolus remains active is a challenge even to closed-loop systems. We investigated the effect of exercise announcement on the efficacy of a closed-loop system, to reduce hypoglycaemia during postprandial exercise.

METHODS

A single-blind randomised, crossover open-label trial was carried out to compare three strategies applied to a closed-loop system at mealtime in preparation for exercise taken 90 min after eating at a research testing centre: (1) announced exercise to the closed-loop system (increases target glucose levels) in addition to a 33% reduction in meal bolus (A-RB); (2) announced exercise to the closed-loop system and a full meal bolus (A-FB); (3) unannounced exercise and a full meal bolus (U-FB). Participants performed 60 min of exercise at 60% [Formula: see text] 90 min after eating breakfast. The investigators were not blinded to the interventions. However, the participants were blinded to the sensor glucose readings and to the insulin infusion rates throughout the intervention visits.

RESULTS

The trial was completed by 37 adults with type 1 diabetes, all using insulin pumps: mean±SD, 40.0 ± 15.0 years of age, HbA_1c 57.1 ± 10.8 mmol/mol (7.3 ± 1.0%). Reported results were based on plasma glucose values. During exercise and the following 1 h recovery period, time spent in hypoglycaemia (<3.9 mmol/l; primary outcome) was reduced with A-RB (mean ± SD; 2.0 ± 6.2%) and A-FB (7.0 ± 12.6%) vs U-FB (13.0 ± 19.0%; p < 0.0001 and p = 0.005, respectively). During exercise, A-RB had the least drop in plasma glucose levels: A-RB -0.3 ± 2.8 mmol/l, A-FB -2.6 ± 2.9 mmol/l vs U-FB -2.4 ± 2.7 mmol/l (p < 0.0001 and p = 0.5, respectively). Comparison of A-RB vs U-FB revealed a decrease in the time spent in target (3.9-10 mmol/l) by 12.7% (p = 0.05) and an increase in the time spent in hyperglycaemia (>10 mmol/l) by 21% (p = 0.001). No side effects were reported during the applied strategies.

CONCLUSIONS/INTERPRETATION

Combining postprandial exercise announcement, which increases closed-loop system glucose target levels, with a 33% meal bolus reduction significantly reduced time spent in hypoglycaemia compared with the other two strategies, yet at the expense of more time spent in hyperglycaemia.

TRIAL REGISTRATION

ClinicalTrials.gov NCT0285530 FUNDING: JDRF (2-SRA-2016-210-A-N), the Canadian Institutes of Health Research (354024) and the Fondation J.-A. DeSève chair held by RR-L.

Data-Driven Robust Control for a Closed-Loop Artificial Pancreas

We present a fully closed-loop design for an artificial pancreas (AP) that regulates the delivery of insulin for the control of Type I diabetes. Our AP controller operates in a fully automated fashion, without requiring any manual interaction with the patient (e.g., in the form of meal announcements). A major obstacle to achieving closed-loop insulin control are the "unknown disturbances" related to various aspects of a patient's daily behavior, especially meals and physical activity. Such disturbances can significantly affect the patient's blood glucose levels. To handle such uncertainties, we present a data-driven, robust, model-predictive control framework in which we capture a wide range of individual meal and exercise patterns using uncertainty sets learned from historical data. These uncertainty sets are then used in the insulin controller to achieve automated, precise, and personalized insulin therapy. We provide an extensive in silico evaluation of our robust AP design, demonstrating the potential of the approach. In particular, without the benefit of explicit meal announcements, our approach can regulate glucose levels for large clusters of meal profiles learned from population-wide survey data and cohorts of virtual patients, even in the presence of high carbohydrate disturbances.

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

Algorithms that can determine the type of physical activity (PA) and quantify the intensity can allow precision medicine approaches, such as automated insulin delivery systems that modulate insulin administration in response to PA. In this work, data from a multi-sensor wristband is used to design classifiers to distinguish among five different physical states (PS) (resting, activities of daily living, running, biking, and resistance training), and to develop models to estimate the energy expenditure (EE) of the PA for diabetes therapy. The data collected are filtered, features are extracted from the reconciled signals, and the extracted features are used by machine learning algorithms, including deep-learning techniques, to obtain accurate PS classification and EE estimation. The various machine learning techniques have different success rates ranging from 75.7% to 94.8% in classifying the five different PS. The deep neural network model with long short-term memory has 94.8% classification accuracy. We achieved 0.5 MET (Metabolic Equivalent of Task) root-mean-square error for EE estimation accuracy, relative to indirect calorimetry with randomly selected testing data (10% of collected data). We also demonstrate a 5% improvement in PS classification accuracy and a 0.34 MET decrease in the mean absolute error when using multi-sensor approach relative to using only accelerometer data.

