Heart diagnosis is not always possible at every medical center, especially in the rural areas where less support and care, due to lack of advanced heart diagnosis equipment. Also, physician intuition and experience ar...Heart diagnosis is not always possible at every medical center, especially in the rural areas where less support and care, due to lack of advanced heart diagnosis equipment. Also, physician intuition and experience are not always sufficient to achieve high quality medical procedures results. Therefore, medical errors and undesirable results are reasons for a need for unconventional computer-based diagnosis systems, which in turns reduce medical fatal errors, increasing the patient safety and save lives. The proposed solution, which is based on an Artificial Neural Networks (ANNs), provides a decision support system to identify three main heart diseases: mitral stenosis, aortic stenosis and ventricular septal defect. Furthermore, the system deals with an encouraging opportunity to develop an operational screening and testing device for heart disease diagnosis and can deliver great assistance for clinicians to make advanced heart diagnosis. Using real medical data, series of experiments have been conducted to examine the performance and accuracy of the proposed solution. Compared results revealed that the system performance and accuracy are acceptable, with a heart diseases classification accuracy of 92%.展开更多
Computational electrocardiogram (ECG) analysis is one of the most crucial topics in cardiovascular research domain especially in identifying abnormalities of heart condition through cardiac arrhythmia symptom. There a...Computational electrocardiogram (ECG) analysis is one of the most crucial topics in cardiovascular research domain especially in identifying abnormalities of heart condition through cardiac arrhythmia symptom. There are many existing works focusing on recognizing the abnormalities condition through arrhythmia symptom, however, the detection rate is still unsatisfied. Arrhythmia consists of more than 14 various types of symptoms. Therefore, most of the existing research found it difficult to classify the entire symptom and maintain the overall accuracy especially in long hour data. In this study, a new mechanism to overcome this issue is proposed: A combination between Autocorrelation methods with K-Nearest Neighbor (KNN) classifier method is introduced to accurately and robustly detect 14 types of Arrhythmia symptom regardless of the origin of the symptom in a long hour data. Moreover, variability analysis based on periodic autocorrelation result is proposed and used for classification procedure. 1 minute and 12 hours duration data was chosen to compare and signify the most suitable time duration to detect Arrhythmia symptom. In addition, an analytical result and discussion is done to provide justification behind each tendency of Arrhythmia and Normal Sinus symptom in autocorrelation result. As the result of proposed method performance evaluation, it was revealed that the accuracy of 95.5% in discriminating Arrhythmia from Normal Sinus data is achieved. Furthermore, it was confirmed that utilizing autocorrelation result in long hour data can help to generalize abnormalities characteristic of heart condition like Arrhythmia symptom. It is concluded that the proposed method can be useful to diagnose abnormalities of heart condition at any stage.展开更多
文摘Heart diagnosis is not always possible at every medical center, especially in the rural areas where less support and care, due to lack of advanced heart diagnosis equipment. Also, physician intuition and experience are not always sufficient to achieve high quality medical procedures results. Therefore, medical errors and undesirable results are reasons for a need for unconventional computer-based diagnosis systems, which in turns reduce medical fatal errors, increasing the patient safety and save lives. The proposed solution, which is based on an Artificial Neural Networks (ANNs), provides a decision support system to identify three main heart diseases: mitral stenosis, aortic stenosis and ventricular septal defect. Furthermore, the system deals with an encouraging opportunity to develop an operational screening and testing device for heart disease diagnosis and can deliver great assistance for clinicians to make advanced heart diagnosis. Using real medical data, series of experiments have been conducted to examine the performance and accuracy of the proposed solution. Compared results revealed that the system performance and accuracy are acceptable, with a heart diseases classification accuracy of 92%.
文摘Computational electrocardiogram (ECG) analysis is one of the most crucial topics in cardiovascular research domain especially in identifying abnormalities of heart condition through cardiac arrhythmia symptom. There are many existing works focusing on recognizing the abnormalities condition through arrhythmia symptom, however, the detection rate is still unsatisfied. Arrhythmia consists of more than 14 various types of symptoms. Therefore, most of the existing research found it difficult to classify the entire symptom and maintain the overall accuracy especially in long hour data. In this study, a new mechanism to overcome this issue is proposed: A combination between Autocorrelation methods with K-Nearest Neighbor (KNN) classifier method is introduced to accurately and robustly detect 14 types of Arrhythmia symptom regardless of the origin of the symptom in a long hour data. Moreover, variability analysis based on periodic autocorrelation result is proposed and used for classification procedure. 1 minute and 12 hours duration data was chosen to compare and signify the most suitable time duration to detect Arrhythmia symptom. In addition, an analytical result and discussion is done to provide justification behind each tendency of Arrhythmia and Normal Sinus symptom in autocorrelation result. As the result of proposed method performance evaluation, it was revealed that the accuracy of 95.5% in discriminating Arrhythmia from Normal Sinus data is achieved. Furthermore, it was confirmed that utilizing autocorrelation result in long hour data can help to generalize abnormalities characteristic of heart condition like Arrhythmia symptom. It is concluded that the proposed method can be useful to diagnose abnormalities of heart condition at any stage.
