Diagnosis of cardiac abnormalities based on phonocardiogram using a novel fuzzy matching feature extraction method
Abstract Background The diagnosis of cardiac abnormalities based on heart sound signal is a research hotspot in recent years. The early diagnosis of cardiac abnormalities has a crucial significance for the treatment of heart diseases. Methods For the sake of achieving more practical clinical applica...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-09-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-022-01976-6 |
| _version_ | 1797397928353988608 |
|---|---|
| author | Wanrong Yang Jiajie Xu Junhong Xiang Zhonghong Yan Hengyu Zhou Binbin Wen Hai Kong Rui Zhu Wang Li |
| author_facet | Wanrong Yang Jiajie Xu Junhong Xiang Zhonghong Yan Hengyu Zhou Binbin Wen Hai Kong Rui Zhu Wang Li |
| author_sort | Wanrong Yang |
| collection | DOAJ |
| description | Abstract Background The diagnosis of cardiac abnormalities based on heart sound signal is a research hotspot in recent years. The early diagnosis of cardiac abnormalities has a crucial significance for the treatment of heart diseases. Methods For the sake of achieving more practical clinical applications of automatic recognition of cardiac abnormalities, here we proposed a novel fuzzy matching feature extraction method. First of all, a group of Gaussian wavelets are selected and then optimized based on a template signal. Convolutional features of test signal and the template signal are then computed. Matching degree and matching energy features between template signal and test signal in time domain and frequency domain are then extracted. To test performance of proposed feature extraction method, machine learning algorithms such as K-nearest neighbor, support vector machine, random forest and multilayer perceptron with grid search parameter optimization are constructed to recognize heart disease using the extracted features based on phonocardiogram signals. Results As a result, we found that the best classification accuracy of random forest reaches 96.5% under tenfold cross validation using the features extracted by the proposed method. Further, Mel-Frequency Cepstral Coefficients of phonocardiogram signals combing with features extracted by our algorithm are evaluated. Accuracy, sensitivity and specificity of integrated features reaches 99.0%, 99.4% and 99.7% respectively when using support vector machine, which achieves the best performance among all reported algorithms based on the same dataset. On several common features, we used independent sample t-tests. The results revealed that there are significant differences (p < 0.05) between 5 categories. Conclusion It can be concluded that our proposed fuzzy matching feature extraction method is a practical approach to extract powerful and interpretable features from one-dimensional signals for heart sound diagnostics and other pattern recognition task. |
| first_indexed | 2024-03-09T01:17:17Z |
| format | Article |
| id | doaj.art-1e66ddf569b74358aa195770c1bc64c4 |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-03-09T01:17:17Z |
| publishDate | 2022-09-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-1e66ddf569b74358aa195770c1bc64c42023-12-10T12:21:17ZengBMCBMC Medical Informatics and Decision Making1472-69472022-09-0122111310.1186/s12911-022-01976-6Diagnosis of cardiac abnormalities based on phonocardiogram using a novel fuzzy matching feature extraction methodWanrong Yang0Jiajie Xu1Junhong Xiang2Zhonghong Yan3Hengyu Zhou4Binbin Wen5Hai Kong6Rui Zhu7Wang Li8School of Pharmacy and Bioengineering, Chongqing University of TechnologySchool of Pharmacy and Bioengineering, Chongqing University of TechnologySchool of Pharmacy and Bioengineering, Chongqing University of TechnologySchool of Pharmacy and Bioengineering, Chongqing University of TechnologySchool of Pharmacy and Bioengineering, Chongqing University of TechnologySchool of Pharmacy and Bioengineering, Chongqing University of TechnologySchool of Pharmacy and Bioengineering, Chongqing University of TechnologySchool of Pharmacy and Bioengineering, Chongqing University of TechnologySchool of Pharmacy and Bioengineering, Chongqing University of TechnologyAbstract Background The diagnosis of cardiac abnormalities based on heart sound signal is a research hotspot in recent years. The early diagnosis of cardiac