Artificial neural network models for diagnosing heart disease: a brief review

Zebardast, Behnam; Rashidi, Rahim; Hasanpour, Taha; Gharehchopogh, Farhad Soleimanian

doi:10.7813/2075-4124.2014/6-3/a.11

Cited by 17 publications

(20 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, ANN adopts (adjust) its weights in response to the inputs at the training phase, such that the real output of ANN converges to the desired output. Once actual output of ANN becomes the desired output, the process of training the networks terminates, such that ANN leads to the least error rate [5,6,8,20,21]. After training the ANN using training data until achieving minimum error rate, other data which have no effects in training process feeds to the ANN as testing inputs.…”

Section: Proposed Modelmentioning

confidence: 99%

“…Lastly, when the program passes the training phase, and generates the right response on every input, then it is obvious that ANN's weights adjusted in a right way. Therefore, from now on these values are used for diagnosis and prediction tasks [5,6,8,20,21]. Additionally, Mean Square Error (MSE) is the performance index in the process of training PNN model.…”

Section: Proposed Modelmentioning

confidence: 99%

“…Generally, diagnosis is a complex task which requires high skill and experience. Timely diagnosis and specialized medical care of patients can reduce issues of patients, as well as treatment costs in other therapeutic courses [5,6]. A lot of diverse solutions have been proposed for different diseases up to now.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A New Artificial Neural Networks Approach for Diagnosing Diabetes Disease Type II

Soltani¹,

Jafarian²

2016

ijacsa

View full text Add to dashboard Cite

Abstract-Diabetes is one of the major health problems as it causes physical disability and even death in people. Therefore, to diagnose this dangerous disease better, methods with minimum error rate must be used. Different models of artificial neural networks have the capability to diagnose this disease with minimum error. Hence, in this paper we have used probabilistic artificial neural networks for an approach to diagnose diabetes disease type II. We took advantage of Pima Indians Diabetes dataset with 768 samples in our experiments. According to this dataset, PNN is implemented in MATLAB. Furthermore, maximizing accuracy of diagnosing the Diabetes disease type II in training and testing the Pima Indians Diabetes dataset is the performance measure in this paper. Finally, we concluded that training accuracy and testing accuracy of the proposed method is 89.56% and 81.49%, respectively.

show abstract

Section: Proposed Modelmentioning

confidence: 99%

Section: Proposed Modelmentioning

confidence: 99%

See 1 more Smart Citation

A New Artificial Neural Networks Approach for Diagnosing Diabetes Disease Type II

Soltani¹,

Jafarian²

2016

ijacsa

View full text Add to dashboard Cite

show abstract

“…Moreover, heart attack arises from the death of heart muscle cells caused by the reduction or stoppage of blood flow in the heart arteries. Although it often occurs in people over the age of 40 years, but can occur in any age groups [1]. According to the report of World Health Organization, Heart disease among other diseases is the most common cause of death.…”

Section: Introductionmentioning

confidence: 99%

“…Diagnosis of the disease can be difficult due to nonspecific symptoms or other common symptoms with the other illnesses. Human life depends on effective work of heart [1,2]. The important factors that increase the risk of heart disease include smoking, high blood pressure, high blood cholesterol, family health history, physical inactivity, obesity, etc.…”

Section: Introductionmentioning

confidence: 99%

A Novel Probabilistic Artificial Neural Networks Approach for Diagnosing Heart Disease

Sa'di¹,

Hashemi²,

Abdollapour³

et al. 2015

IJFCST

View full text Add to dashboard Cite

In today's world one of the most common diseases are heart disease which its mortality and disability is high. Therefore, heart disease is one of the biggest health problems in the world. Since the diagnosis of heart disease in people is very important, a method should be used in the right diagnosis of heart diseases that have the least errors in heart disease diagnosis. For this reason, in this paper, Probabilistic Neural Networks (PNNs) for the diagnosis of heart disease from a dataset that includes 303 samples from different patients is used. In this paper, we have implemented PNN in the MATLAB environment.As well as, the efficiency criteria in this paper is to maximize accuracy of heart disease diagnosis in the process of training and testing. According to the Cleveland dataset which contains 303 samples, we found that the accuracy of training and test accuracy are 87% and 75% respectively.

show abstract

Enhanced deep residual network for bone classification and abnormality detection

Guo

2022

Medical Physics

View full text Add to dashboard Cite

Purpose A two‐stage deep learning framework for bone classification and abnormality detection is proposed based on X‐rays. The primary focus is on improving the speed of orthopedic disease diagnosis and helping physicians reduce the probability of false diagnoses. Methods The method is based on two stages. In the first stage, one classifier with ResNeXt50 as the backbone is used to classify bones to eliminate the effect of bone type differences on abnormality detection. In the second stage, seven anomaly detectors are trained based on each type of training data. The seven detectors tested the seven results of the first stage, respectively. Pretrained models, data augmentation, focal loss, label smoothing loss, LR‐attenuation and early stopping are used to improve performance and reduce the risk of overfitting. Results Experiments are based on the largest dataset for bone abnormality detection, MURA. In the first stage for bone classification, we got an accuracy of 96.69%, a sensitivity of 96.69%, a specificity of 99.46%, and an F1 score of 96.42%. In the second stage for abnormality detection, we got an accuracy of 84.15%, a sensitivity of 84.15%, a specificity of 87.50%, an F1 score of 84.10%, a Cohen's Kappa of 0.72, and an area under the ROC curve (AUC) score of 0.90. Conclusions Compared with other excellent convolutional neural network models, the framework's effectiveness was verified with better accuracy, sensitivity, specificity, F1 score, Cohen's Kappa score, and AUC score for bone classification and abnormality detection.

show abstract

Artificial neural network models for diagnosing heart disease: a brief review

Cited by 17 publications

References 0 publications

A New Artificial Neural Networks Approach for Diagnosing Diabetes Disease Type II

A New Artificial Neural Networks Approach for Diagnosing Diabetes Disease Type II

A Novel Probabilistic Artificial Neural Networks Approach for Diagnosing Heart Disease

Enhanced deep residual network for bone classification and abnormality detection

Contact Info

Product

Resources

About