Electrocardiographic Signals and Swarm-Based Support Vector Machine for Hypoglycemia Detection

Nuryani, Nuryani; Ling, Sai Ho; Nguyen, Hung T.

doi:10.1007/s10439-011-0446-7

Cited by 70 publications

(64 citation statements)

References 46 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…23,28,35 While it is important to choose the most informative features and the best classification method, the efficacy is governed by The sample-based hypoglycemia detection sensitivity and specificity levels of the CGM device reported in this study were 31% and 98%, respectively. Much higher sensitivities have been reported, ranging from 38% to 67%, whereas similar specificities are reported.…”

Section: Discussionmentioning

confidence: 93%

“…Furthermore, the concept of pattern recognition can be appended to the existing recalibration algorithms, and pattern recognition tools have been used with success in other chronic diseases to detect events. 22,23 Optimization of hypoglycemia detection in professional CGM is necessary when the clinician strives to identify and adjust insulin regimen responsible for hypoglycemia.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Professional Continuous Glucose Monitoring in Subjects with Type 1 Diabetes: Retrospective Hypoglycemia Detection

Jensen

Christensen

Tarnow

et al. 2013

J Diabetes Sci Technol

View full text Add to dashboard Cite

Background: An important task in diabetes management is detection of hypoglycemia. Professional continuous glucose monitoring (CGM), which produces a glucose reading every 5 min, is a powerful tool for retrospective identification of unrecognized hypoglycemia. Unfortunately, CGM devices tend to be inaccurate, especially in the hypoglycemic range, which limits their applicability for hypoglycemia detection. The objective of this study was to develop an automated pattern recognition algorithm to detect hypoglycemic events in retrospective, professional CGM. Method: Continuous glucose monitoring and plasma glucose (PG) readings were obtained from 17 data sets of 10 type 1 diabetes patients undergoing insulin-induced hypoglycemia. The CGM readings were automatically classified into a hypoglycemic group and a nonhypoglycemic group on the basis of different features from CGM readings and insulin injection. The classification was evaluated by comparing the automated classification with PG using sample-based and event-based sensitivity and specificity measures. Results: With an event-based sensitivity of 100%, the algorithm produced only one false hypoglycemia detection. The sample-based sensitivity and specificity levels were 78% and 96%, respectively. Conclusions: The automated pattern recognition algorithm provides a new approach for detecting unrecognized hypoglycemic events in professional CGM data. The tool may assist physicians and diabetologists in conducting a more thorough evaluation of the diabetes patient's glycemic control and in initiating necessary measures for improving glycemic control.

show abstract

Section: Discussionmentioning

confidence: 93%

Section: Introductionmentioning

confidence: 99%

Professional Continuous Glucose Monitoring in Subjects with Type 1 Diabetes: Retrospective Hypoglycemia Detection

Jensen

Christensen

Tarnow

et al. 2013

J Diabetes Sci Technol

View full text Add to dashboard Cite

show abstract

“…Based on the unique theory of the structural risk minimization principle, SVR estimates a function by minimizing an upper bound of the generalization error. 25 Supposing that there are training data f(x l , y l ), . .…”

Section: Svr Model Forecastingmentioning

confidence: 99%

A Novel Adaptive-Weighted-Average Framework for Blood Glucose Prediction

Wang

Wu²,

Mo³

2013

Diabetes Technology & Therapeutics

View full text Add to dashboard Cite

Background: Blood glucose (BG) prediction plays a very important role in daily BG management of patients with diabetes mellitus. Several algorithms, such as autoregressive (AR) models and artificial neural networks, have been proposed for BG prediction. However, every algorithm has its own subject range (i.e., one algorithm might work well for one diabetes patient but poorly for another patient). Even for one individual patient, this algorithm might perform well during the preprandial period but poorly during the postprandial period. Materials and Methods: A novel framework was proposed to combine several BG prediction algorithms. The main idea of the novel framework is that an adaptive weight is given to each algorithm where one algorithm's weight is inversely proportional to the sum of the squared prediction errors. In general, this framework can be applied to combine any BG prediction algorithms. Results: As an example, the proposed framework was used to combine an AR model, extreme learning machine, and support vector regression. The new algorithm was compared with these three prediction algorithms on the continuous glucose monitoring system (CGMS) readings of 10 type 1 diabetes mellitus patients; the CGMS readings of each patient included 860 CGMS data points. For each patient, the algorithms were evaluated in terms of root-mean-square error, relative error, Clarke error-grid analysis, and J index. Of the 40 evaluations, the new adaptive-weighted algorithm achieved the best prediction performance in 37 (92.5%). Conclusions: Thus, we conclude that the adaptive-weighted-average framework proposed in this study can give satisfactory predictions and should be used in BG prediction. The new algorithm has great robustness with respect to variations in data characteristics, patients, and prediction horizons. At the same time, it is universal.

show abstract

“…The work in [4] has proposed a new neural network based fault diagnosis approach for analog circuits by using kurtosis and entropy as a preprocessor. However, SVM is a classification technique which is successfully employed in many applications [13][14][15]. Their advantages in classifications have been exemplified in many fields.…”

Section: Introductionmentioning

confidence: 99%

A new swarm-SVM-based fault diagnosis approach for switched current circuit by using kurtosis and entropy as a preprocessor

Zhang

Duan

Long

et al. 2014

Analog Integr Circ Sig Process

View full text Add to dashboard Cite

This paper presents a new fault diagnosis method for switched current (SI) circuits. The kurtoses and entropies of the signals are calculated by extracting the original signals from the output terminals of the circuit. Support vector machine (SVM) is introduced for fault diagnosis using the entropies and kurtoses as inputs. In this technique, a particle swarm optimization is proposed to optimize the SVM to diagnose switched current circuits. The proposed method can identify faulty components in switched current circuit. A lowpass SI filter circuit has been used as test beached to verify the effectiveness of the proposed method. The accuracy of fault recognition achieved is about 97 % although there are some overlapping data when tolerance is considered. A comparison of our work with Long et al. (Analog Integr Circuit Signal Process 66:93-102, 2011), which only used entropy as a preprocessor, reveals that our method performs well in the part of fault diagnostic accuracy.

show abstract

Electrocardiographic Signals and Swarm-Based Support Vector Machine for Hypoglycemia Detection

Cited by 70 publications

References 46 publications

Professional Continuous Glucose Monitoring in Subjects with Type 1 Diabetes: Retrospective Hypoglycemia Detection

Professional Continuous Glucose Monitoring in Subjects with Type 1 Diabetes: Retrospective Hypoglycemia Detection

A Novel Adaptive-Weighted-Average Framework for Blood Glucose Prediction

A new swarm-SVM-based fault diagnosis approach for switched current circuit by using kurtosis and entropy as a preprocessor

Contact Info

Product

Resources

About