A Modular Safety System for an Insulin Dose Recommender: A Feasibility Study

A strategy based on integer programming for optimal dosing and timing of preventive hypoglycemic treatments in type 1 diabetes management

BACKGROUND AND OBJECTIVES

One of the major problems related to type 1 diabetes (T1D) management is hypoglycemia, a condition characterized by low blood glucose levels and responsible for reduced quality of life and increased mortality. Fast-acting carbohydrates, also known as hypoglycemic treatments (HT), can counteract this event. In the literature, dosage and timing of HT are usually based on heuristic rules. In the present work, we propose an algorithm for mitigating hypoglycemia by suggesting preventive HT consumption, with dosages and timing determined by solving an optimization problem.

METHODS

By leveraging integer programming and linear inequality constraints, the algorithm can bind the amount of suggested carbohydrates to standardized quantities (i.e., those available in "off-the-shelf" HT) and the minimal distance between consecutive suggestions (to reduce the nuisance for patients).

RESULTS

The proposed method was tested in silico and compared with competitor algorithms using the UVa/Padova T1D simulator. At the cost of a slight increase of HT consumed per day, the proposed algorithm produces the lowest median and interquartile range of the time spent in hypoglycemia, with a statistically significant improvement over most competitor algorithms. Also, the average number of hypoglycemic events per day is reduced to 0 in median.

CONCLUSIONS

Thanks to its positive performances and reduced computational burden, the proposed algorithm could be a candidate tool for integration in a DSS aimed at improving T1D management.

Offline Deep Reinforcement Learning and Off-Policy Evaluation for Personalized Basal Insulin Control in Type 1 Diabetes

Recent advancements in hybrid closed-loop systems, also known as the artificial pancreas (AP), have been shown to optimize glucose control and reduce the self-management burdens for people living with type 1 diabetes (T1D). AP systems can adjust the basal infusion rates of insulin pumps, facilitated by real-time communication with continuous glucose monitoring. Deep reinforcement learning (DRL) has introduced new paradigms of basal insulin control algorithms. However, all the existing DRL-based AP controllers require extensive random online interactions between the agent and environment. While this can be validated in T1D simulators, it becomes impractical in real-world clinical settings. To this end, we propose an offline DRL framework that can develop and validate models for basal insulin control entirely offline. It comprises a DRL model based on the twin delayed deep deterministic policy gradient and behavior cloning, as well as off-policy evaluation (OPE) using fitted Q evaluation. We evaluated the proposed framework on an in silico dataset generated by the UVA/Padova T1D simulator, and the OhioT1DM dataset, a real clinical dataset. The performance on the in silico dataset shows that the offline DRL algorithm significantly increased time in range while reducing time below range and time above range for both adult and adolescent groups. Then, we used the OPE to estimate model performance on the clinical dataset, where a notable increase in policy values was observed for each subject. The results demonstrate that the proposed framework is a viable and safe method for improving personalized basal insulin control in T1D.

Development and Validation of Binary Classifiers to Predict Nocturnal Hypoglycemia in Adults With Type 1 Diabetes

BACKGROUND

One of the biggest challenges for people with type 1 diabetes (T1D) using multiple daily injections (MDIs) is nocturnal hypoglycemia (NH). Recurrent NH can lead to serious complications; hence, prevention is of high importance. In this work, we develop and externally validate, device-agnostic Machine Learning (ML) models to provide bedtime decision support to people with T1D and minimize the risk of NH.

METHODS

We present the design and development of binary classifiers to predict NH (blood glucose levels occurring below 70 mg/dL). Using data collected from a 6-month study of 37 adult participants with T1D under free-living conditions, we extract daytime features from continuous glucose monitor (CGM) sensors, administered insulin, meal, and physical activity information. We use these features to train and test the performance of two ML algorithms: Random Forests (RF) and Support Vector Machines (SVMs). We further evaluate our model in an external population of 20 adults with T1D using MDI insulin therapy and wearing CGM and flash glucose monitoring sensors for two periods of eight weeks each.

RESULTS

At population-level, SVM outperforms RF algorithm with a receiver operating characteristic-area under curve (ROC-AUC) of 79.36% (95% CI: 76.86%, 81.86%). The proposed SVM model generalizes well in an unseen population (ROC-AUC = 77.06%), as well as between the two different glucose sensors (ROC-AUC = 77.74%).

CONCLUSIONS

Our model shows state-of-the-art performance, generalizability, and robustness in sensor devices from different manufacturers. We believe it is a potential viable approach to inform people with T1D about their risk of NH before it occurs.

