Hypoglycemia event prediction from CGM using ensemble learning

Explainable Machine-Learning Models to Predict Weekly Risk of Hyperglycemia, Hypoglycemia, and Glycemic Variability in Patients With Type 1 Diabetes Based on Continuous Glucose Monitoring

BACKGROUND AND OBJECTIVE

The aim of this study was to develop and validate explainable prediction models based on continuous glucose monitoring (CGM) and baseline data to identify a week-to-week risk of CGM key metrics (hyperglycemia, hypoglycemia, glycemic variability). By having a weekly prediction of CGM key metrics, it is possible for the patient or health care personnel to take immediate preemptive action.

METHODS

We analyzed, trained, and internally tested three prediction models (Logistic regression, XGBoost, and TabNet) using CGM data from 187 type 1 diabetes patients with long-term CGM monitoring. A binary classification approach combined with feature engineering deployed on the CGM signals was used to predict hyperglycemia, hypoglycemia, and glycemic variability based on consensus targets (time above range ≥5%, time below range ≥4%, coefficient of variation ≥36%). The models were validated in two independent cohorts with a total of 223 additional patients of varying ages.

RESULTS

A total of 46 593 weeks of CGM data were included in the analysis. For the best model (XGBoost), the area under the receiver operating characteristic curve (ROC-AUC) was 0.9 [95% confidence interval (CI) = 0.89-0.91], 0.89 [95% CI = 0.88-0.9], and 0.8 [95% CI = 0.79-0.81] for predicting hyperglycemia, hypoglycemia, and glycemic variability in the interval validation, respectively. The validation test showed good generalizability of the models with ROC-AUC of 0.88 to 0.95, 0.84 to 0.89, and 0.80 to 0.82 for predicting the glycemic outcomes.

CONCLUSION

Prediction models based on real-world CGM data can be used to predict the risk of unstable glycemic control in the forthcoming week. The models showed good performance in both internal and external validation cohorts.

Development and Validation of a Nocturnal Hypoglycaemia Risk Model for Patients With Type 2 Diabetes Mellitus

AIM

To develop and test different machine learning algorithms for predicting nocturnal hypoglycaemia in patients with type 2 diabetes mellitus.

DESIGN

A retrospective study.

METHODS

We collected data from dynamic blood glucose monitoring of patients with T2DM admitted to the Department of Endocrinology and Metabolism at a hospital in Shanghai, China, from November 2020 to January 2022. Patients undergone the continuous glucose monitoring (CGM) for ≥ 24 h were included in this study. Logistic regression, random forest and light gradient boosting machine algorithms were employed, and the models were validated and compared using AUC, accuracy, specificity, recall rate, precision, F1 score and the Kolmogorov-Smirnov test.

RESULTS

A total of 4015 continuous glucose-monitoring data points from 440 patients were included, and 28 variables were selected to build the risk prediction model. The 440 patients had an average age of 62.7 years. Approximately 48.2% of the patients were female and 51.8% were male. Nocturnal hypoglycaemia appeared in 573 (14.30%) of 4015 continuous glucose monitoring data. The light gradient boosting machine model demonstrated the highest predictive performances: AUC (0.869), specificity (0.802), accuracy (0.801), precision (0.409), recall rate (0.797), F1 score (0.255) and Kolmogorov (0.603). The selected predictive factors included time below the target glucose range, duration of diabetes, insulin use before bed and dynamic blood glucose monitoring parameters from the previous day.

PATIENT OR PUBLIC CONTRIBUTION

No Patient or Public Contribution.

Development and Validation of a Machine Learning Model to Predict Weekly Risk of Hypoglycemia in Patients with Type 1 Diabetes Based on Continuous Glucose Monitoring

Aim: The aim of this study was to develop and validate a prediction model based on continuous glucose monitoring (CGM) data to identify a week-to-week risk profile of excessive hypoglycemia. Methods: We analyzed, trained, and internally tested two prediction models using CGM data from 205 type 1 diabetes patients with long-term CGM monitoring. A binary classification approach (XGBoost) combined with feature engineering deployed on the CGM signals was utilized to predict excessive hypoglycemia risk defined by two targets (time below range [TBR] >4% and the upper TBR 90th percentile limit) of TBR the following week. The models were validated in two independent cohorts with a total of 253 additional patients. Results: A total of 61,470 weeks of CGM data were included in the analysis. The XGBoost models had an area under the receiver operating characteristic curve (ROC-AUC) of 0.83-0.87 (95% confidence interval; 0.83-0.88) in the test dataset. The external validation showed ROC-AUCs of 0.81-0.90. The most discriminative features included the low blood glucose index, the glycemic risk assessment diabetes equation (GRADE), hypoglycemia, the TBR, waveform length, the coefficient of variation and mean glucose during the previous week. This highlights that the pattern of hypoglycemia combined with glucose variability during the past week contains information on the risk of future hypoglycemia. Conclusion: Prediction models based on real-world CGM data can be used to predict the risk of hypoglycemia in the forthcoming week. The models showed good performance in both the internal and external validation cohorts.

Continuous Glucose Monitoring in Pregnancy

Diabetes mellitus in pregnancy is associated with adverse maternal and neonatal outcomes. Optimal glycemic control is associated with improved outcomes. Continuous glucose monitoring is a less invasive alternative to blood glucose measurements. Two types of continuous glucose monitoring are available in the market: real time and intermittently scanned. Continuous glucose monitoring is gaining popularity and is now recommended by some societies for glucose monitoring in pregnant women. In this review, we discuss the differences between the two types of continuous glucose monitoring, optimal treatment goals, and whether there is an improvement in maternal or neonatal outcomes.

Prediction of Hypoglycemia From Continuous Glucose Monitoring in Insulin-Treated Patients With Type 2 Diabetes Using Transfer Learning on Type 1 Diabetes Data: A Deep Transfer Learning Approach

BACKGROUND

Hypoglycemia is common in insulin-treated type 2 diabetes (T2D) patients, which can lead to decreased quality of life or premature death. Deep learning models offer promise of accurate predictions, but data scarcity poses a challenge. This study aims to develop a deep learning model utilizing transfer learning to predict hypoglycemia.

METHODS

Continuous glucose monitoring (CGM) data from 226 patients with type 1 diabetes (T1D) and 180 patients with T2D were utilized. Data were structured into one-hour samples and labeled as hypoglycemia or not depending on whether three consecutive CGM values were below 3.9 [mmol/L] (70 mg/dL) one hour after the sample. A convolutional neural network (CNN) was pre-trained with the T1D data set and subsequently fitted using a T2D data set, all while being optimized toward maximizing the area under the receiver operating characteristics curve (AUC) value, and it was externally validated on a separate T2D data set.

RESULTS

The developed model was externally validated with 334 711 one-hour CGM samples, of which 15 695 (4.69%) were labeled as hypoglycemic. The model achieved an AUC of 0.941 and a positive predictive value of 40.49% at a specificity of 95% and a sensitivity of 69.16%.

CONCLUSIONS

The transfer learned CNN model showed promising performance in predicting hypoglycemic episodes and with slightly better results than a non-transfer learned CNN model.

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.