Review of the Omnipod® 5 Automated Glucose Control System Powered by Horizon™ for the treatment of Type 1 diabetes

Type 1 diabetes (T1D) is a medical condition that requires constant management, including monitoring of blood glucose levels and administration of insulin. Advancements in diabetes technology have offered methods to reduce the burden on people with T1D. Several hybrid closed-loop systems are commercially available or in clinical trials, each with unique features to improve care for patients with T1D. This article reviews the Omnipod® 5 Automated Glucose Control System Powered by Horizon™ and the safety and efficacy data to support its use in the management of T1D.

Where Do We Stand with Closed-Loop Systems and Their Challenges?

Treatments for type 1 diabetes have advanced significantly over recent years. There are now multiple hybrid closed-loop systems commercially available and additional systems are in development. Challenges remain, however. This review outlines the recent advances in closed-loop systems and outlines the remaining challenges, including post-prandial hyperglycemia and exercise-related dysglycemia.

Feasibility of the Energy Expenditure Prediction for Athletes and Non-Athletes from Ankle-Mounted Accelerometer and Heart Rate Monitor

Due to the nature of micro-electromechanical systems, the vector magnitude (VM) activity of accelerometers varies depending on the wearing position and does not identify different levels of physical fitness. Without an appropriate energy expenditure (EE) estimation equation, bias can occur in the estimated values. We aimed to amend the EE estimation equation using heart rate reserve (HRR) parameters as the correction factor, which could be applied to athletes and non-athletes who primarily use ankle-mounted devices. Indirect calorimetry was used as the criterion measure with an accelerometer (ankle-mounted) equipped with a heart rate monitor to synchronously measure the EE of 120 healthy adults on a treadmill in four groups. Compared with ankle-mounted accelerometer outputs, when the traditional equation was modified using linear regression by combining VM with body weight and/or HRR parameters (modified models: Model A, without HRR; Model B, with HRR), both Model A (r: 0.931 to 0.972; ICC: 0.913 to 0.954) and Model B (r: 0.933 to 0.975; ICC: 0.930 to 0.959) showed the valid and reliable predictive ability for the four groups. With respect to the simplest and most reasonable mode, Model A seems to be a good choice for predicting EE when using an ankle-mounted device.

Application of Artificial Intelligence in Diabetes Education and Management: Present Status and Promising Prospect

Despite the rapid development of science and technology in healthcare, diabetes remains an incurable lifelong illness. Diabetes education aiming to improve the self-management skills is an essential way to help patients enhance their metabolic control and quality of life. Artificial intelligence (AI) technologies have made significant progress in transforming available genetic data and clinical information into valuable knowledge. The application of AI tech in disease education would be extremely beneficial considering their advantages in promoting individualization and full-course education intervention according to the unique pictures of different individuals. This paper reviews and discusses the most recent applications of AI techniques to various aspects of diabetes education. With the information and evidence collected, this review attempts to provide insight and guidance for the development of prospective, data-driven decision support platforms for diabetes management, with a focus on individualized patient management and lifelong educational interventions.

