Continuous Glucose Monitoring Enables the Detection of Losses in Infusion Set Actuation (LISAs)

Supervised and Unsupervised Approaches for the Real-Time Detection of Undesired Insulin Suspension Caused by Malfunctions

BACKGROUND

Automated insulin delivery (AID) systems, permit improved treatment of type 1 diabetes (T1D). Unfortunately, malfunctioning in the insulin pump or in the infusion set can prevent insulin from being administered, reducing the AID efficacy and posing the patient at risk. Different data-driven methods available in the literature can be used to deal with the problem of automatically detecting complete insulin suspension in real-time. This article investigates both supervised and unsupervised strategies and proposes a fair comparison under either population or personalized settings.

METHODS

Several algorithms are compared using data generated through the UVA/Padova T1D simulator, a computer simulator widely used to test control strategies in silico and accepted by the Food and Drugs Administration (FDA) as a substitute to animal pre-clinical trials. Two synthetic data sets, each consisting of 100 virtual subjects monitored for 1 month, were generated. Occasional faults of the insulin pump are simulated as complete occlusions by suspending the therapy administration. Personalized algorithms are investigated with unsupervised approaches only, since personalized labels are hardly available.

RESULTS

In the population scenario, the supervised approach outperforms the unsupervised strategy. In particular, logistic regression and random forest achieves a recall of 72% and 82%, with 0.12 and 0.21 false positives (FP) per day, respectively. In the personalized setting scenario, the unsupervised algorithms are tailored on each patient and outperform the population ones, in particular isolation forest achieves a recall 80% and 0.06 FPs per day.

CONCLUSIONS

This article suggests that unsupervised personalized approach, by addressing the large variability in glucose response among individuals with T1D, is superior to other one-fits-all approaches in detecting insulin suspensions caused by malfunctioning. Population methodologies can be effectively used while waiting to collect sufficient patient data, when the system is installed on a new patient.

Machine Learning-Based Anomaly Detection Algorithms to Alert Patients Using Sensor Augmented Pump of Infusion Site Failures

BACKGROUND

Personal insulin pumps have shown to be effective in improving the quality of therapy for people with type 1 diabetes (T1D). However, the safety of this technology is limited by the possible infusion site failures, which are linked with hyperglycemia and ketoacidosis. Thanks to the large availability of collected data provided by modern therapeutic technologies, machine learning algorithms have the potential to provide new way to identify failures early and avert adverse events.

METHODS

A clinical dataset (N = 20) is used to evaluate a novel method for detecting real-time infusion site failures using unsupervised anomaly detection algorithms, previously proposed and developed on in-silico data. An adapted feature engineering procedure is introduced to make the method able to operate in the absence of a closed-loop (CL) system and meal announcements.

RESULTS

In the optimal configuration, we obtained a performance of 0.75 Sensitivity (15 out of 20 total failures detected) and 0.08 FP/day, outperforming previously proposed literature algorithms. The algorithm was able to anticipate the replacement of the malfunctioning infusion sets by ~2 h on average.

CONCLUSIONS

On the considered dataset, the proposed algorithm showed the potential to improve the safety of patients treated with sensor-augmented pump systems.

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.

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.

Detection of Insulin Pump Malfunctioning to Improve Safety in Artificial Pancreas Using Unsupervised Algorithms

BACKGROUND

Recent development of automated closed-loop (CL) insulin delivery systems, the so-called artificial pancreas (AP), improved the quality of type 1 diabetes (T1D) therapy. As new technologies emerge, patients put increasing trust in their therapeutic devices; therefore, it becomes increasingly important to detect malfunctioning affecting such devices. In this work, we explore a new paradigm to detect insulin pump faults (IPFs) that use unsupervised anomaly detection.

