Comparison of NN and LR classifiers in the context of screening native American elders with diabetes

Upadhyaya, Sudhi; Farahmand, Kambiz; Baker-Demaray, Twyla

doi:10.1016/j.eswa.2013.05.012

Cited by 14 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The algorithms evaluated to build the classifier are the C4.5 decision tree and a neural network with the multilayer perceptron (MLP) architecture. Both algorithms have been widely and successfully used in diabetes clinical domain with multiple purposes like retinal disease diagnosis (Bourouis, Feham, Hossain, & Zhang, 2014), impaired glucose metabolism or type 2 diabetes mellitus identification (Hische, Luis-Dominguez, & Pfeiffer, 2010;Mohlig, Floter, & Spranger, 2006;Shankaracharya, Mallick, & Shukla, 2012;Upadhyaya, Farahmand, & Baker-Demaray, 2013), or to identify significant factors influencing diabetes control (Huang, McCullagh, Black, & Harper, 2007). However, they have not been used for BG level classification in mealtime intervals.…”

Section: Learning Algorithmsmentioning

confidence: 99%

Automatic classification of glycaemia measurements to enhance data interpretation in an expert system for gestational diabetes

Caballero-Ruiz

García-Sáez

Rigla

et al. 2016

Expert Systems with Applications

View full text Add to dashboard Cite

Expert systems for diabetes care need to automatically evaluate glycaemia measurements in relationship to meals to correctly determine patients' metabolic condition and generate recommendations about therapy adjustments. Most glucose meters allow patients to manually label each measurement with a meal tag, but as this utility is not always used, a completion procedure is needed. Classification methods are usually based on predefined mealtimes and present insufficient accuracy that might affect the automatic data analysis. Expert systems in diabetes require a reliable method to manage incomplete glycaemia data so that they can determine if patients' metabolic condition is altered due to a specific meal or due to an extended fasting period. This paper presents the design and application of a classification module to automatically assign the appropriate meal and 'moment of measurement' to incomplete glycaemia data. Different machine learning techniques were studied in order to design the best classification algorithm in terms of accuracy. The selected classifier was implemented with a C4.5 decision tree with 7 input features selected with a wrapper evaluator and the genetic search algorithm, which achieved 95.45% of accuracy with the training set on cross-validation. The classification module was integrated in the Sinedie expert system for gestational diabetes care and was evaluated in a clinical environment for 8 months with 42 patients. A total of 7,113 glycaemia measurements were uploaded by patients into the Sinedie system and were completed by the "classification module". The 98.79% of the measurements were correctly classified, while patients modified the automatic classification of 1.21% of them. Classification results were improved by 21.04% compared to a classification based on predefined mealtimes. The automatic classification of glycaemia measurements minimizes the patient's intervention, allows structuring measurements in relationship to meals and makes automatic data interpretation by expert systems more reliable.

show abstract

Section: Learning Algorithmsmentioning

confidence: 99%

Automatic classification of glycaemia measurements to enhance data interpretation in an expert system for gestational diabetes

Caballero-Ruiz

García-Sáez

Rigla

et al. 2016

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…Diabetes mellitus (DM) is a complex chronic disease [1]. It is estimated that in 2030 the incidence of diabetes will be 39% higher than it was in 2000 [2]. In 2013, around 382 million adults worldwide had DM, and it is predicted that there will be 592 million people with diabetes by 2035 [3].…”

Section: Introductionmentioning

confidence: 99%

“…">Related WorkDiagnosis of DM has been extensively studied under many data mining techniques [21][22][23]. The most suitable data mining subfield for disease diagnosis is classification [2]. A plethora of techniques has been applied to data analytics in medical diagnosis, including single and ensemble classifiers [2,8,24,25].…”

mentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Medical Decision–Support Framework Based on a Heterogeneous Ensemble Classifier for Diabetes Prediction

et al. 2019

View full text Add to dashboard Cite

Early diagnosis of diabetes mellitus (DM) is critical to prevent its serious complications. An ensemble of classifiers is an effective way to enhance classification performance, which can be used to diagnose complex diseases, such as DM. This paper proposes an ensemble framework to diagnose DM by optimally employing multiple classifiers based on bagging and random subspace techniques. The proposed framework combines seven of the most suitable and heterogeneous data mining techniques, each with a separate set of suitable features. These techniques are k-nearest neighbors, naïve Bayes, decision tree, support vector machine, fuzzy decision tree, artificial neural network, and logistic regression. The framework is designed accurately by selecting, for every sub-dataset, the most suitable feature set and the most accurate classifier. It was evaluated using a real dataset collected from electronic health records of Mansura University Hospitals (Mansura, Egypt). The resulting framework achieved 90% of accuracy, 90.2% of recall = 90.2%, and 94.9% of precision. We evaluated and compared the proposed framework with many other classification algorithms. An analysis of the results indicated that the proposed ensemble framework significantly outperforms all other classifiers. It is a successful step towards constructing a personalized decision support system, which could help physicians in daily clinical practice.

show abstract

“…Los algoritmos de aprendizaje escogidos han sido el árbol de decisión C4.5 (Quinlan, J. Ross, 1993) y la red neuronal con la arquitectura perceptrón multicapa (MLP) (Haykin, S. S., 1994). La elección de estos dos algoritmos se debe a que ambos han sido probados amplia y satisfactoriamente en el dominio de la diabetes para diferentes propósitos, predicción de glucemias (Pérez-Gandía et al, 2010), diagnosis de retinopatía diabética (Bourouis et al, 2014), metabolismo de la intolerancia de la glucosa o identificación de DM2 (Möhlig et al, 2006;Hische et al, 2010;Shankaracharya et al, 2012;Upadhyaya, Farahmand and Baker-Demaray, 2013) o para identificar factores que influyan en el control diabético (Huang et al, 2007). Aunque todavía no habían sido aplicados a la clasificación de glucemias en intervalos de ingesta.…”

Section: D) Diseño Del Clasificadorunclassified

Propuesta y evaluación de un sistema de telemedicina y de ayuda a la decisión para el cuidado de pacientes con diabetes gestacional

Ruiz¹

View full text Add to dashboard Cite

show abstract

Comparison of NN and LR classifiers in the context of screening native American elders with diabetes

Cited by 14 publications

References 36 publications

Automatic classification of glycaemia measurements to enhance data interpretation in an expert system for gestational diabetes

Automatic classification of glycaemia measurements to enhance data interpretation in an expert system for gestational diabetes

A Comprehensive Medical Decision–Support Framework Based on a Heterogeneous Ensemble Classifier for Diabetes Prediction

Propuesta y evaluación de un sistema de telemedicina y de ayuda a la decisión para el cuidado de pacientes con diabetes gestacional

Contact Info

Product

Resources

About