Measuring glucose at the site of insulin delivery with a redox-mediated sensor

Automated insulin delivery systems for people with type 1 diabetes rely on an accurate subcutaneous glucose sensor and an infusion cannula that delivers insulin in response to measured glucose. Integrating the sensor with the infusion cannula would provide substantial benefit by reducing the number of devices inserted into subcutaneous tissue. We describe the sensor chemistry and a calibration algorithm to minimize impact of insulin delivery artifacts in a new glucose sensing cannula. Seven people with type 1 diabetes undergoing automated insulin delivery used two sensing cannulae whereby one delivered a rapidly-acting insulin analog and the other delivered a control phosphate buffered saline (PBS) solution with no insulin. While there was a small artifact in both conditions that increased for larger volumes, there was no difference between the artifacts in the sensing cannula delivering insulin compared with the sensing cannula delivering PBS as determined by integrating the area-under-the-curve of the sensor values following delivery of larger amounts of fluid (P = 0.7). The time for the sensor to recover from the artifact was found to be longer for larger fluid amounts compared with smaller fluid amounts (10.3 ± 8.5 min vs. 41.2 ± 78.3 s, P < 0.05). Using a smart-sampling Kalman filtering smoothing algorithm improved sensor accuracy. When using an all-point calibration on all sensors, the smart-sampling Kalman filter reduced the mean absolute relative difference from 10.9% to 9.5% and resulted in 96.7% of the data points falling within the A and B regions of the Clarke error grid. Despite a small artifact, which is likely due to dilution by fluid delivery, it is possible to continuously measure glucose in a cannula that simultaneously delivers insulin.

Role of Glucagon in Automated Insulin Delivery

Treatment of type 1 diabetes with exogenous insulin often results in unpredictable daily glucose variability and hypoglycemia, which can be dangerous. Automated insulin delivery systems can improve glucose control while reducing burden for people with diabetes. One approach to improve treatment outcomes is to incorporate the counter-regulatory hormone glucagon into the automated delivery system to help prevent the hypoglycemia that can be induced by the slow pharmacodynamics of insulin action. This article explores the advantages and disadvantages of incorporating glucagon into dual-hormone automated hormone delivery systems.

Diabetes Technology and Exercise

Advances in technologies such as glucose monitors, exercise wearables, closed-loop systems, and various smartphone applications are helping many people with diabetes to be more physically active. These technologies are designed to overcome the challenges associated with exercise duration, mode, relative intensity, and absolute intensity, all of which affect glucose homeostasis in people living with diabetes. At present, optimal use of these technologies depends largely on motivation, competence, and adherence to daily diabetes care requirements. This article discusses recent technologies designed to help patients with diabetes to be more physically active, while also trying to improve glucose control around exercise.

Carbohydrate Intake in the Context of Exercise in People with Type 1 Diabetes

Although the benefits of regular exercise on cardiovascular risk factors are well established for people with type 1 diabetes (T1D), glycemic control remains a challenge during exercise. Carbohydrate consumption to fuel the exercise bout and/or for hypoglycemia prevention is an important cornerstone to maintain performance and avoid hypoglycemia. The main strategies pertinent to carbohydrate supplementation in the context of exercise cover three aspects: the amount of carbohydrates ingested (i.e., quantity in relation to demands to fuel exercise and avoid hypoglycemia), the timing of the intake (before, during and after the exercise, as well as circadian factors), and the quality of the carbohydrates (encompassing differing carbohydrate types, as well as the context within a meal and the associated macronutrients). The aim of this review is to comprehensively summarize the literature on carbohydrate intake in the context of exercise in people with T1D.

Realizing a Closed-Loop (Artificial Pancreas) System for the Treatment of Type 1 Diabetes

Recent, rapid changes in the treatment of type 1 diabetes have allowed for commercialization of an "artificial pancreas" that is better described as a closed-loop controller of insulin delivery. This review presents the current state of closed-loop control systems and expected future developments with a discussion of the human factor issues in allowing automation of glucose control. The goal of these systems is to minimize or prevent both short-term and long-term complications from diabetes and to decrease the daily burden of managing diabetes. The closed-loop systems are generally very effective and safe at night, have allowed for improved sleep, and have decreased the burden of diabetes management overnight. However, there are still significant barriers to achieving excellent daytime glucose control while simultaneously decreasing the burden of daytime diabetes management. These systems use a subcutaneous continuous glucose sensor, an algorithm that accounts for the current glucose and rate of change of the glucose, and the amount of insulin that has already been delivered to safely deliver insulin to control hyperglycemia, while minimizing the risk of hypoglycemia. The future challenge will be to allow for full closed-loop control with minimal burden on the patient during the day, alleviating meal announcements, carbohydrate counting, alerts, and maintenance. The human factors involved with interfacing with a closed-loop system and allowing the system to take control of diabetes management are significant. It is important to find a balance between enthusiasm and realistic expectations and experiences with the closed-loop system.