METHODS

We generated CL data corrupted with IPFs using the latest version of the T1D Padova/UVA simulator. From the data, we extracted several features capable to describe the patient dynamics and making more apparent suspicious data portions. Then, a feature selection is performed to determine the optimal feature set. Finally, the performance of several popular unsupervised anomaly detection algorithms is analyzed and compared on the identified optimal feature set.

RESULTS

Using the identified optimal configuration, the best performance is obtained by the Histogram-Based Outlier Score (HBOS) algorithm, which detected 87% of the IPF with only 0.08 false positives per day on average. Isolation forest is the best algorithm that offers more conservative performances, detection of 85% of the faults but only 0.06 false positives per day on average.

CONCLUSION

Unsupervised anomaly detection algorithms can be used effectively to detect IPFs and improve the safety of the AP. Future studies will be dedicated to test the presented method inside dedicated clinical trials.

Enabling the Internet of Mobile Crowdsourcing Health Things: A Mobile Fog Computing, Blockchain and IoT Based Continuous Glucose Monitoring System for Diabetes Mellitus Research and Care

Diabetes patients suffer from abnormal blood glucose levels, which can cause diverse health disorders that affect their kidneys, heart and vision. Due to these conditions, diabetes patients have traditionally checked blood glucose levels through Self-Monitoring of Blood Glucose (SMBG) techniques, like pricking their fingers multiple times per day. Such techniques involve a number of drawbacks that can be solved by using a device called Continuous Glucose Monitor (CGM), which can measure blood glucose levels continuously throughout the day without having to prick the patient when carrying out every measurement. This article details the design and implementation of a system that enhances commercial CGMs by adding Internet of Things (IoT) capabilities to them that allow for monitoring patients remotely and, thus, warning them about potentially dangerous situations. The proposed system makes use of smartphones to collect blood glucose values from CGMs and then sends them either to a remote cloud or to distributed fog computing nodes. Moreover, in order to exchange reliable, trustworthy and cybersecure data with medical scientists, doctors and caretakers, the system includes the deployment of a decentralized storage system that receives, processes and stores the collected data. Furthermore, in order to motivate users to add new data to the system, an incentive system based on a digital cryptocurrency named GlucoCoin was devised. Such a system makes use of a blockchain that is able to execute smart contracts in order to automate CGM sensor purchases or to reward the users that contribute to the system by providing their own data. Thanks to all the previously mentioned technologies, the proposed system enables patient data crowdsourcing and the development of novel mobile health (mHealth) applications for diagnosing, monitoring, studying and taking public health actions that can help to advance in the control of the disease and raise global awareness on the increasing prevalence of diabetes.

Classification of Postprandial Glycemic Status with Application to Insulin Dosing in Type 1 Diabetes-An In Silico Proof-of-Concept

In the daily management of type 1 diabetes (T1D), determining the correct insulin dose to be injected at meal-time is fundamental to achieve optimal glycemic control. Wearable sensors, such as continuous glucose monitoring (CGM) devices, are instrumental to achieve this purpose. In this paper, we show how CGM data, together with commonly recorded inputs (carbohydrate intake and bolus insulin), can be used to develop an algorithm that allows classifying, at meal-time, the post-prandial glycemic status (i.e., blood glucose concentration being too low, too high, or within target range). Such an outcome can then be used to improve the efficacy of insulin therapy by reducing or increasing the corresponding meal bolus dose. A state-of-the-art T1D simulation environment, including intraday variability and a behavioral model, was used to generate a rich in silico dataset corresponding to 100 subjects over a two-month scenario. Then, an extreme gradient-boosted tree (XGB) algorithm was employed to classify the post-prandial glycemic status. Finally, we demonstrate how the XGB algorithm outcome can be exploited to improve glycemic control in T1D through real-time adjustment of the meal insulin bolus. The proposed XGB algorithm obtained good accuracy at classifying post-prandial glycemic status (AUROC = 0.84 [0.78, 0.87]). Consequently, when used to adjust, in real-time, meal insulin boluses obtained with a bolus calculator, the proposed approach improves glycemic control when compared to the baseline bolus calculator. In particular, percentage time in target [70, 180] mg/dL was improved from 61.98 (±13.89) to 67.00 (±11.54; p < 0.01) without increasing hypoglycemia.