Continuous glucose monitoring for children with hypoglycaemia: Evidence in 2023

In 2023, childhood hypoglycaemia remains a major public health problem and significant risk factor for consequent adverse neurodevelopment. Irrespective of the underlying cause, key elements of clinical management include the detection, prediction and prevention of episodes of hypoglycaemia. These tasks are increasingly served by Continuous Glucose Monitoring (CGM) devices that measure subcutaneous glucose at near-continuous frequency. While the use of CGM in type 1 diabetes is well established, the evidence for widespread use in rare hypoglycaemia disorders is less than convincing. However, in the few years since our last review there have been multiple developments and increased user feedback, requiring a review of clinical application. Despite advances in device technology, point accuracy of CGM remains low for children with non-diabetes hypoglycaemia. Simple provision of CGM devices has not replicated the efficacy seen in those with diabetes and is yet to show benefit. Machine learning techniques for hypoglycaemia prevention have so far failed to demonstrate sufficient prediction accuracy for real world use even in those with diabetes. Furthermore, access to CGM globally is restricted by costs kept high by the commercially-driven speed of technical innovation. Nonetheless, the ability of CGM to digitally phenotype disease groups has led to a better understanding of natural history of disease, facilitated diagnoses and informed changes in clinical management. Large CGM datasets have prompted re-evaluation of hypoglycaemia incidence and facilitated improved trial design. Importantly, an individualised approach and focus on the behavioural determinants of hypoglycaemia has led to real world reduction in hypoglycaemia. In this state of the art review, we critically analyse the updated evidence for use of CGM in non-diabetic childhood hypoglycaemia disorders since 2020 and provide suggestions for qualified use.

The behaviour change behind a successful pilot of hypoglycaemia reduction with HYPO-CHEAT

Background

Children with hypoglycaemia disorders, such as congenital hyperinsulinism (CHI), are at constant risk of hypoglycaemia (low blood sugars) with the attendant risk of brain injury. Current approaches to hypoglycaemia detection and prevention vary from fingerprick glucose testing to the provision of continuous glucose monitoring (CGM) to machine learning (ML) driven glucose forecasting. Recent trends for ML have had limited success in preventing free-living hypoglycaemia, due to a focus on increasingly accurate glucose forecasts and a failure to acknowledge the human in the loop and the essential step of changing behaviour. The wealth of evidence from the fields of behaviour change and persuasive technology (PT) allows for the creation of a theory-informed and technologically considered approach.

Objectives

We aimed to create a PT that would overcome the identified barriers to hypoglycaemia prevention for those with CHI to focus on proactive prevention rather than commonly used reactive approaches.

Methods

We used the behaviour change technique taxonomy and persuasive systems design models to create HYPO-CHEAT (HYpoglycaemia-Prevention-thrOugh-Cgm-HEatmap-Assisted-Technology): a novel approach that presents aggregated CGM data in simple visualisations. The resultant ease of data interpretation is intended to facilitate behaviour change and subsequently reduce hypoglycaemia.

Results

HYPO-CHEAT was piloted in 10 patients with CHI over 12 weeks and successfully identified weekly patterns of hypoglycaemia. These patterns consistently correlated with identifiable behaviours and were translated into both a change in proximal fingerprick behaviour and ultimately, a significant reduction in aggregated hypoglycaemia from 7.1% to 5.4% with four out of five patients showing clinically meaningful reductions in hypoglycaemia.

Conclusions

We have provided pilot data of a new approach to hypoglycaemia prevention that focuses on proactive prevention and behaviour change. This approach is personalised for individual patients with CHI and is a first step in changing our approach to hypoglycaemia prevention in this group.

HYPO-CHEAT's aggregated weekly visualisations of risk reduce real world hypoglycaemia

Background

Children with congenital hyperinsulinism (CHI) are at constant risk of hypoglycaemia with the attendant risk of brain injury. Current hypoglycaemia prevention methods centre on the prediction of a continuous glucose variable using machine learning (ML) processing of continuous glucose monitoring (CGM). This approach ignores repetitive and predictable behavioural factors and is dependent upon ongoing CGM. Thus, there has been very limited success in reducing real-world hypoglycaemia with a ML approach in any condition.

Objectives

We describe the development of HYPO-CHEAT (HYpoglycaemia-Prevention-thrOugh-CGM-HEatmap-Technology), which is designed to overcome these limitations by describing weekly hypoglycaemia risk. We tested HYPO-CHEAT in a real-world setting to evaluate change in hypoglycaemia.

