A multilayer perceptron-based medical decision support system for heart disease diagnosis

Yan, Hongmei; Jiang, Yingtao; Zheng, Jun; Peng, Chenglin; Li, Qinghui

doi:10.1016/j.eswa.2005.07.022

Cited by 283 publications

(139 citation statements)

References 20 publications

Supporting

Mentioning

136

Contrasting

Unclassified

Order By: Relevance

“…The multilayer perceptron (MLP) is one of the most popular supervised ANN models due to its architecture and simple algorithm [40]. A MLP consists on an input layer that receives the values of the variables, one or more hidden layers where the adjustment processes are carried out and the output layer [16,41].…”

Section: Aid Decision Algorithms 321 Multilayer Perceptron (Mlp)mentioning

confidence: 99%

Aid decision algorithms to estimate the risk in congenital heart surgery

Ruiz-Fernández

Torra

Soriano-Payá

et al. 2016

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

A c c e p t e d M a n u s c r i p t Highlights  We propose an alternative system for classifying the risk in paediatric congenital heart surgery. Four methods are tested: a perceptron multilayer, self-organising maps, a radial basis function neural network and decision trees. We obtain an accuracy of 99.87% (using pre and post-surgical data) and 83% (using just pre-surgical data).Page 2 In this paper, we have tested the suitability of using different artificial intelligence-based algorithms for decision support when classifying the risk of congenital heart surgery. In this sense, classification of those surgical risks provides enormous benefits as the a priori estimation of surgical outcomes depending on either the type of disease or the type of repair, and other elements that influence the final result. This preventive estimation may help to avoid future complications, or even death. MethodsWe have evaluated four machine learning algorithms to achieve our objective: multilayer perceptron, self-organizing map, radial basis function networks and decision trees. The architectures implemented have the aim of classifying among three types of surgical risk: low complexity, medium complexity and high complexity. ResultsAccuracy outcomes achieved range between 80% and 99%, being the multilayer perceptron method the one that offered a higher hit ratio. ConclusionsAccording to the results, it is feasible to develop a clinical decision support system using the evaluated algorithms. Such system would help cardiology specialists, paediatricians and surgeons to forecast the level of risk related to a congenital heart disease surgery.

show abstract

Section: Aid Decision Algorithms 321 Multilayer Perceptron (Mlp)mentioning

confidence: 99%

Aid decision algorithms to estimate the risk in congenital heart surgery

Ruiz-Fernández

Torra

Soriano-Payá

et al. 2016

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

show abstract

“…Each node in MLP can be modelled as an artificial neuron (Fig. 1.) [8] In the MLP, each neuron j in the hidden layer computes the sum of input x i weighted by respective connection weight w ij and calculates its output y j as a function of the sum.…”

Section: Structure Of the Used Artificial Neural Networkmentioning

confidence: 99%

Road Detection from High Satellite Images Using Neural Networks

Kahraman¹,

Turan²,

Karaş³

2015

IJMO

View full text Add to dashboard Cite

Abstract-In this paper, we propose a road detection model approach based on neural networks from satellite images. The model is based on Multilayer Perceptron (MLP) which is one of the most preferred artificial neural network architecture in classification and prediction problems. According the neural network, the RGB values are used for deciding the pixel belongs to road or not. The found road pixels are marked in the output image.

show abstract

“…Several studies can be found in the related literature about data-driven systems. Some of these studies can be referred to Bayesian networks 5 , Rough sets 6 and artificial neural networks 7 . Data-driven systems are more flexible compared to the rule-based systems and they have the ability to learn by themselves.…”

Section: Introductionmentioning

confidence: 99%

Comparison of different inference algorithms for medical decision making

Köse¹,

Sever²,

Bal³

et al. 2014

IJCIS

View full text Add to dashboard Cite

A medical diagnosis system (DRCAD), which consists of two sub-modules Bayesian and rule-based inference models, is presented in this study. Three types of tests are conducted to assess the performances of the models producing synthetic data based on the ALARM network. The results indicate that the linear combination of the aforementioned models leads to a 5% and a 30% improvement in medical diagnosis when compared to the "Rule Based Method" and the "Bayesian Network Based Method", respectively.

show abstract

A multilayer perceptron-based medical decision support system for heart disease diagnosis

Cited by 283 publications

References 20 publications

Aid decision algorithms to estimate the risk in congenital heart surgery

Aid decision algorithms to estimate the risk in congenital heart surgery

Road Detection from High Satellite Images Using Neural Networks

Comparison of different inference algorithms for medical decision making

Contact Info

Product

Resources

About