Reducing high-risk glucose forecasting errors by evolving interpretable models for Type 1 diabetes

Cioppa, Antonio Della; Falco, Ivanoe De; Koutný, Tomáš; Scafuri, Umberto; Ubl, Martin; Tarantino, Ernesto

doi:10.1016/j.asoc.2023.110012

Cited by 8 publications

(3 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In diabetes management, XAI applications in the current literature mostly relates to predicting early asymptomatic stages of diabetes for early diagnosis [45], [46] or assessing the risks of adverse events [47], [48] in an interpretable manner. As for BGLs prediction, a personalized bidirectional LSTM model equipped with interpretability tools has been proposed in [49] using data from six T1DM patients.…”

Section: Related Workmentioning

confidence: 99%

Exploring Nutritional Influence on Blood Glucose Forecasting for Type 1 Diabetes Using Explainable AI

Annuzzi,

Apicella,

Arpaia

et al. 2024

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Type 1 diabetes mellitus (T1DM) is characterized by insulin deficiency and blood sugar control issues. The state-of-the-art solution is the artificial pancreas (AP), which integrates basal insulin delivery and glucose monitoring. However, APs are unable to manage postprandial glucose response (PGR) due to limited knowledge of its determinants, requiring additional information for accurate bolus delivery, such as estimated carbohydrate intake. This study aims to quantify the influence of various mealrelated factors on predicting postprandial blood glucose levels (BGLs) at different time intervals (15 min, 60 min, and 120 min) after meals by using deep neural network (DNN) models. The prediction models incorporate preprandial blood glucose values, insulin dosage, and various mealrelated nutritional factors such as intake of energy, carbohydrates, proteins, lipids, fatty acids, fibers, glycemic index, and glycemic load as input variables. The impact of input features was assessed by exploiting eXplainable Artificial Intelligence (XAI) methodologies, specifically SHapley Additive exPlanations (SHAP), which provide insights into each feature's contribution to the model predictions. By leveraging XAI methodologies, this study aims to enhance the interpretability and transparency of BGL prediction models and validate clinical literature hypotheses. The findings can aid in the development of decision-support tools for individuals with T1DM, facilitating PGR management and reducing the risks of adverse events. The improved understanding of PGR determinants may lead to advancements in AP technology and improve the overall quality of life for T1DM patients.

show abstract

Section: Related Workmentioning

confidence: 99%

Exploring Nutritional Influence on Blood Glucose Forecasting for Type 1 Diabetes Using Explainable AI

Annuzzi,

Apicella,

Arpaia

et al. 2024

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…Both the above issues assume noticeable importance in the medical domain, e.g., diabetes management. Several techniques have been investigated to discover data-driven glucose forecasting models, ranging from approaches based on regression [ 35 , 36 , 37 , 38 , 39 ] to those that handle the prediction as a classification problem [ 29 , 40 , 41 , 42 ]. These techniques can be classified as explainable or interpretable based on the techniques employed for discovering the learning model.…”

Section: State Of the Artmentioning

confidence: 99%

A Federated Learning-Inspired Evolutionary Algorithm: Application to Glucose Prediction

