Hypoglycemia Prevention via Personalized Glucose-Insulin Models Identified in Free-Living Conditions

Integration of a Safety Module to Prevent Rebound Hypoglycemia in Closed-Loop Artificial Pancreas Systems

BACKGROUND

With automated insulin delivery (AID) systems becoming widely adopted in the management of type 1 diabetes, we have seen an increase in occurrences of rebound hypoglycemia or generated hypoglycemia induced by the controller's response to rapid glucose rises following rescue carbohydrates. Furthermore, as AID systems aim to enable complete automation of prandial control, algorithms are designed to react even more strongly to glycemic rises. This work introduces a rebound hypoglycemia prevention layer (HypoSafe) that can be easily integrated into any AID system.

METHODS

HypoSafe constrains the maximum permissible insulin delivery dose based on the minimum glucose reading from the previous hour and the current glucose level. To demonstrate its efficacy, we integrated HypoSafe into the latest University of Virginia (UVA) AID system and simulated two scenarios using the 100-adult cohort of the UVA/Padova T1D simulator: a nominal case including three unannounced meals, and another case where hypoglycemia was purposely induced by an overestimated manual bolus.

RESULTS

In both simulation scenarios, rebound hypoglycemia events were reduced with HypoSafe (nominal: from 39 to 0, hypo-induced: from 55 to 7) by attenuating the commanded basal (nominal: 0.27U vs. 0.04U, hypo-induced: 0.27U vs. 0.03U) and bolus (nominal: 1.02U vs. 0.05U, hypo-induced: 0.43U vs. 0.02U) within the 30-minute interval after treating a hypoglycemia event. No clinically significant changes resulted for time in the range of 70 to 180 mg/dL or above 180 mg/dL.

CONCLUSION

HypoSafe was shown to be effective in reducing rebound hypoglycemia events without affecting achieved time in range when combined with an advanced AID system.

Machine Learning Models for Blood Glucose Level Prediction in Patients With Diabetes Mellitus: Systematic Review and Network Meta-Analysis

BACKGROUND

Machine learning (ML) models provide more choices to patients with diabetes mellitus (DM) to more properly manage blood glucose (BG) levels. However, because of numerous types of ML algorithms, choosing an appropriate model is vitally important.

OBJECTIVE

In a systematic review and network meta-analysis, this study aimed to comprehensively assess the performance of ML models in predicting BG levels. In addition, we assessed ML models used to detect and predict adverse BG (hypoglycemia) events by calculating pooled estimates of sensitivity and specificity.

METHODS

PubMed, Embase, Web of Science, and Institute of Electrical and Electronics Engineers Explore databases were systematically searched for studies on predicting BG levels and predicting or detecting adverse BG events using ML models, from inception to November 2022. Studies that assessed the performance of different ML models in predicting or detecting BG levels or adverse BG events of patients with DM were included. Studies with no derivation or performance metrics of ML models were excluded. The Quality Assessment of Diagnostic Accuracy Studies tool was applied to assess the quality of included studies. Primary outcomes were the relative ranking of ML models for predicting BG levels in different prediction horizons (PHs) and pooled estimates of the sensitivity and specificity of ML models in detecting or predicting adverse BG events.

RESULTS

In total, 46 eligible studies were included for meta-analysis. Regarding ML models for predicting BG levels, the means of the absolute root mean square error (RMSE) in a PH of 15, 30, 45, and 60 minutes were 18.88 (SD 19.71), 21.40 (SD 12.56), 21.27 (SD 5.17), and 30.01 (SD 7.23) mg/dL, respectively. The neural network model (NNM) showed the highest relative performance in different PHs. Furthermore, the pooled estimates of the positive likelihood ratio and the negative likelihood ratio of ML models were 8.3 (95% CI 5.7-12.0) and 0.31 (95% CI 0.22-0.44), respectively, for predicting hypoglycemia and 2.4 (95% CI 1.6-3.7) and 0.37 (95% CI 0.29-0.46), respectively, for detecting hypoglycemia.

CONCLUSIONS

Statistically significant high heterogeneity was detected in all subgroups, with different sources of heterogeneity. For predicting precise BG levels, the RMSE increases with a rise in the PH, and the NNM shows the highest relative performance among all the ML models. Meanwhile, current ML models have sufficient ability to predict adverse BG events, while their ability to detect adverse BG events needs to be enhanced.

TRIAL REGISTRATION

PROSPERO CRD42022375250; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=375250.

The Diabits App for Smartphone-Assisted Predictive Monitoring of Glycemia in Patients With Diabetes: Retrospective Observational Study

BACKGROUND

Diabetes mellitus, which causes dysregulation of blood glucose in humans, is a major public health challenge. Patients with diabetes must monitor their glycemic levels to keep them in a healthy range. This task is made easier by using continuous glucose monitoring (CGM) devices and relaying their output to smartphone apps, thus providing users with real-time information on their glycemic fluctuations and possibly predicting future trends.

OBJECTIVE

This study aims to discuss various challenges of predictive monitoring of glycemia and examines the accuracy and blood glucose control effects of Diabits, a smartphone app that helps patients with diabetes monitor and manage their blood glucose levels in real time.

METHODS

Using data from CGM devices and user input, Diabits applies machine learning techniques to create personalized patient models and predict blood glucose fluctuations up to 60 min in advance. These predictions give patients an opportunity to take pre-emptive action to maintain their blood glucose values within the reference range. In this retrospective observational cohort study, the predictive accuracy of Diabits and the correlation between daily use of the app and blood glucose control metrics were examined based on real app users' data. Moreover, the accuracy of predictions on the 2018 Ohio T1DM (type 1 diabetes mellitus) data set was calculated and compared against other published results.

RESULTS

On the basis of more than 6.8 million data points, 30-min Diabits predictions evaluated using Parkes Error Grid were found to be 86.89% (5,963,930/6,864,130) clinically accurate (zone A) and 99.56% (6,833,625/6,864,130) clinically acceptable (zones A and B), whereas 60-min predictions were 70.56% (4,843,605/6,864,130) clinically accurate and 97.49% (6,692,165/6,864,130) clinically acceptable. By analyzing daily use statistics and CGM data for the 280 most long-standing users of Diabits, it was established that under free-living conditions, many common blood glucose control metrics improved with increased frequency of app use. For instance, the average blood glucose for the days these users did not interact with the app was 154.0 (SD 47.2) mg/dL, with 67.52% of the time spent in the healthy 70 to 180 mg/dL range. For days with 10 or more Diabits sessions, the average blood glucose decreased to 141.6 (SD 42.0) mg/dL (P<.001), whereas the time in euglycemic range increased to 74.28% (P<.001). On the Ohio T1DM data set of 6 patients with type 1 diabetes, 30-min predictions of the base Diabits model had an average root mean square error of 18.68 (SD 2.19) mg/dL, which is an improvement over the published state-of-the-art results for this data set.

CONCLUSIONS

Diabits accurately predicts future glycemic fluctuations, potentially making it easier for patients with diabetes to maintain their blood glucose in the reference range. Furthermore, an improvement in glucose control was observed on days with more frequent Diabits use.