Use of an Artificial Neural Network for the Diagnosis of Myocardial Infarction

Baxt, William G.

doi:10.7326/0003-4819-115-11-843

Cited by 427 publications

(178 citation statements)

References 15 publications

Supporting

Mentioning

172

Contrasting

Unclassified

Order By: Relevance

“…Fuzzy expert systems [31,32] manage to keep this feature without applying strict threshold values. ANNs [4,21,[26][27][28][29] due to their non-linear characteristics and learning capabilities have provided good performance results. The above methods when tested with the ESC ST-T database demonstrated a Se that ranged from 71 to 94% and a PPA from 66 to 90%.…”

Section: Discussionmentioning

confidence: 99%

“…The above methods when tested with the ESC ST-T database demonstrated a Se that ranged from 71 to 94% and a PPA from 66 to 90%. Some works [3][4][5]15,20,21,25,32] report better results, which are not comparable since they refer to their own datasets. In [28] a non-linear PCA neural network is proposed for ischemic beat classification instead of episode detection.…”

Section: Discussionmentioning

confidence: 99%

“…The accuracy of beat classification influences ischemic episode definition where sequences of ischemic beats need to be identified. Various methods have been proposed for ischemia detection based on set of rules [2,5,15,20,[25][26][27], artificial neural networks (ANNs) [4,21,[26][27][28][29], fuzzy logic [31,32] or other signal analysis techniques [3,11,13,16,30].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An ischemia detection method based on artificial neural networks

Papaloukas

Fotiadis

Likas

et al. 2002

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

An automated technique was developed for the detection of ischemic episodes in long duration electrocardiographic (ECG) recordings that employs an artificial neural network. In order to train the network for beat classification, a cardiac beat dataset was constructed based on recordings from the European Society of Cardiology (ESC) ST-T database. The network was trained using a Bayesian regularisation method. The raw ECG signal containing the ST segment and the T wave of each beat were the inputs to the beat classification system and the output was the classification of the beat. The input to the network was produced through a principal component analysis (PCA) to achieve dimensionality reduction. The network performance in beat classification was tested on the cardiac beat database providing 90% sensitivity (Se) and 90% specificity (Sp). The neural beat classifier is integrated in a four-stage procedure for ischemic episode detection. The whole system was evaluated on the ESC ST-T database. When aggregate gross statistics was used the Se was 90% and the positive predictive accuracy (PPA) 89%. When aggregate average statistics was used the Se became 86% and the PPA 87%. These results are better than other reported. #

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An ischemia detection method based on artificial neural networks

Papaloukas

Fotiadis

Likas

et al. 2002

Artificial Intelligence in Medicine

View full text Add to dashboard Cite

show abstract

“…Second, as opposed to statistical methods, ANNs are non-linear and may perform better than their statistical, linear counterparts (10). This means that they may identify relationships between variables not previously appreciated (8). However, statistical methods and ANNs are essentially identical in many respects (6).…”

Section: Discussionmentioning

confidence: 99%

Artificial neural network-aided image analysis system for cell counting

Sjöström¹,

Frydel²,

Wahlberg

1999

Cytometry

View full text Add to dashboard Cite

Background: In histological preparations containing debris and synthetic materials, it is difficult to automate cell counting using standard image analysis tools, i.e., systems that rely on boundary contours, histogram thresholding, etc. In an attempt to mimic manual cell recognition, an automated cell counter was constructed using a combination of artificial intelligence and standard image analysis methods. Methods: Artificial neural network (ANN) methods were applied on digitized microscopy fields without pre‐ANN feature extraction. A three‐layer feed‐forward network with extensive weight sharing in the first hidden layer was employed and trained on 1,830 examples using the error back‐propagation algorithm on a Power Macintosh 7300/180 desktop computer. The optimal number of hidden neurons was determined and the trained system was validated by comparison with blinded human counts. System performance at 50x and 100x magnification was evaluated. Results: The correlation index at 100x magnification neared person‐to‐person variability, while 50x magnification was not useful. The system was approximately six times faster than an experienced human. Conclusions: ANN‐based automated cell counting in noisy histological preparations is feasible. Consistent histology and computer power are crucial for system performance. The system provides several benefits, such as speed of analysis and consistency, and frees up personnel for other tasks. Cytometry 36:18–26, 1999. © 1999 Wiley‐Liss, Inc.

show abstract

“…Generally, neural networks have performed at least as well as other methods, with coronary artery disease and breast cancer among the most widely studied databases. For example, in a well publicized study, Baxt (1991) used backpropagation to identify myocardial infarction; on a coronary artery disease database, Rosenberg, Ercl, & Atlan (1993) found performance of a radial basis function network to be comparable with that of human experts and superior to various backpropagation methods; and for breast cancer detection, researchers have successfully applied backpropagation (Floyd et al 1994;, ART 2 and fractal analysis (Downes, 1994), the neocognitron (Lo et al, 1995), convolution neural networks , and decision trees (Bohren, Hadzikadic, & Hanley, 1995).…”

Section: Neural Network and Medical Diagnosismentioning

confidence: 99%