Simulation Software for Assessment of Nonlinear and Adaptive Multivariable Control Algorithms: Glucose - Insulin Dynamics in Type 1 Diabetes

A simulator for testing automatic control algorithms for nonlinear systems with time-varying parameters, variable time delays, and uncertainties is developed. It is based on simulation of virtual patients with Type 1 diabetes (T1D). Nonlinear models are developed to describe glucose concentration (GC) variations based on user-defined scenarios for meal consumption, insulin administration, and physical activity. They compute GC values and physiological variables, such as heart rate, skin temperature, accelerometer, and energy expenditure, that are indicative of physical activities affecting GC dynamics. This is the first simulator designed for assessment of multivariable controllers that consider supplemental physiological variables in addition to GC measurements to improve glycemic control. Virtual patients are generated from distributions of identified model parameters using clinical data. The simulator will enable testing and evaluation of new control algorithms proposed for automated insulin delivery as well as various control algorithms for nonlinear systems with uncertainties, time-varying parameters and delays.

Adaptive Control of an Artificial Pancreas Using Model Identification, Adaptive Postprandial Insulin Delivery, and Heart Rate and Accelerometry as Control Inputs

BACKGROUND

People with type 1 diabetes (T1D) have varying sensitivities to insulin and also varying responses to meals and exercise. We introduce a new adaptive run-to-run model predictive control (MPC) algorithm that can be used to help people with T1D better manage their glucose levels using an artificial pancreas (AP). The algorithm adapts to individuals' different insulin sensitivities, glycemic response to meals, and adjustment during exercise as a continuous input during free-living conditions.

METHODS

A new insulin sensitivity adaptation (ISA) algorithm is presented that updates each patient's insulin sensitivity during nonmeal periods to reduce the error between the actual glucose levels and the process model. We further demonstrate how an adaptive learning postprandial hypoglycemia prevention algorithm (ALPHA) presented in the previous work can complement the ISA algorithm, and the algorithm can adapt in several days. We further show that if physical activity is incorporated as a continuous input (heart rate and accelerometry), performance is improved. The contribution of this work is the description of the ISA algorithm and the evaluation of how ISA, ALPHA, and incorporation of exercise metrics as a continuous input can impact glycemic control.

RESULTS

Incorporating ALPHA, ISA, and physical activity into the MPC improved glycemic outcome measures. The adaptive learning postprandial hypoglycemia prevention algorithm combined with ISA significantly reduced time spent in hypoglycemia by 71.7% and the total number of rescue carbs by 67.8% to 0.37% events/day/patient. Insulin sensitivity adaptation significantly reduced model-actual mismatch by 12.2% compared to an AP without ISA. Incorporating physical activity as a continuous input modestly improved time in the range 70 to 180 mg/dL during high physical activity days from 84.4% to 84.9% and reduced the percentage time in hypoglycemia by 23.8% from 2.1% to 1.6%.

CONCLUSION

Adapting postprandial insulin delivery, insulin sensitivity, and adapting to physical exercise in an MPC-based AP systems can improve glycemic outcomes.

Artificial Pancreas Systems and Physical Activity in Patients with Type 1 Diabetes: Challenges, Adopted Approaches, and Future Perspectives

Physical activity is important for patients living with type 1 diabetes (T1D) but limited by the challenges associated with physical activity induced glucose variability. Optimizing glycemic control without increasing the risk of hypoglycemia is still a hurdle despite many advances in insulin formulations, delivery methods, and continuous glucose monitoring systems. In this respect, the artificial pancreas (AP) system is a promising therapeutic option for a safer practice of physical activity in the context of T1D. It is important that healthcare professionals as well as patients acquire the necessary knowledge about how the AP system works, its limits, and how glucose control is regulated during physical activity. This review aims to examine the current state of knowledge on exercise-related glucose variations especially hypoglycemic risk in T1D and to discuss their effects on the use and development of AP systems. Though effective and highly promising, these systems warrant further research for an optimized use around exercise.

Closed loop control in adolescents and children during winter sports: Use of the Tandem Control-IQ AP system

OBJECTIVE

Artificial pancreas (AP) systems have been shown to improve glycemic control throughout the day and night in adults, adolescents, and children. However, AP testing remains limited during intense and prolonged exercise in adolescents and children. We present the performance of the Tandem Control-IQ AP system in adolescents and children during a winter ski camp study, where high altitude, low temperature, prolonged intense activity, and stress challenged glycemic control.

