Short Term Blood Glucose Prediction based on Continuous Glucose Monitoring Data

Mohebbi, Ali; Hansen, Niels Ebbe; Christensen, Peter Ebert; Tarp, Jens M.; Jensen, Morten Lind; Bengtsson, Henrik; Mørup, Morten

doi:10.1109/embc44109.2020.9176695

Cited by 20 publications

(16 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our CGM-based models were able to accurately predict glucose values at 15 (RMSEs, overall/type 2 diabetes: 0.19/0.29 mmol/L) and 60 minutes (RMSEs, overall/type 2 diabetes: 0.59/0.70 mmol/L). These results surpass previously reported RMSE values for a sample of 50 individuals with type 2 diabetes, which were 0.65 and 1.50 mmol/L for 15-and 60-minute CGM-based glucose prediction, respectively [34]. We expect this difference to, in part, stem from our much larger sample size.…”

Section: Discussioncontrasting

confidence: 82%

“…Although most research has thus far focused on type 1 diabetes [12], several efforts have been made to use machine learning for glucose prediction in individuals with type 2 diabetes [30][31][32][33][34]. Most of these studies assessed technical aspects of glucose prediction in relatively small (n = 1 to 50) or even virtual, in silico populations.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Machine learning-based glucose prediction with use of continuous glucose and physical activity monitoring data: The Maastricht Study

et al. 2021

View full text Add to dashboard Cite

Background Closed-loop insulin delivery systems, which integrate continuous glucose monitoring (CGM) and algorithms that continuously guide insulin dosing, have been shown to improve glycaemic control. The ability to predict future glucose values can further optimize such devices. In this study, we used machine learning to train models in predicting future glucose levels based on prior CGM and accelerometry data. Methods We used data from The Maastricht Study, an observational population‐based cohort that comprises individuals with normal glucose metabolism, prediabetes, or type 2 diabetes. We included individuals who underwent >48h of CGM (n = 851), most of whom (n = 540) simultaneously wore an accelerometer to assess physical activity. A random subset of individuals was used to train models in predicting glucose levels at 15- and 60-minute intervals based on either CGM data or both CGM and accelerometer data. In the remaining individuals, model performance was evaluated with root-mean-square error (RMSE), Spearman’s correlation coefficient (rho) and surveillance error grid. For a proof-of-concept translation, CGM-based prediction models were optimized and validated with the use of data from individuals with type 1 diabetes (OhioT1DM Dataset, n = 6). Results Models trained with CGM data were able to accurately predict glucose values at 15 (RMSE: 0.19mmol/L; rho: 0.96) and 60 minutes (RMSE: 0.59mmol/L, rho: 0.72). Model performance was comparable in individuals with type 2 diabetes. Incorporation of accelerometer data only slightly improved prediction. The error grid results indicated that model predictions were clinically safe (15 min: >99%, 60 min >98%). Our prediction models translated well to individuals with type 1 diabetes, which is reflected by high accuracy (RMSEs for 15 and 60 minutes of 0.43 and 1.73 mmol/L, respectively) and clinical safety (15 min: >99%, 60 min: >91%). Conclusions Machine learning-based models are able to accurately and safely predict glucose values at 15- and 60-minute intervals based on CGM data only. Future research should further optimize the models for implementation in closed-loop insulin delivery systems.

show abstract

Section: Discussioncontrasting

confidence: 82%

Section: Discussionmentioning

confidence: 99%

Machine learning-based glucose prediction with use of continuous glucose and physical activity monitoring data: The Maastricht Study

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Because RNN with LSTM [16] and ARMA with the RLS and change detection methods [19] are conducted on CGM data, insulin, and carbohydrate and CGM data, continuous metabolic, physical activity, and lifestyle information, respectively, we cannot run them based on our dataset with only CGM data. To fill the gap of comparison, we add LSTM-based RNN [12] and ARMA with the RLS and change detection methods [17] as two baseline methods. Also, the training processings of those methods are the same as the way used in this work.…”

Section: Comparison With Previous Studiesmentioning

confidence: 99%

“…The comparison results are listed in Table 7 (30-min-ahead predictions). From Table 7, we can see that the proposed method slightly outperforms the best method in predicting the BG levels by using the Machine learning methods ANN [8] CGM data RMSE: 18 mg/dL ANN with optimal structure [9] CGM data RMSE: 7.45 mg/dL SVR based on the DE algorithm [10] CGM data RMSE: 10.78 mg/dL DNN with LSTM [11] CGM data RMSE: 12.38 mg/dL LSTM-based RNN [12] CGM data RMSE: 1.1557 mmol/L MLP with time-domain features [13] CGM data RMSE: 6.31 mg/dL SVR [14] CGM data,…”

Section: Comparison With Previous Studiesmentioning

confidence: 99%

“…Besides, the support vector regression (SVR) is also utilized to predict the future BG levels [10]. Benefited from the development of deep neural network (DNN), Idriss et al [11] proposed DNN with long short-term memory (LSTM) cells, and Mohebbi et al [12] explored the LSTM-based recurrent neural networks (RNN) to establish the BG prediction model. In essence, the prediction methods are modeling the historical data.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A predictive model incorporating the change detection and Winsorization methods for alerting hypoglycemia and hyperglycemia

Xie

Yang

2021

Med Biol Eng Comput

View full text Add to dashboard Cite

This paper focuses on establishing an effective predictive model to quickly and accurately alert hypoglycemia and hyperglycemia for helping control blood glucose levels of people with diabetes. In general, a good predictive model is established on the features of data. Inspired by this, we first analyze the characteristics of continuous glucose monitoring (CGM) data by the equality of variances test and outlier detection, which show time-varying fluctuations and jump points in CGM data. Therefore, we incorporate the change detection method and the Winsorization method into the predictive model based on the autoregressive moving average (ARMA) model and the recursive least squares (RLS) method to fit the above characteristics. To the best of our knowledge, the proposed method is the first attempt to give a solution for matching the time-varying fluctuations and jump points of CGM data simultaneously. A case study using CGM data is given to validate the effectiveness of the proposed method under 30-min-ahead prediction. The results show that the proposed method can improve the true alarm ratio of hypoglycemia and hyperglycemia from 0.7983 to 0.8783, and lengthen the average advance detection time of hypoglycemia and hyperglycemia from 19.77 to 22.64 min.

show abstract