Methods

HYPO-CHEAT aggregates individual CGM data to identify weekly hypoglycaemia patterns. These are visualised via a hypoglycaemia heatmap along with actionable interpretations and targets. The algorithm is iterative and reacts to anticipated changing patterns of hypoglycaemia. HYPO-CHEAT was compared with Dexcom Clarity's pattern identification and Facebook Prophet's forecasting algorithm using data from 10 children with CHI using CGM for 12 weeks. HYPO-CHEAT's efficacy was assessed via change in time below range (TBR).

Results

HYPO-CHEAT identified hypoglycaemia patterns in all patients. Dexcom Clarity identified no patterns. Predictions from Facebook Prophet were inconsistent and difficult to interpret. Importantly, the patterns identified by HYPO-CHEAT matched the lived experience of all patients, generating new and actionable understanding of the cause of hypos. This facilitated patients to significantly reduce their time in hypoglycaemia from 7.1% to 5.4% even when real-time CGM data was removed.

Conclusions

HYPO-CHEAT's personalised hypoglycaemia heatmaps reduced total and targeted TBR even when CGM was reblinded. HYPO-CHEAT offers a highly effective and immediately available personalised approach to prevent hypoglycaemia and empower patients to self-care.

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

People living with type 1 diabetes (T1D) require lifelong self-management to maintain glucose levels in a safe range. Failure to do so can lead to adverse glycemic events with short and long-term complications. Continuous glucose monitoring (CGM) is widely used in T1D self-management for real-time glucose measurements, while smartphone apps are adopted as basic electronic diaries, data visualization tools, and simple decision support tools for insulin dosing. Applying a mixed effects logistic regression analysis to the outcomes of a six-week longitudinal study in 12 T1D adults using CGM and a clinically validated wearable sensor wristband (NCT ID: NCT03643692), we identified several significant associations between physiological measurements and hypo- and hyperglycemic events measured an hour later. We proceeded to develop a new smartphone-based platform, ARISES (Adaptive, Real-time, and Intelligent System to Enhance Self-care), with an embedded deep learning algorithm utilizing multi-modal data from CGM, daily entries of meal and bolus insulin, and the sensor wristband to predict glucose levels and hypo- and hyperglycemia. For a 60-minute prediction horizon, the proposed algorithm achieved the average root mean square error (RMSE) of 35.28 ± 5.77 mg/dL with the Matthews correlation coefficients for detecting hypoglycemia and hyperglycemia of 0.56 ± 0.07 and 0.70 ± 0.05, respectively. The use of wristband data significantly reduced the RMSE by 2.25 mg/dL (p < 0.01). The well-trained model is implemented on the ARISES app to provide real-time decision support. These results indicate that the ARISES has great potential to mitigate the risk of severe complications and enhance self-management for people with T1D.

Optimizing the use of technology to support people with diabetes: research recommendations from Diabetes UK's 2019 diabetes and technology workshop

AIMS

To identify key gaps in the research evidence base that could help improve how technology supports people with diabetes, and provide recommendations to researchers and research funders on how best to address them.

METHODS

A research workshop was conducted, bringing together research experts in diabetes, research experts in technology, people living with diabetes and healthcare professionals.

RESULTS

The following key areas within this field were identified, and research recommendations for each were developed: Matching the pace of research with that of technology development Time in range as a measure Health inequalities and high-risk groups How to train people to use technology most effectively Impact of technology usage on mental health CONCLUSIONS: This position statement outlines recommendations through which research could improve how technology is employed to care for and support people living with diabetes, and calls on the research community and funders to address them in future research programmes and strategies.

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

People with Type 1 diabetes (T1D) require regular exogenous infusion of insulin to maintain their blood glucose concentration in a therapeutically adequate target range. Although the artificial pancreas and continuous glucose monitoring have been proven to be effective in achieving closed-loop control, significant challenges still remain due to the high complexity of glucose dynamics and limitations in the technology. In this work, we propose a novel deep reinforcement learning model for single-hormone (insulin) and dual-hormone (insulin and glucagon) delivery. In particular, the delivery strategies are developed by double Q-learning with dilated recurrent neural networks. For designing and testing purposes, the FDA-accepted UVA/Padova Type 1 simulator was employed. First, we performed long-term generalized training to obtain a population model. Then, this model was personalized with a small data-set of subject-specific data. In silico results show that the single and dual-hormone delivery strategies achieve good glucose control when compared to a standard basal-bolus therapy with low-glucose insulin suspension. Specifically, in the adult cohort (n = 10), percentage time in target range 70, 180 mg/dL improved from 77.6% to 80.9% with single-hormone control, and to 85.6% with dual-hormone control. In the adolescent cohort (n = 10), percentage time in target range improved from 55.5% to [Formula: see text] with single-hormone control, and to 78.8% with dual-hormone control. In all scenarios, a significant decrease in hypoglycemia was observed. These results show that the use of deep reinforcement learning is a viable approach for closed-loop glucose control in T1D.