METHODS

In a randomized controlled trial, 24 adolescents (ages 13-18 years) and 24 school-aged children (6-12 years) with Type 1 diabetes (T1D) participated in a 48 hours ski camp (∼5 hours skiing/day) at three sites: Wintergreen, VA; Kirkwood, and Breckenridge, CO. Study participants were randomized 1:1 at each site. The control group used remote monitored sensor-augmented pump (RM-SAP), and the experimental group used the t: slim X2 with Control-IQ Technology AP system. All subjects were remotely monitored 24 hours per day by study staff.

RESULTS

The Control-IQ system improved percent time within range (70-180 mg/dL) over the entire camp duration: 66.4 ± 16.4 vs 53.9 ± 24.8%; P = .01 in both children and adolescents. The AP system was associated with a significantly lower average glucose based on continuous glucose monitor data: 161 ± 29.9 vs 176.8 ± 36.5 mg/dL; P = .023. There were no differences between groups for hypoglycemia exposure or carbohydrate interventions. There were no adverse events.

CONCLUSIONS

The use of the Control-IQ AP improved glycemic control and safely reduced exposure to hyperglycemia relative to RM-SAP in pediatric patients with T1D during prolonged intensive winter sport activities.

Prediction of Hypoglycemia During Aerobic Exercise in Adults With Type 1 Diabetes

BACKGROUND

Fear of exercise related hypoglycemia is a major reason why people with type 1 diabetes (T1D) do not exercise. There is no validated prediction algorithm that can predict hypoglycemia at the start of aerobic exercise.

METHODS

We have developed and evaluated two separate algorithms to predict hypoglycemia at the start of exercise. Model 1 is a decision tree and model 2 is a random forest model. Both models were trained using a meta-data set based on 154 observations of in-clinic aerobic exercise in 43 adults with T1D from 3 different studies that included participants using sensor augmented pump therapy, automated insulin delivery therapy, and automated insulin and glucagon therapy. Both models were validated using an entirely new validation data set with 90 exercise observations collected from 12 new adults with T1D.

RESULTS

Model 1 identified two critical features predictive of hypoglycemia during exercise: heart rate and glucose at the start of exercise. If heart rate was greater than 121 bpm during the first 5 min of exercise and glucose at the start of exercise was less than 182 mg/dL, it predicted hypoglycemia with 79.55% accuracy. Model 2 achieved a higher accuracy of 86.7% using additional features and higher complexity.

CONCLUSIONS

Models presented here can assist people with T1D to avoid exercise related hypoglycemia. The simple model 1 heuristic can be easily remembered (the 180/120 rule) and model 2 is more complex requiring computational resources, making it suitable for automated artificial pancreas or decision support systems.

Automated Insulin Delivery Algorithms

IN BRIEF Automated insulin delivery (AID; also known as artificial pancreas) has improved the regulation of blood glucose concentrations, reduced the frequency of hyperglycemic and hypoglycemic episodes, and improved the quality of life of people with diabetes and their families. Three different types of algorithms-proportional-integral-derivative control, model predictive control, and fuzzy-logic knowledge-based systems-have been used in AID control systems. This article will highlight the foundations of these algorithms and discuss their strengths and limitations. Multivariable artificial pancreas and dual-hormone (insulin and glucagon) systems will be introduced.

A statistical virtual patient population for the glucoregulatory system in type 1 diabetes with integrated exercise model

Purpose

We introduce two validated single (SH) and dual hormone (DH) mathematical models that represent an in-silico virtual patient population (VPP) for type 1 diabetes (T1D). The VPP can be used to evaluate automated insulin and glucagon delivery algorithms, so-called artificial pancreas (AP) algorithms that are currently being used to help people with T1D better manage their glucose levels. We present validation results comparing these virtual patients with true clinical patients undergoing AP control and demonstrate that the virtual patients behave similarly to people with T1D.

