The research on evaluation of diabetes metabolic function based on Support Vector Machine

Huang, Chunquan; Jiang, Guotai; Chen, Zhihong; Chen, Shuohao

doi:10.1109/bmei.2010.5640041

Cited by 3 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chunquan Huang et al [11] gave a detailed research on Evaluation of Diabetes Metabolic Function Based on Support Vector Machine aims to provide a survey using Support Vector Machine (SVM) to predict and assess metabolic functions of diabetes based on bio-heat transfer theory and infrared thermal imaging technology. Two metabolic characteristic values, metabolic function parameter and blood perfusion rate, are extracted from thermography data of cold water stimulation experiment as inputs of SVM to set up models by different kernel functions.…”

Section: Methodologies Used In Diabetes Detectionmentioning

confidence: 99%

See 1 more Smart Citation

A Review on associative classification for Diabetic Datasets A Simulation Approach

Jain¹,

Singh²

2013

IJCT

View full text Add to dashboard Cite

Association rules are used to discover all the interesting relationship in a potentially large database. Association rule mining is used to discover a small set of rules over the database to form more accurate evaluation. They capture all possible rules that explain the presence of some attributes in relation to the presence of other attributes. This review paper aims to study and observe a flexible way, of, mining frequent patterns by extending the idea of the Associative Classification method. For better performance, the Neural Network Association Classification system is also analyzed here to be one of the approaches for building accurate and efficient classifiers. In this review paper, the Neural Network Association Classification system is studied and compared in order to find best possible accurate results. Association rule mining and classification rule mining can be integrated to form a framework called as Associative Classification and these rules are referred as Class Association Rules. This review research paper also analyzes how data mining techniques are used for predicting different types of diseases. This paper reviewed the research papers which mainly concentrated on predicting Diabetes.

show abstract

Section: Methodologies Used In Diabetes Detectionmentioning

confidence: 99%

“…Association datasets [11] may contain many continuous properties. Association rules mining with continuous properties is a research content.…”

Section: Quantization Phasementioning

confidence: 99%

A Review on associative classification for Diabetic Datasets A Simulation Approach

Jain¹,

Singh²

2013

IJCT

View full text Add to dashboard Cite

show abstract

An Improved SVM-Based Cognitive Diagnosis Algorithm for Operation States of Distribution Grid

et al. 2015

View full text Add to dashboard Cite

Evaluation of the Accuracy and Safety of a Portable Metabolic Heat Conformation-Based Non-invasive Glucose Meter: A Multicentre Clinical Study. (Preprint)

Xu¹,

Li²,

Wu³

et al. 2021

Preprint

View full text Add to dashboard Cite

BACKGROUND Non-invasive blood glucose measurement is expected to be an ideal way for glucose monitoring, although most of the methods are under study and yet to be verified in large-scale clinical trials. OBJECTIVE We intend to evaluate the stability, accuracy of the metabolic heat conformation (MHC)-based non-invasive glucometer in a multicentre, self-controlled clinical trial. This device obtained the first medical device registration certificate awarded by the National Medical Products Administration of China (NMPA). METHODS The clinical study was conducted at three sites on 200 subjects who received glucose measurement with a non-invasive glucometer, the Contour Plus blood glucose monitoring system, and venous plasma glucose (VPG) measurements, in a fasted state and at 2 and 4 hours after meals. Trial Registration: ChiCTR1900020523. RESULTS The non-invasive and VPG measurements showed 93.9% (95% CI, 91.7–95.6%) of the values in zone A + B in a Consensus Error Grid. The measurements obtained in a fasted state and at 2 hours after meals are more accurate, with 99.0% and 97.0% of the values in zone A + B, respectively. The proportion of values in zone A + B and the correlation coefficients in subjects who did not receive insulin were 3.1% and 0.0596 higher than in those who received insulin. The accuracy of the non-invasive glucometer was influenced by the level of islet cell function and insulin resistance, which had a correlation coefficient with the MARD of -0.0961 (p=0.020) and -0.1577 (p=0.00012), respectively. CONCLUSIONS The MHC-based non-invasive glucometer demonstrates generally high stability and accuracy in the glucose monitoring of diabetic patients. The calculation model needs to be further explored and optimised for patients with different diabetes subtypes, levels of insulin resistance and insulin secretion capacity. CLINICALTRIAL the name of the trial registry : A multi-center study for evaluating the accuracy and safety of noninvasive glucose meter in people with diabetes or impaired glucose regulation (impaired fasting glucose and impaired glucose tolerance), using an experimental test system as a reference. registration number : ChiCTR1900020523 URL : https://www.chictr.org.cn/showproj.aspx?proj=33857

show abstract

The research on evaluation of diabetes metabolic function based on Support Vector Machine

Cited by 3 publications

References 5 publications

A Review on associative classification for Diabetic Datasets A Simulation Approach

A Review on associative classification for Diabetic Datasets A Simulation Approach

An Improved SVM-Based Cognitive Diagnosis Algorithm for Operation States of Distribution Grid

Evaluation of the Accuracy and Safety of a Portable Metabolic Heat Conformation-Based Non-invasive Glucose Meter: A Multicentre Clinical Study. (Preprint)

Contact Info

Product

Resources

About