Safety and Feasibility of the PEPPER Adaptive Bolus Advisor and Safety System: A Randomized Control Study

Background: The Patient Empowerment through Predictive Personalized Decision Support (PEPPER) system provides personalized bolus advice for people with type 1 diabetes. The system incorporates an adaptive insulin recommender system (based on case-based reasoning, an artificial intelligence methodology), coupled with a safety system, which includes predictive glucose alerts and alarms, predictive low-glucose suspend, personalized carbohydrate recommendations, and dynamic bolus insulin constraint. We evaluated the safety and efficacy of the PEPPER system compared to a standard bolus calculator. Methods: This was an open-labeled multicenter randomized controlled crossover study. Following 4-week run-in, participants were randomized to PEPPER/Control or Control/PEPPER in a 1:1 ratio for 12 weeks. Participants then crossed over after a washout period. The primary end-point was percentage time in range (TIR, 3.9-10.0 mmol/L [70-180 mg/dL]). Secondary outcomes included glycemic variability, quality of life, and outcomes on the safety system and insulin recommender. Results: Fifty-four participants on multiple daily injections (MDI) or insulin pump completed the run-in period, making up the intention-to-treat analysis. Median (interquartile range) age was 41.5 (32.3-49.8) years, diabetes duration 21.0 (11.5-26.0) years, and HbA1c 61.0 (58.0-66.1) mmol/mol. No significant difference was observed for percentage TIR between the PEPPER and Control groups (62.5 [52.1-67.8] % vs. 58.4 [49.6-64.3] %, respectively, P = 0.27). For quality of life, participants reported higher perceived hypoglycemia with the PEPPER system despite no objective difference in time spent in hypoglycemia. Conclusions: The PEPPER system was safe, but did not change glycemic outcomes, compared to control. There is wide scope for integrating PEPPER into routine diabetes management for pump and MDI users. Further studies are required to confirm overall effectiveness. Clinical trial registration: ClinicalTrials.gov NCT03849755.

An Insulin Bolus Advisor for Type 1 Diabetes Using Deep Reinforcement Learning

(1) Background: People living with type 1 diabetes (T1D) require self-management to maintain blood glucose (BG) levels in a therapeutic range through the delivery of exogenous insulin. However, due to the various variability, uncertainty and complex glucose dynamics, optimizing the doses of insulin delivery to minimize the risk of hyperglycemia and hypoglycemia is still an open problem. (2) Methods: In this work, we propose a novel insulin bolus advisor which uses deep reinforcement learning (DRL) and continuous glucose monitoring to optimize insulin dosing at mealtime. In particular, an actor-critic model based on deep deterministic policy gradient is designed to compute mealtime insulin doses. The proposed system architecture uses a two-step learning framework, in which a population model is first obtained and then personalized by subject-specific data. Prioritized memory replay is adopted to accelerate the training process in clinical practice. To validate the algorithm, we employ a customized version of the FDA-accepted UVA/Padova T1D simulator to perform in silico trials on 10 adult subjects and 10 adolescent subjects. (3) Results: Compared to a standard bolus calculator as the baseline, the DRL insulin bolus advisor significantly improved the average percentage time in target range (70-180 mg/dL) from 74.1%±8.4% to 80.9%±6.9% (p<0.01) and 54.9%±12.4% to 61.6%±14.1% (p<0.01) in the the adult and adolescent cohorts, respectively, while reducing hypoglycemia. (4) Conclusions: The proposed algorithm has the potential to improve mealtime bolus insulin delivery in people with T1D and is a feasible candidate for future clinical validation.