abnormalities has a crucial significance for the treatment of heart diseases. Methods For the sake of achieving more practical clinical applications of automatic recognition of cardiac abnormalities, here we proposed a novel fuzzy matching feature extraction method. First of all, a group of Gaussian wavelets are selected and then optimized based on a template signal. Convolutional features of test signal and the template signal are then computed. Matching degree and matching energy features between template signal and test signal in time domain and frequency domain are then extracted. To test performance of proposed feature extraction method, machine learning algorithms such as K-nearest neighbor, support vector machine, random forest and multilayer perceptron with grid search parameter optimization are constructed to recognize heart disease using the extracted features based on phonocardiogram signals. Results As a result, we found that the best classification accuracy of random forest reaches 96.5% under tenfold cross validation using the features extracted by the proposed method. Further, Mel-Frequency Cepstral Coefficients of phonocardiogram signals combing with features extracted by our algorithm are evaluated. Accuracy, sensitivity and specificity of integrated features reaches 99.0%, 99.4% and 99.7% respectively when using support vector machine, which achieves the best performance among all reported algorithms based on the same dataset. On several common features, we used independent sample t-tests. The results revealed that there are significant differences (p < 0.05) between 5 categories. Conclusion It can be concluded that our proposed fuzzy matching feature extraction method is a practical approach to extract powerful and interpretable features from one-dimensional signals for heart sound diagnostics and other pattern recognition task.https://doi.org/10.1186/s12911-022-01976-6Feature engineeringPhonocardiogramMachine learningWaveletMatching feature extraction |
| spellingShingle | Wanrong Yang Jiajie Xu Junhong Xiang Zhonghong Yan Hengyu Zhou Binbin Wen Hai Kong Rui Zhu Wang Li Diagnosis of cardiac abnormalities based on phonocardiogram using a novel fuzzy matching feature extraction method BMC Medical Informatics and Decision Making Feature engineering Phonocardiogram Machine learning Wavelet Matching feature extraction |
| title | Diagnosis of cardiac abnormalities based on phonocardiogram using a novel fuzzy matching feature extraction method |
| title_full | Diagnosis of cardiac abnormalities based on phonocardiogram using a novel fuzzy matching feature extraction method |
| title_fullStr | Diagnosis of cardiac abnormalities based on phonocardiogram using a novel fuzzy matching feature extraction method |
| title_full_unstemmed | Diagnosis of cardiac abnormalities based on phonocardiogram using a novel fuzzy matching feature extraction method |
| title_short | Diagnosis of cardiac abnormalities based on phonocardiogram using a novel fuzzy matching feature extraction method |
| title_sort | diagnosis of cardiac abnormalities based on phonocardiogram using a novel fuzzy matching feature extraction method |
| topic | Feature engineering Phonocardiogram Machine learning Wavelet Matching feature extraction |
| url | https://doi.org/10.1186/s12911-022-01976-6 |
| work_keys_str_mv | AT wanrongyang diagnosisofcardiacabnormalitiesbasedonphonocardiogramusinganovelfuzzymatchingfeatureextractionmethod AT jiajiexu diagnosisofcardiacabnormalitiesbasedonphonocardiogramusinganovelfuzzymatchingfeatureextractionmethod AT junhongxiang diagnosisofcardiacabnormalitiesbasedonphonocardiogramusinganovelfuzzymatchingfeatureextractionmethod AT zhonghongyan diagnosisofcardiacabnormalitiesbasedonphonocardiogramusinganovelfuzzymatchingfeatureextractionmethod AT hengyuzhou diagnosisofcardiacabnormalitiesbasedonphonocardiogramusinganovelfuzzymatchingfeatureextractionmethod AT binbinwen diagnosisofcardiacabnormalitiesbasedonphonocardiogramusinganovelfuzzymatchingfeatureextractionmethod AT haikong diagnosisofcardiacabnormalitiesbasedonphonocardiogramusinganovelfuzzymatchingfeatureextractionmethod AT ruizhu diagnosisofcardiacabnormalitiesbasedonphonocardiogramusinganovelfuzzymatchingfeatureextractionmethod AT wangli diagnosisofcardiacabnormalitiesbasedonphonocardiogramusinganovelfuzzymatchingfeatureextractionmethod |