Evaluating the Risk of Metabolic Syndrome Based on an Artificial Intelligence Model

Chen, Hui; Xiong, Shenghua; Ren, Xuan

doi:10.1155/2014/207268

Cited by 13 publications

(21 citation statements)

References 35 publications

(47 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hirose et al applied ANN for prediction of the 6-year incidence of MetS by using clinical data [30]. Chen et al concluded that ANN is preferable to the traditional logistic regression analysis for assessing the risk of MetS from sex, age, BMI, waist circumference, waist-to-height ratio, hip circumference, systolic and diastolic blood pressure [31]. Darko Ivanovic´ proposed the feed-forward ANN with back propagation as the training algorithm to predict MetS.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Machine Learning Techniques for Screening and Diagnosis of Diabetes: a Survey

Sun

Zhang

2019

Teh. vjesn.

View full text Add to dashboard Cite

Diabetes has become one of the major causes of national disease and death in most countries. By 2015, diabetes had affected more than 415 million people worldwide. According to the International Diabetes Federation report, this figure is expected to rise to more than 642 million in 2040, so early screening and diagnosis of diabetes patients have great significance in detecting and treating diabetes on time. Diabetes is a multifactorial metabolic disease, its diagnostic criteria is difficult to cover all the ethology, damage degree, pathogenesis and other factors, so there is a situation for uncertainty and imprecision under various aspects of medical diagnosis process. With the development of Data mining, researchers find that machine learning is playing an increasingly important role in diabetes research. Machine learning techniques can find the risky factors of diabetes and reasonable threshold of physiological parameters to unearth hidden knowledge from a huge amount of diabetes-related data, which has a very important significance for diagnosis and treatment of diabetes. So this paper provides a survey of machine learning techniques that has been applied to diabetes data screening and diagnosis of the disease. In this paper, conventional machine learning techniques are described in early screening and diagnosis of diabetes, moreover deep learning techniques which have a significance of biomedical effect are also described.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Machine Learning Techniques for Screening and Diagnosis of Diabetes: a Survey

Sun

Zhang

2019

Teh. vjesn.

View full text Add to dashboard Cite

show abstract

“…Chen et al [38] proposed a neural network to diagnose the Metabolic Syndrome without using biochemical variables such as blood glucose and cholesterol levels. The authors proposed instead the use of anthropometric variables such as Sex, Age, BMI, WC, HC, WHR, SBP, and DBP, and in an implicit way, they used Weight and Height to measure the occurrence of the Metabolic Syndrome.…”

Section: Reviewmentioning

confidence: 99%

“…This phase conducted experiments using the variables and techniques proposed in the analyzed works by Kroon [36], Ivanovic [22], and Chen [38]. The purpose was to build their performance indicators for the dataset of the population of the Atlantic coast of Colombia.…”

Section: Experimenting With Modelsmentioning

confidence: 99%

“…Chen [38] used two data mining techniques to diagnose metabolic syndrome. First, it used Principal Component Logistic Regression(PCLR) with the variables SEX, AGE, BMI, WC, HC, WHR, SBP and DBP where it obtained the principal components of the training data and the testing data getting the following Equations (11)-(13).…”

Section: Experimenting With Modelsmentioning

confidence: 99%

“…PC 1 = −0.142Sex + 0.093Age + 0.230BMI + 0.253WC + 0.192HC + 0.192W HR + 0.178SBP + 0.160DBP (11) PC 2 = 0.045Sex + 0.402Age − 0.192BMI − 0.255WC − 0.184HC − 0.199W HR + 0.494SBP + 0.394DBP 12PC 3 = 0.543Sex + 0.241Age + 0.278BMI + 0.001WC + 0.513HC − 0.429W HR + 0.046SBP − 0.207DBP (13) These were used to find the principal components through the 615 patients to test the model of logistic regression shown in the Equation 14proposed by Chen [38], using the training data.…”

Section: Experimenting With Modelsmentioning

confidence: 99%

See 2 more Smart Citations

Novel Data Mining Methodology for Healthcare Applied to a New Model to Diagnose Metabolic Syndrome without a Blood Test

et al. 2019

View full text Add to dashboard Cite

Metabolic Syndrome (MetS) is a cluster of risk factors that increase the likelihood of heart disease and diabetes mellitus. It is crucial to get diagnosed with time to take preventive measures, especially for patients in locations without proper access to laboratories and medical consultations. This work presented a new methodology to diagnose diseases using data mining that documents all the phases thoroughly for further improvement of the resulting models. We used the methodology to create a new model to diagnose the syndrome without using biochemical variables. We compared similar classification models, using their reported variables and previously obtained data from a study in Colombia. We built a new model and compared it to previous models using the holdout, and random subsampling validation methods to get performance evaluation indicators between the models. Our resulting ANN model used three hidden layers and only Hip Circumference, dichotomous Waist Circumference, and dichotomous blood pressure variables. It gave an Area Under Curve (AUC) of 87.75% by the IDF and 85.12% by HMS MetS diagnosis criteria, higher than previous models. Thanks to our new methodology, diagnosis models can be thoroughly documented for appropriate future comparisons, thus benefiting the diagnosis of the studied diseases.

show abstract

Using Neural Networks and Ensemble Techniques based on Decision Trees for Skin Permeability Prediction

et al. 2017

View full text Add to dashboard Cite

Abstract. Development of an accurate skin permeability model is becoming increasingly important as skin has been more utilized in recent development of drug delivery methods. This paper presents results of development of Artificial Neural Network (ANN) for prediction of skin permeability. The performance of developed ANN was compared to three regression algorithms used in this paper. The prediction of skin permeability is based on three input parameters: molecular weight, partition coefficient -log(P), and melting temperature for each drug. The dataset of 400 samples was used for prediction of skin permeability. Out of that number, 75% was used for training of ANN, and testing of developed ANN was performed on 100 samples from the dataset. During testing, system correctly predicted 76.7%. This dataset was also used as input to three ensemble techniques based on decision trees: REPTree, Bagging, Random SubSpaceDeveloped. It was shown that Bagging algorithm outperformed developed ANN with 81% while RandomSubspace performed at 73.3%. System can be used in laboratory conditions and can be used in the future for drug discovery.

show abstract

Evaluating the Risk of Metabolic Syndrome Based on an Artificial Intelligence Model

Cited by 13 publications

References 35 publications

Machine Learning Techniques for Screening and Diagnosis of Diabetes: a Survey

Machine Learning Techniques for Screening and Diagnosis of Diabetes: a Survey

Novel Data Mining Methodology for Healthcare Applied to a New Model to Diagnose Metabolic Syndrome without a Blood Test

Using Neural Networks and Ensemble Techniques based on Decision Trees for Skin Permeability Prediction

Contact Info

Product

Resources

About