Real-Time Detection of Infusion Site Failures in a Closed-Loop Artificial Pancreas

BACKGROUND

As evidence emerges that artificial pancreas systems improve clinical outcomes for patients with type 1 diabetes, the burden of this disease will hopefully begin to be alleviated for many patients and caregivers. However, reliance on automated insulin delivery potentially means patients will be slower to act when devices stop functioning appropriately. One such scenario involves an insulin infusion site failure, where the insulin that is recorded as delivered fails to affect the patient's glucose as expected. Alerting patients to these events in real time would potentially reduce hyperglycemia and ketosis associated with infusion site failures.

METHODS

An infusion site failure detection algorithm was deployed in a randomized crossover study with artificial pancreas and sensor-augmented pump arms in an outpatient setting. Each arm lasted two weeks. Nineteen participants wore infusion sets for up to 7 days. Clinicians contacted patients to confirm infusion site failures detected by the algorithm and instructed on set replacement if failure was confirmed.

RESULTS

In real time and under zone model predictive control, the infusion site failure detection algorithm achieved a sensitivity of 88.0% (n = 25) while issuing only 0.22 false positives per day, compared with a sensitivity of 73.3% (n = 15) and 0.27 false positives per day in the SAP arm (as indicated by retrospective analysis). No association between intervention strategy and duration of infusion sets was observed ( P = .58).

CONCLUSIONS

As patient burden is reduced by each generation of advanced diabetes technology, fault detection algorithms will help ensure that patients are alerted when they need to manually intervene. Clinical Trial Identifier: www.clinicaltrials.gov,NCT02773875.

Application of Zone Model Predictive Control Artificial Pancreas During Extended Use of Infusion Set and Sensor: A Randomized Crossover-Controlled Home-Use Trial

OBJECTIVE

As artificial pancreas (AP) becomes standard of care, consideration of extended use of insulin infusion sets (IIS) and continuous glucose monitors (CGMs) becomes vital. We conducted an outpatient randomized crossover study to test the safety and efficacy of a zone model predictive control (zone-MPC)-based AP system versus sensor augmented pump (SAP) therapy in which IIS and CGM failures were provoked via extended wear to 7 and 21 days, respectively.

RESEARCH DESIGN AND METHODS

A smartphone-based AP system was used by 19 adults (median age 23 years [IQR 10], mean 8.0 ± 1.7% HbA_1c) over 2 weeks and compared with SAP therapy for 2 weeks in a crossover, unblinded outpatient study with remote monitoring in both study arms.

RESULTS

AP improved percent time 70-140 mg/dL (48.1 vs. 39.2%; P = 0.016) and time 70-180 mg/dL (71.6 vs. 65.2%; P = 0.008) and decreased median glucose (141 vs. 153 mg/dL; P = 0.036) and glycemic variability (SD 52 vs. 55 mg/dL; P = 0.044) while decreasing percent time <70 mg/dL (1.3 vs. 2.7%; P = 0.001). AP also improved overnight control, as measured by mean glucose at 0600 h (140 vs. 158 mg/dL; P = 0.02). IIS failures (1.26 ± 1.44 vs. 0.78 ± 0.78 events; P = 0.13) and sensor failures (0.84 ± 0.6 vs. 1.1 ± 0.73 events; P = 0.25) were similar between AP and SAP arms. Higher percent time in closed loop was associated with better glycemic outcomes.

CONCLUSIONS

Zone-MPC significantly and safely improved glycemic control in a home-use environment despite prolonged CGM and IIS wear. This project represents the first home-use AP study attempting to provoke and detect component failure while successfully maintaining safety and effective glucose control.