Study of Short-Term Personalized Glucose Predictive Models on Type-1 Diabetic Children

Bois, Maxime De; Yacoubi, Mounîm El; Ammi, Mehdi

doi:10.1109/ijcnn.2019.8852399

Cited by 10 publications

(32 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The predictions of three popular (in the context of glucose prediction) predictors have been used as the input to the DCP: a Feed-forward Neural Network (FFNN), a Gaussian Process regressor (GP), and an Extreme Learning Machine network (ELM) [5], [7]- [10], [14]. All the models have been optimized through the tuning of their hyperparameters.…”

Section: B Base Predictorsmentioning

confidence: 99%

See 1 more Smart Citation

Model Fusion to Enhance the Clinical Acceptability of Long-Term Glucose Predictions

Bois

Ammi²,

Yacoubi

2019

2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)

Self Cite

View full text Add to dashboard Cite

This paper presents the Derivatives Combination Predictor (DCP), a novel model fusion algorithm for making long-term glucose predictions for diabetic people. First, using the history of glucose predictions made by several models, the future glucose variation at a given horizon is predicted. Then, by accumulating the past predicted variations starting from a known glucose value, the fused glucose prediction is computed. A new loss function is introduced to make the DCP model learn to react faster to changes in glucose variations. The algorithm has been tested on 10 in-silico type-1 diabetic children from the T1DMS software. Three initial predictors have been used: a Gaussian process regressor, a feed-forward neural network and an extreme learning machine model. The DCP and two other fusion algorithms have been evaluated at a prediction horizon of 120 minutes with the root-mean-squared error of the prediction, the root-mean-squared error of the predicted variation, and the continuous glucose-error grid analysis. By making a successful trade-off between prediction accuracy and predicted-variation accuracy, the DCP, alongside with its specifically designed loss function, improves the clinical acceptability of the predictions, and therefore the safety of the model for diabetic people.

show abstract

Section: B Base Predictorsmentioning

confidence: 99%

“…2) GP: The GP model has been implemented with a dotproduct kernel [10]. Whereas the kernel coefficient and the inhomogeneity have been set to 0.5 and 0.01 respectively, the noise-controlling hyperparameter has been grid-searched inside the [10 −2 , 10 1 ] range.…”

Section: B Base Predictorsmentioning

confidence: 99%

Model Fusion to Enhance the Clinical Acceptability of Long-Term Glucose Predictions

Bois

Ammi²,

Yacoubi

2019

2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The GP model has been implemented with a dot-product kernel. The dotproduct has been chosen instead of a traditional radial basis function kernel as it has been shown to perform better in the context of glucose prediction [5]. The inhomogeneity parameter of the kernel has been set to 10 −8 .…”

Section: Modelsmentioning

confidence: 99%

“…As for them, Georga et al studied the use of Extreme Learning Machine models (ELM) in short-term (PH of 30 minutes) type 1 diabetes glucose prediction [10]. Finally, recurrent neural networks (RNN) have shown a lot of interest in the field [27], and in particular those with long short-term memory (LSTM) units [5,15,17,24].…”

Section: Introductionmentioning

confidence: 99%

Prediction-Coherent LSTM-Based Recurrent Neural Network for Safer Glucose Predictions in Diabetic People

Bois¹,

Yacoubi²,

Ammi³

2019

Neural Information Processing

Self Cite

View full text Add to dashboard Cite

In the context of time-series forecasting, we propose a LSTMbased recurrent neural network architecture and loss function that enhance the stability of the predictions. In particular, the loss function penalizes the model, not only on the prediction error (mean-squared error), but also on the predicted variation error. We apply this idea to the prediction of future glucose values in diabetes, which is a delicate task as unstable predictions can leave the patient in doubt and make him/her take the wrong action, threatening his/her life. The study is conducted on type 1 and type 2 diabetic people, with a focus on predictions made 30-minutes ahead of time. First, we confirm the superiority, in the context of glucose prediction, of the LSTM model by comparing it to other state-of-the-art models (Extreme Learning Machine, Gaussian Process regressor, Support Vector Regressor). Then, we show the importance of making stable predictions by smoothing the predictions made by the models, resulting in an overall improvement of the clinical acceptability of the models at the cost in a slight loss in prediction accuracy. Finally, we show that the proposed approach, outperforms all baseline results. More precisely, it trades a loss of 4.3% in the prediction accuracy for an improvement of the clinical acceptability of 27.1%. When compared to the moving average post-processing method, we show that the trade-off is more efficient with our approach.

show abstract

“…Machine learning techniques and algorithms are proving to be able to build a solid foundation in many areas in general and for blood glucose prediction in particular [ 2 , 3 ]. Data from real patients, by applying data-based models and techniques able to learn and extract patterns from the data, have been used for monitoring patients and predicting possible drops or rises in blood glucose levels, establishing recommendations based on each user’s particular and personal data.…”

Section: Introductionmentioning

confidence: 99%

Learning Carbohydrate Digestion and Insulin Absorption Curves Using Blood Glucose Level Prediction and Deep Learning Models

Muñoz-Organero

Queipo-Álvarez

García

2021

Sensors

View full text Add to dashboard Cite

Type 1 diabetes is a chronic disease caused by the inability of the pancreas to produce insulin. Patients suffering type 1 diabetes depend on the appropriate estimation of the units of insulin they have to use in order to keep blood glucose levels in range (considering the calories taken and the physical exercise carried out). In recent years, machine learning models have been developed in order to help type 1 diabetes patients with their blood glucose control. These models tend to receive the insulin units used and the carbohydrate taken as inputs and generate optimal estimations for future blood glucose levels over a prediction horizon. The body glucose kinetics is a complex user-dependent process, and learning patient-specific blood glucose patterns from insulin units and carbohydrate content is a difficult task even for deep learning-based models. This paper proposes a novel mechanism to increase the accuracy of blood glucose predictions from deep learning models based on the estimation of carbohydrate digestion and insulin absorption curves for a particular patient. This manuscript proposes a method to estimate absorption curves by using a simplified model with two parameters which are fitted to each patient by using a genetic algorithm. Using simulated data, the results show the ability of the proposed model to estimate absorption curves with mean absolute errors below 0.1 for normalized fast insulin curves having a maximum value of 1 unit.

show abstract

Study of Short-Term Personalized Glucose Predictive Models on Type-1 Diabetic Children

Cited by 10 publications

References 22 publications

Model Fusion to Enhance the Clinical Acceptability of Long-Term Glucose Predictions

Model Fusion to Enhance the Clinical Acceptability of Long-Term Glucose Predictions

Prediction-Coherent LSTM-Based Recurrent Neural Network for Safer Glucose Predictions in Diabetic People

Learning Carbohydrate Digestion and Insulin Absorption Curves Using Blood Glucose Level Prediction and Deep Learning Models

Contact Info

Product

Resources

About