Artificial Intelligence in Decision Support Systems for Type 1 Diabetes

Type 1 diabetes (T1D) is a chronic health condition resulting from pancreatic beta cell dysfunction and insulin depletion. While automated insulin delivery systems are now available, many people choose to manage insulin delivery manually through insulin pumps or through multiple daily injections. Frequent insulin titrations are needed to adequately manage glucose, however, provider adjustments are typically made every several months. Recent automated decision support systems incorporate artificial intelligence algorithms to deliver personalized recommendations regarding insulin doses and daily behaviors. This paper presents a comprehensive review of computational and artificial intelligence-based decision support systems to manage T1D. Articles were obtained from PubMed, IEEE Xplore, and ScienceDirect databases. No time period restrictions were imposed on the search. After removing off-topic articles and duplicates, 562 articles were left to review. Of those articles, we identified 61 articles for comprehensive review based on algorithm evaluation using real-world human data, in silico trials, or clinical studies. We grouped decision support systems into general categories of (1) those which recommend adjustments to insulin and (2) those which predict and help avoid hypoglycemia. We review the artificial intelligence methods used for each type of decision support system, and discuss the performance and potential applications of these systems.

The Bio-inspired Artificial Pancreas for Type 1 Diabetes Control in the Home: System Architecture and Preliminary Results

BACKGROUND

Artificial pancreas (AP) technology has been proven to improve glucose and patient-centered outcomes for people with type 1 diabetes (T1D). Several approaches to implement the AP have been described, clinically evaluated, and in one case, commercialized. However, none of these approaches has shown a clear superiority with respect to others. In addition, several challenges still need to be solved before achieving a fully automated AP that fulfills the users' expectations. We have introduced the Bio-inspired Artificial Pancreas (BiAP), a hybrid adaptive closed-loop control system based on beta-cell physiology and implemented directly in hardware to provide an embedded low-power solution in a dedicated handheld device. In coordination with the closed-loop controller, the BiAP system incorporates a novel adaptive bolus calculator which aims at improving postprandial glycemic control. This paper focuses on the latest developments of the BiAP system for its utilization in the home environment.

METHODS

The hardware and software architectures of the BiAP system designed to be used in the home environment are described. Then, the clinical trial design proposed to evaluate the BiAP system in an ambulatory setting is introduced. Finally, preliminary results corresponding to two participants enrolled in the trial are presented.

RESULTS

Apart from minor technical issues, mainly due to wireless communications between devices, the BiAP system performed well (~88% of the time in closed-loop) during the clinical trials conducted so far. Preliminary results show that the BiAP system might achieve comparable glycemic outcomes to the existing AP systems (~73% time in target range 70-180 mg/dL).

CONCLUSION

The BiAP system is a viable platform to conduct ambulatory clinical trials and a potential solution for people with T1D to control their glucose control in a home environment.

Long-Term Glucose Forecasting Using a Physiological Model and Deconvolution of the Continuous Glucose Monitoring Signal

(1) Objective: Blood glucose forecasting in type 1 diabetes (T1D) management is a maturing field with numerous algorithms being published and a few of them having reached the commercialisation stage. However, accurate long-term glucose predictions (e.g., >60 min), which are usually needed in applications such as precision insulin dosing (e.g., an artificial pancreas), still remain a challenge. In this paper, we present a novel glucose forecasting algorithm that is well-suited for long-term prediction horizons. The proposed algorithm is currently being used as the core component of a modular safety system for an insulin dose recommender developed within the EU-funded PEPPER (Patient Empowerment through Predictive PERsonalised decision support) project. (2) Methods: The proposed blood glucose forecasting algorithm is based on a compartmental composite model of glucose-insulin dynamics, which uses a deconvolution technique applied to the continuous glucose monitoring (CGM) signal for state estimation. In addition to commonly employed inputs by glucose forecasting methods (i.e., CGM data, insulin, carbohydrates), the proposed algorithm allows the optional input of meal absorption information to enhance prediction accuracy. Clinical data corresponding to 10 adult subjects with T1D were used for evaluation purposes. In addition, in silico data obtained with a modified version of the UVa-Padova simulator was used to further evaluate the impact of accounting for meal absorption information on prediction accuracy. Finally, a comparison with two well-established glucose forecasting algorithms, the autoregressive exogenous (ARX) model and the latent variable-based statistical (LVX) model, was carried out. (3) Results: For prediction horizons beyond 60 min, the performance of the proposed physiological model-based (PM) algorithm is superior to that of the LVX and ARX algorithms. When comparing the performance of PM against the secondly ranked method (ARX) on a 120 min prediction horizon, the percentage improvement on prediction accuracy measured with the root mean square error, A-region of error grid analysis (EGA), and hypoglycaemia prediction calculated by the Matthews correlation coefficient, was 18.8 % , 17.9 % , and 80.9 % , respectively. Although showing a trend towards improvement, the addition of meal absorption information did not provide clinically significant improvements. (4) Conclusion: The proposed glucose forecasting algorithm is potentially well-suited for T1D management applications which require long-term glucose predictions.