A Nonlinear Blind Identification Approach to Modeling of Diabetic Patients

Novara, Carlo; Pour, N. Mohammad; Vincent, Tyrone L.; Grassi, Giorgio

doi:10.1109/tcst.2015.2462734

Cited by 28 publications

(9 citation statements)

References 28 publications

(4 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. Various techniques are investigated to the BGL prediction problem: statistical methods such as AR [15], [16] and Kalman Filter (KF) [17]; machine learning methods such as Artificial NNs [18]- [20] and Support Vector Regression (SVR) [21], [22]; and recently deep learning techniques [8], [9].…”

Section: Related Workmentioning

confidence: 99%

Predicting blood glucose using an LSTM Neural Network

Idriss¹,

Idri

Abnane

et al. 2019

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

Diabetes self-management relies on the blood glucose prediction as it allows taking suitable actions to prevent low or high blood glucose level. In this paper, we propose a deep learning neural network (NN) model for blood glucose prediction. It is a sequential one using a Long-Short-Term Memory (LSTM) layer with two fully connected layers. Several experiments were carried out over data of 10 diabetic patients to decide on the model's parameters in order to identify the best variant of it. The performance of the proposed LSTM NN measured in terms of root mean square error (RMSE) was compared with the ones of an existing LSTM and an autoregressive (AR) models. The results show that our LSTM NN is significantly more accurate; in fact, it outperforms the existing LSTM model for all patients and outperforms the AR model in 9 over 10 patients, besides, the performance differences were assessed by the Wilcoxon statistical test. Furthermore, the mean of the RMSE of our model was 12.38 mg/dl while it was 28.84 mg/dl and 50.69 mg/dl for AR and the existing LSTM respectively.

show abstract

Section: Related Workmentioning

confidence: 99%

Predicting blood glucose using an LSTM Neural Network

Idriss¹,

Idri

Abnane

et al. 2019

Annals of Computer Science and Information Systems

View full text Add to dashboard Cite

show abstract

“…In the physiological model, the overall BG dynamic is usually characterised into: meal dynamics (Dalla Man, Rizza and Cobelli, 2007;Hovorka et al, 2004), insulin dynamics (Duke, 2010;Wilinska et al, 2005), exercise model (Vehí et al, 2019) and glucose dynamics (Duke, 2010;Lehmann and Deutsch, 1992;Tarín et al, 2005). These models require previous knowledge to set the physiological constants (Hidalgo et al, 2017;Novara et al, 2016).…”

Section: Models and Systems For Glycaemia Predictionmentioning

confidence: 99%

“…The data-based models are in general more accurate (Novara et al, 2016). These models have been proposed using pattern recognition techniques and experimental data.…”

Section: Models and Systems For Glycaemia Predictionmentioning

confidence: 99%

Hypoglycaemia Prediction Models With Auto Explanation

et al. 2022

View full text Add to dashboard Cite

World-wide statistics show a considerable growth of the occurrence of different types of Diabetes Mellitus, posing diverse challenges at many levels for public health policies. Some of these challenges may be addressed by means of computerised systems which may pave the way to provide practitioners with insight on their patient's conditions anywhere and at anytime, but also to empower Diabetes patients as managers of their health. These systems for disease management come in many shapes and sizes, being the most promising trends the ones that involve expert systems that comprise specialised knowledge, use predictive models, feature engineering and reasoning. This study presents the state-of-the-art on reasoning and prediction models related with either blood glucose level or hypoglycaemia events. The main findings revealed are that there is room for improvement on predictive models, namely to enhance its accuracy and ability to forecast future events into a wider time frame. On the other hand, reasoning models are understudied and its usage in Diabetes management is reduced. We discuss an architecture that combines a predictive model and a reasoning system, with the objective of alerting of impending occurrences and interpret the current situation to accurately advise the diabetic user.

show abstract

“…Based on real-world cases, the CEP method provides poor performance on large-scale data for identifying heart failure. Novara et al (2016), the input signals such as emotions, food and physical activity were effectively recovered by blind identification approach for type 1 diabetic patients. The samples for five type 1 diabetic patients were collected for experimental study to the blood glucose for that five patients.…”

Section: Literature Reviewmentioning

confidence: 99%

An Analysis of Heart Disease for Diabetic Patients Using Recursive Feature Elimination with Random Forest

Channabasavaraju¹,

Vinayakamurthy²

2020

Journal of Computer Science

View full text Add to dashboard Cite

Data Mining Techniques are used in many areas like banking, healthcare, education because of extracting relevant information from the database. Many algorithms in data mining are used to predict the disease to reduce the patient treatment cost as well as increase the diagnosis accuracy. In this research work, the risk level of diabetic heart disease patient can be predicted using two datasets such as Pima Indians Diabetes dataset and heart disease dataset. Based on the World Health Organization (WHO), diabetes is the one of the biggest health concerns so mining the diabetes data is an ambiguous task. Diabetic patients may also have to suffer from other diseases like heart disease, eye complications, kidney disease, nerve damage, foot problems, skin complications and dental diseases. However, the existing techniques faced the difficulty to identify inconsistent and redundant features. In this research work, the Random Forest Feature Selection Technique (RFS) is developed to identify the significant features and eliminate irrelevant features which are used to improve the predicting accuracy of Cardio Vascular (CV) disease for diabetic patients. According to the output from the extensive experiments, this research categorizes that whether the diabetic patients having CV or not by using True Positive as diabetes and True Negative as no diabetes.

show abstract

A Nonlinear Blind Identification Approach to Modeling of Diabetic Patients

Cited by 28 publications

References 28 publications

Predicting blood glucose using an LSTM Neural Network

Predicting blood glucose using an LSTM Neural Network

Hypoglycaemia Prediction Models With Auto Explanation

An Analysis of Heart Disease for Diabetic Patients Using Recursive Feature Elimination with Random Forest

Contact Info

Product

Resources

About