Methods

A single hormone virtual patient population (SH-VPP) was created that is comprised of eight differential equations that describe insulin kinetics, insulin dynamics and carbohydrate absorption. The parameters in this model that represent insulin sensitivity were statistically sampled from a normal distribution to create a population of virtual patients with different levels of insulin sensitivity. A dual hormone virtual patient population (DH-VPP) extended this SH-VPP by incorporating additional equations to represent glucagon kinetics and glucagon dynamics. The DH-VPP is comprised of thirteen differential equations and a parameter representing glucagon sensitivity, which was statistically sampled from a normal distribution to create virtual patients with different levels of glucagon sensitivity. We evaluated the SH-VPP and DH-VPP on a clinical data set of 20 people with T1D who participated in a 3.5-day outpatient AP study. Twenty virtual patients were matched with the 20 clinical patients by total daily insulin requirements and body weight. The identical meals given during the AP study were given to the virtual patients and the identical AP control algorithm that was used to control the glucose of the virtual patients was used on the clinical patients. We compared percent time in target range (70–180 mg/dL), time in hypoglycemia (<70 mg/dL) and time in hyperglycemia (>180 mg/dL) for both the virtual patients and the actual patients.

Results

The subjects in the SH-VPP performed similarly vs. the actual patients (time in range: 78.1 ± 5.1% vs. 74.3 ± 8.1%, p = 0.11; time in hypoglycemia: 3.4 ± 1.3% vs. 2.8 ± 1.7%, p = 0.23). The subjects in the DH-VPP also performed similarly vs. the actual patients (time in range: 75.6 ± 5.5% vs. 71.9 ± 10.9%, p = 0.13; time in hypoglycemia: 0.9 ± 0.8% vs. 1.3 ± 1%, p = 0.19). While the VPPs tended to over-estimate the time in range relative to actual patients, the difference was not statistically significant.

Conclusions

We have verified that a SH-VPP and a DH-VPP performed comparably with actual patients undergoing AP control using an identical control algorithm. The SH-VPP and DH-VPP may be used as a simulator for pre-evaluation of T1D control algorithms.

Improving Glucose Prediction Accuracy in Physically Active Adolescents With Type 1 Diabetes

BACKGROUND

Physical activity presents a significant challenge for glycemic control in individuals with type 1 diabetes. As accurate glycemic predictions are key to successful automated decision-making systems (eg, artificial pancreas, AP), the inclusion of additional physiological variables in the estimation of the metabolic state may improve the glucose prediction accuracy during exercise.

METHODS

Predictor-based subspace identification is applied to a dynamic glucose prediction model including heart rate measurements along with variables representing the carbohydrate consumption and insulin boluses. To demonstrate the improvement in prediction ability due to the additional heart rate variable, the performance of the proposed modeling technique is evaluated with (SID-HR) and without heart rate (SID-2) as an additional input using experimental data involving adolescents at ski camp. Furthermore, the performance of the proposed approach is compared to that of the metabolic state observer (MSO) model currently used in the University of Virginia AP algorithm.

RESULTS

The addition of heart rate in the subspace-based model (SID-HR) yields a statistically significant improvement in the root-mean-square error compared to the SID-2 model (P < .001) and the standard MSO (P < .001). Furthermore, the SID-HR model performed favorably in comparison to the SID-2 and MSO models after accounting for its increased complexity.

CONCLUSIONS

Directly considering the effects of physical activity levels on glycemic dynamics through the inclusion of heart rate as an additional input variable in the glucose dynamics model improves the glucose prediction accuracy. The proposed methodology could improve exercise-informed model-based predictive control algorithms in artificial pancreas systems.

A Century of Diabetes Technology: Signals, Models, and Artificial Pancreas Control

Arguably, diabetes mellitus is one of the best-quantified human conditions: elaborate in silico models describe the action of the human metabolic system; real-time signals such as continuous glucose monitoring are readily available; insulin delivery is being automated; and control algorithms are capable of optimizing blood glucose fluctuation in patients' natural environments. The transition of the artificial pancreas (AP) to everyday clinical use is happening now, and is contingent upon seamless concerted work of devices encompassing the patient in a digital treatment ecosystem. This review recounts briefly the story of diabetes technology, which began a century ago with the discovery of insulin, progressed through glucose monitoring and subcutaneous insulin delivery, and is now rapidly advancing towards fully automated clinically viable AP systems.