Falco

Cioppa

Koutný

et al. 2023

Sensors

View full text Add to dashboard Cite

In this paper, we propose an innovative Federated Learning-inspired evolutionary framework. Its main novelty is that this is the first time that an Evolutionary Algorithm is employed on its own to directly perform Federated Learning activity. A further novelty resides in the fact that, differently from the other Federated Learning frameworks in the literature, ours can efficiently deal at the same time with two relevant issues in Machine Learning, i.e., data privacy and interpretability of the solutions. Our framework consists of a master/slave approach in which each slave contains local data, protecting sensible private data, and exploits an evolutionary algorithm to generate prediction models. The master shares through the slaves the locally learned models that emerge on each slave. Sharing these local models results in global models. Being that data privacy and interpretability are very significant in the medical domain, the algorithm is tested to forecast future glucose values for diabetic patients by exploiting a Grammatical Evolution algorithm. The effectiveness of this knowledge-sharing process is assessed experimentally by comparing the proposed framework with another where no exchange of local models occurs. The results show that the performance of the proposed approach is better and demonstrate the validity of its sharing process for the emergence of local models for personal diabetes management, usable as efficient global models. When further subjects not involved in the learning process are considered, the models discovered by our framework show higher generalization capability than those achieved without knowledge sharing: the improvement provided by knowledge sharing is equal to about 3.03% for precision, 1.56% for recall, 3.17% for F1, and 1.56% for accuracy. Moreover, statistical analysis reveals the statistical superiority of model exchange with respect to the case of no exchange taking place.

show abstract

“…To reduce hyper- or hypoglycemic excursions, reliable prediction of future blood glucose levels from previous measurements is desirable for children, as well as adults with T1D. Since the release of the OhioT1DM dataset ( 4 ), which consists of data of 6, and later 12 ( 5 ) adults with T1D, the topic of blood glucose forecasting has been picked up by the machine learning community ( 6 – 10 ). For example, McShinsky and Marshall ( 7 ) investigated the performance of classical non deep-learning based methods such as autoregressive moving average (ARIMA), random forests, and support vector machines (SVM) for forecasting blood glucose values.…”

Section: Introductionmentioning

confidence: 99%

Blood glucose forecasting from temporal and static information in children with T1D

Marx,

Di Stefano,

Leutheuser

et al. 2023

Front. Pediatr.

View full text Add to dashboard Cite

BackgroundThe overarching goal of blood glucose forecasting is to assist individuals with type 1 diabetes (T1D) in avoiding hyper- or hypoglycemic conditions. While deep learning approaches have shown promising results for blood glucose forecasting in adults with T1D, it is not known if these results generalize to children. Possible reasons are physical activity (PA), which is often unplanned in children, as well as age and development of a child, which both have an effect on the blood glucose level.Materials and MethodsIn this study, we collected time series measurements of glucose levels, carbohydrate intake, insulin-dosing and physical activity from children with T1D for one week in an ethics approved prospective observational study, which included daily physical activities. We investigate the performance of state-of-the-art deep learning methods for adult data—(dilated) recurrent neural networks and a transformer—on our dataset for short-term (30 min) and long-term (2 h) prediction. We propose to integrate static patient characteristics, such as age, gender, BMI, and percentage of basal insulin, to account for the heterogeneity of our study group.ResultsIntegrating static patient characteristics (SPC) proves beneficial, especially for short-term prediction. LSTMs and GRUs with SPC perform best for a prediction horizon of 30 min (RMSE of 1.66 mmol/l), a vanilla RNN with SPC performs best across different prediction horizons, while the performance significantly decays for long-term prediction. For prediction during the night, the best method improves to an RMSE of 1.50 mmol/l. Overall, the results for our baselines and RNN models indicate that blood glucose forecasting for children conducting regular physical activity is more challenging than for previously studied adult data.ConclusionWe find that integrating static data improves the performance of deep-learning architectures for blood glucose forecasting of children with T1D and achieves promising results for short-term prediction. Despite these improvements, additional clinical studies are warranted to extend forecasting to longer-term prediction horizons.

show abstract

Reducing high-risk glucose forecasting errors by evolving interpretable models for Type 1 diabetes

Cited by 8 publications

References 52 publications

Exploring Nutritional Influence on Blood Glucose Forecasting for Type 1 Diabetes Using Explainable AI

Exploring Nutritional Influence on Blood Glucose Forecasting for Type 1 Diabetes Using Explainable AI

A Federated Learning-Inspired Evolutionary Algorithm: Application to Glucose Prediction

Blood glucose forecasting from temporal and static information in children with T1D

Contact Info

Product

Resources

About