Gestational Diabetes Mellitus(GDM)is one of the commonly occurring diseases among women during pregnancy.Oral Glucose Tolerance Test(OGTT)is followed universally in the diagnosis of GDM diagnosis at early pregnancy wh...Gestational Diabetes Mellitus(GDM)is one of the commonly occurring diseases among women during pregnancy.Oral Glucose Tolerance Test(OGTT)is followed universally in the diagnosis of GDM diagnosis at early pregnancy which is costly and ineffective.So,there is a need to design an effective and automated GDM diagnosis and classification model.The recent developments in the field of Deep Learning(DL)are useful in diagnosing different diseases.In this view,the current research article presents a new outlier detection with deep-stacked Autoencoder(OD-DSAE)model for GDM diagnosis and classification.The goal of the proposed OD-DSAE model is to find out those mothers with high risks and make them undergo earlier diagnosis,monitoring,and treatment compared to low-risk women.The presented ODDSAE model involves three major processes namely,preprocessing,outlier detection,and classification.In the first step i.e.,data preprocessing,there exists three stages namely,format conversion,class labelling,and missing value replacement using k-nearest neighbors(KNN)model.Outliers are superior values which considerably varies from other data observations.So,it might represent the variability in measurement,experimental errors or novelty too.So,Hierarchical Clustering(HC)-based outlier detection technique is incorporated in OD-DSAE model,and thereby classification performance can be improved.The proposed model was simulated using Python 3.6.5 on a dataset collected by the researcher themselves.A series of experiments was conducted and the results were investigated under different aspects.The experimental outcomes inferred that the OD-DSAE model has outperformed the compared methods and achieved high precision of 96.17%,recall of 98.69%,specificity of 89.50%,accuracy of 96.18%,and F-score of 97.41%.展开更多
Gestational Diabetes Mellitus(GDM)is an illness that represents a certain degree of glucose intolerance with onset or first recognition during pregnancy.In the past few decades,numerous investigations were conducted u...Gestational Diabetes Mellitus(GDM)is an illness that represents a certain degree of glucose intolerance with onset or first recognition during pregnancy.In the past few decades,numerous investigations were conducted upon early identification of GDM.Machine Learning(ML)methods are found to be efficient prediction techniques with significant advantage over statistical models.In this view,the current research paper presents an ensemble of ML-based GDM prediction and classification models.The presented model involves three steps such as preprocessing,classification,and ensemble voting process.At first,the input medical data is preprocessed in four levels namely,format conversion,class labeling,replacement of missing values,and normalization.Besides,four ML models such as Logistic Regression(LR),k-Nearest Neighbor(KNN),Support Vector Machine(SVM),and Random Forest(RF)are used for classification.In addition to the above,RF,LR,KNN and SVM classifiers are integrated to perform the final classification in which a voting classifier is also used.In order to investigate the proficiency of the proposed model,the authors conducted extensive set of simulations and the results were examined under distinct aspects.Particularly,the ensemble model has outperformed the classical ML models with a precision of 94%,recall of 94%,accuracy of 94.24%,and F-score of 94%.展开更多
基金The authors received no specific funding for this study。
文摘Gestational Diabetes Mellitus(GDM)is one of the commonly occurring diseases among women during pregnancy.Oral Glucose Tolerance Test(OGTT)is followed universally in the diagnosis of GDM diagnosis at early pregnancy which is costly and ineffective.So,there is a need to design an effective and automated GDM diagnosis and classification model.The recent developments in the field of Deep Learning(DL)are useful in diagnosing different diseases.In this view,the current research article presents a new outlier detection with deep-stacked Autoencoder(OD-DSAE)model for GDM diagnosis and classification.The goal of the proposed OD-DSAE model is to find out those mothers with high risks and make them undergo earlier diagnosis,monitoring,and treatment compared to low-risk women.The presented ODDSAE model involves three major processes namely,preprocessing,outlier detection,and classification.In the first step i.e.,data preprocessing,there exists three stages namely,format conversion,class labelling,and missing value replacement using k-nearest neighbors(KNN)model.Outliers are superior values which considerably varies from other data observations.So,it might represent the variability in measurement,experimental errors or novelty too.So,Hierarchical Clustering(HC)-based outlier detection technique is incorporated in OD-DSAE model,and thereby classification performance can be improved.The proposed model was simulated using Python 3.6.5 on a dataset collected by the researcher themselves.A series of experiments was conducted and the results were investigated under different aspects.The experimental outcomes inferred that the OD-DSAE model has outperformed the compared methods and achieved high precision of 96.17%,recall of 98.69%,specificity of 89.50%,accuracy of 96.18%,and F-score of 97.41%.
文摘Gestational Diabetes Mellitus(GDM)is an illness that represents a certain degree of glucose intolerance with onset or first recognition during pregnancy.In the past few decades,numerous investigations were conducted upon early identification of GDM.Machine Learning(ML)methods are found to be efficient prediction techniques with significant advantage over statistical models.In this view,the current research paper presents an ensemble of ML-based GDM prediction and classification models.The presented model involves three steps such as preprocessing,classification,and ensemble voting process.At first,the input medical data is preprocessed in four levels namely,format conversion,class labeling,replacement of missing values,and normalization.Besides,four ML models such as Logistic Regression(LR),k-Nearest Neighbor(KNN),Support Vector Machine(SVM),and Random Forest(RF)are used for classification.In addition to the above,RF,LR,KNN and SVM classifiers are integrated to perform the final classification in which a voting classifier is also used.In order to investigate the proficiency of the proposed model,the authors conducted extensive set of simulations and the results were examined under distinct aspects.Particularly,the ensemble model has outperformed the classical ML models with a precision of 94%,recall of 94%,accuracy of 94.24%,and F-score of 94%.