Detection and Control of Unannounced Exercise in the Artificial Pancreas Without Additional Physiological Signals

The purpose of this study was to develop an algorithm that detects aerobic exercise and triggers disturbance rejection actions to prevent exercise-induced hypoglycemia. This approach can provide a solution to poor glycemic control during and after aerobic exercise, a major hindrance in the participation of exercise by patients with type 1 diabetes. This novel exercise-induced hypoglycemia reduction algorithm (EHRA) detects exercise using a threshold on a disturbance term, a parameter estimated from an augmented minimal model using an unscented Kalman filter. After detection, the EHRA triggers the following three actions: First, a carbohydrate suggestion, second, a reduction in basal insulin and the insulin-on-board maximum limit, and finally, a 30% reduction of the next insulin meal bolus. The EHRA was tested in silico using a 15-day scenario with 8 exercise sessions of 50 min at [Formula: see text] on alternating days. The EHRA was able to obtain improved results when compared to strategies with and without exercise announcement. The unannounced, announced, and EHRA strategies all obtained an overall percentage of time in range (70-180 mg/dl) of 94% and a percentage of time 70 mg/dl of 2%, 0%, and 0%, respectively. The EHRA was tested for robustness during exercise sessions of +25% and -25% intensity and results suggest that the EHRA is able to account for variability in exercise intensity, duration, and patient dynamics such as glucose uptake rate and insulin sensitivity.

Accuracy of Wrist-Worn Activity Monitors During Common Daily Physical Activities and Types of Structured Exercise: Evaluation Study

BACKGROUND

Wrist-worn activity monitors are often used to monitor heart rate (HR) and energy expenditure (EE) in a variety of settings including more recently in medical applications. The use of real-time physiological signals to inform medical systems including drug delivery systems and decision support systems will depend on the accuracy of the signals being measured, including accuracy of HR and EE. Prior studies assessed accuracy of wearables only during steady-state aerobic exercise.

OBJECTIVE

The objective of this study was to validate the accuracy of both HR and EE for 2 common wrist-worn devices during a variety of dynamic activities that represent various physical activities associated with daily living including structured exercise.

METHODS

We assessed the accuracy of both HR and EE for two common wrist-worn devices (Fitbit Charge 2 and Garmin vívosmart HR+) during dynamic activities. Over a 2-day period, 20 healthy adults (age: mean 27.5 [SD 6.0] years; body mass index: mean 22.5 [SD 2.3] kg/m²; 11 females) performed a maximal oxygen uptake test, free-weight resistance circuit, interval training session, and activities of daily living. Validity was assessed using an HR chest strap (Polar) and portable indirect calorimetry (Cosmed). Accuracy of the commercial wearables versus research-grade standards was determined using Bland-Altman analysis, correlational analysis, and error bias.

RESULTS

Fitbit and Garmin were reasonably accurate at measuring HR but with an overall negative bias. There was more error observed during high-intensity activities when there was a lack of repetitive wrist motion and when the exercise mode indicator was not used. The Garmin estimated HR with a mean relative error (RE, %) of -3.3% (SD 16.7), whereas Fitbit estimated HR with an RE of -4.7% (SD 19.6) across all activities. The highest error was observed during high-intensity intervals on bike (Fitbit: -11.4% [SD 35.7]; Garmin: -14.3% [SD 20.5]) and lowest error during high-intensity intervals on treadmill (Fitbit: -1.7% [SD 11.5]; Garmin: -0.5% [SD 9.4]). Fitbit and Garmin EE estimates differed significantly, with Garmin having less negative bias (Fitbit: -19.3% [SD 28.9], Garmin: -1.6% [SD 30.6], P<.001) across all activities, and with both correlating poorly with indirect calorimetry measures.

CONCLUSIONS

Two common wrist-worn devices (Fitbit Charge 2 and Garmin vívosmart HR+) show good HR accuracy, with a small negative bias, and reasonable EE estimates during low to moderate-intensity exercise and during a variety of common daily activities and exercise. Accuracy was compromised markedly when the activity indicator was not used on the watch or when activities involving less wrist motion such as cycle ergometry were done.

