Short and Medium Term Blood Glucose Prediction Using Multi-objective Grammatical Evolution

Contador, Sergio; Colmenar, J. Manuel; Garnica, Óscar; Hidalgo, J. Ignacio

doi:10.1007/978-3-030-43722-0_32

Cited by 2 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Sect. 4.1, we describe the experiments corresponding to the What-if scenario, which deals with the same dataset of ten real patients, as explained in [10]. In Sect.…”

Section: Resultsmentioning

confidence: 99%

“…In this paper, which extends the work presented at the EvoStar 2020 Conference [10], we investigate the benefits and drawbacks of a multi-objective implementation of GE in the generation of models for BG prediction in diabetes patients. In particular, we implement a multi-objective GE based on the classic NSGA-II algorithm, which is guided by two fitness functions: RMSE and F CLARKE , which is a function designed following the CEG metric.…”

Section: Discussionmentioning

confidence: 99%

“…14 Bayesian model of [6] to analyse the GE results with RMSE as objective function for the Agnostic scenario prediction horizon in order to predict glucose values. Data from ten real diabetic patients were studied in this scenario, as in [10]. On the other hand, we have studied the Agnostic scenario, where no information about future events is available.…”

Section: Discussionmentioning

confidence: 99%

“…As will be seen, the development of a problem-specific fitness function does not only considerably improve the quality and the robustness of the GE algorithm as an SR tool in the What-if scenario, as we show in [10], but also allows us to obtain good Agnostic prediction models using only information from the last hour previous to the time of prediction.…”

Section: Introductionmentioning

confidence: 94%

“…We use GE with two objective functions: Root Mean Squared Error (RMSE) and an adapted fitness, denoted as F CLARKE , which is based on the Clarke Error Grid (CEG) metric [8]. This paper is an extended version of the work presented at the EvoStar 2020 Conference [10] and the continuation of the machine learning research developed at the Universidad Complutense de Madrid, Adaptive and Bioinspired Systems Research Group since 2013 [18,[21][22][23][24] and [50]. The contribution of this paper in relation to [10] is twofold: on the one hand we have extended the analysis to the Agnostic scenario using a new dataset also coming from real diabetic patients and, on the other hand, we have performed a deeper analysis of the results where we graphically compare the solutions obtained, allowing us to draw medical conclusions.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Blood glucose prediction using multi-objective grammatical evolution: analysis of the “agnostic” and “what-if” scenarios

Contador

Colmenar

Garnica

et al. 2021

Genet Program Evolvable Mach

Self Cite

View full text Add to dashboard Cite

In this paper we investigate the benefits of applying a multi-objective approach for solving a symbolic regression problem by means of Grammatical Evolution. In particular, we extend previous work, obtaining mathematical expressions to model glucose levels in the blood of diabetic patients. Here we use a multi-objective Grammatical Evolution approach based on the NSGA-II algorithm, considering the root-mean-square error and an ad-hoc fitness function as objectives. This ad-hoc function is based on the Clarke Error Grid analysis, which is useful for showing the potential danger of mispredictions in diabetic patients. In this work, we use two datasets to analyse two different scenarios: What-if and Agnostic, the most common in daily clinical practice. In the What-if scenario, where future events are evaluated, results show that the multi-objective approach improves previous results in terms of Clarke Error Grid analysis by reducing the number of dangerous mispredictions. In the Agnostic situation, with no available information about future events, results suggest that we can obtain good predictions with only information from the previous hour for both Grammatical Evolution and Multi-Objective Grammatical Evolution.

show abstract

“…In Sect. 4.1, we describe the experiments corresponding to the What-if scenario, which deals with the same dataset of ten real patients, as explained in [10]. In Sect.…”

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 94%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Blood glucose prediction using multi-objective grammatical evolution: analysis of the “agnostic” and “what-if” scenarios

Contador

Colmenar

Garnica

et al. 2021

Genet Program Evolvable Mach

Self Cite

View full text Add to dashboard Cite

show abstract

Blood Glucose Prediction from Nutrition Analytics in Type 1 Diabetes: A Review

Lubasinski,

Thabit,

Nutter

et al. 2024

Nutrients

View full text Add to dashboard Cite

Introduction: Type 1 Diabetes (T1D) affects over 9 million worldwide and necessitates meticulous self-management for blood glucose (BG) control. Utilizing BG prediction technology allows for increased BG control and a reduction in the diabetes burden caused by self-management requirements. This paper reviews BG prediction models in T1D, which include nutritional components. Method: A systematic search, utilizing the PRISMA guidelines, identified articles focusing on BG prediction algorithms for T1D that incorporate nutritional variables. Eligible studies were screened and analyzed for model type, inclusion of additional aspects in the model, prediction horizon, patient population, inputs, and accuracy. Results: The study categorizes 138 blood glucose prediction models into data-driven (54%), physiological (14%), and hybrid (33%) types. Prediction horizons of ≤30 min are used in 36% of models, 31–60 min in 34%, 61–90 min in 11%, 91–120 min in 10%, and >120 min in 9%. Neural networks are the most used data-driven technique (47%), and simple carbohydrate intake is commonly included in models (data-driven: 72%, physiological: 52%, hybrid: 67%). Real or free-living data are predominantly used (83%). Conclusion: The primary goal of blood glucose prediction in T1D is to enable informed decisions and maintain safe BG levels, considering the impact of all nutrients for meal planning and clinical relevance.

show abstract

Short and Medium Term Blood Glucose Prediction Using Multi-objective Grammatical Evolution

Cited by 2 publications

References 22 publications

Blood glucose prediction using multi-objective grammatical evolution: analysis of the “agnostic” and “what-if” scenarios

Blood glucose prediction using multi-objective grammatical evolution: analysis of the “agnostic” and “what-if” scenarios

Blood Glucose Prediction from Nutrition Analytics in Type 1 Diabetes: A Review

Contact Info

Product

Resources

About