Randomized Outpatient Trial of Single- and Dual-Hormone Closed-Loop Systems That Adapt to Exercise Using Wearable Sensors

OBJECTIVE

Automated insulin delivery is the new standard for type 1 diabetes, but exercise-related hypoglycemia remains a challenge. Our aim was to determine whether a dual-hormone closed-loop system using wearable sensors to detect exercise and adjust dosing to reduce exercise-related hypoglycemia would outperform other forms of closed-loop and open-loop therapy.

RESEARCH DESIGN AND METHODS

Participants underwent four arms in randomized order: dual-hormone, single-hormone, predictive low glucose suspend, and continuation of current care over 4 outpatient days. Each arm included three moderate-intensity aerobic exercise sessions. The two primary outcomes were percentage of time in hypoglycemia (<70 mg/dL) and in a target range (70-180 mg/dL) assessed across the entire study and from the start of the in-clinic exercise until the next meal.

RESULTS

The analysis included 20 adults with type 1 diabetes who completed all arms. The mean time (SD) in hypoglycemia was the lowest with dual-hormone during the exercise period: 3.4% (4.5) vs. 8.3% (12.6) single-hormone (P = 0.009) vs. 7.6% (8.0) predictive low glucose suspend (P < 0.001) vs. 4.3% (6.8) current care where pre-exercise insulin adjustments were allowed (P = 0.49). Time in hypoglycemia was also the lowest with dual-hormone during the entire 4-day study: 1.3% (1.0) vs. 2.8% (1.7) single-hormone (P < 0.001) vs. 2.0% (1.5) predictive low glucose suspend (P = 0.04) vs. 3.1% (3.2) current care (P = 0.007). Time in range during the entire study was the highest with single-hormone: 74.3% (8.0) vs. 72.0% (10.8) dual-hormone (P = 0.44).

CONCLUSIONS

The addition of glucagon delivery to a closed-loop system with automated exercise detection reduces hypoglycemia in physically active adults with type 1 diabetes.

Artificial Intelligence for Diabetes Management and Decision Support: Literature Review

Background

Artificial intelligence methods in combination with the latest technologies, including medical devices, mobile computing, and sensor technologies, have the potential to enable the creation and delivery of better management services to deal with chronic diseases. One of the most lethal and prevalent chronic diseases is diabetes mellitus, which is characterized by dysfunction of glucose homeostasis.

Objective

The objective of this paper is to review recent efforts to use artificial intelligence techniques to assist in the management of diabetes, along with the associated challenges.

Methods

A review of the literature was conducted using PubMed and related bibliographic resources. Analyses of the literature from 2010 to 2018 yielded 1849 pertinent articles, of which we selected 141 for detailed review.

Results

We propose a functional taxonomy for diabetes management and artificial intelligence. Additionally, a detailed analysis of each subject category was performed using related key outcomes. This approach revealed that the experiments and studies reviewed yielded encouraging results.

Conclusions

We obtained evidence of an acceleration of research activity aimed at developing artificial intelligence-powered tools for prediction and prevention of complications associated with diabetes. Our results indicate that artificial intelligence methods are being progressively established as suitable for use in clinical daily practice, as well as for the self-management of diabetes. Consequently, these methods provide powerful tools for improving patients’ quality of life.

The Benefits and Limits of Technological Advances in Glucose Management Around Physical Activity in Patients Type 1 Diabetes

Physical activity is highly recommended for patients living with type 1 diabetes (T1D) due to its varied health benefits. Nevertheless, glucose management, during and in the hours following exercise, represents a great challenge for these patients who most often end up leading a sedentary life style. Important technological advances in insulin delivery devices and glucose monitoring are now available and continue to progress. These technologies could be used to alleviate glucose management related to physical activity in T1D. Continuous glucose monitoring (CGM) helps patients observe the trends of glycemic fluctuations when exercising and in the following night to deal pre-emptively with hypoglycemic risks and treat hypoglycemic episodes in a timely manner. Insulin pumps offer the flexibility of adjusting insulin basal rates and boluses according to patient's specific needs around exercise. The artificial pancreas links CGM to pump through an intelligent hormone dosing algorithm to close the loop of glucose control and has thus the potential to ease the burden of exercise in T1D. This review will examine and discuss the literature related to physical activity practice using each of these technologies. The aim is to discuss their benefits as well as their limitations and finally the additional research needed in the future to optimize their use in T1D.