A New Method for Heart Disease Detection: Long Short-Term Feature Extraction from Heart Sound Data
Heart sounds have been extensively studied for heart disease diagnosis for several decades. Traditional machine learning algorithms applied in the literature have typically partitioned heart sounds into small windows and employed feature extraction methods to classify samples. However, as there is n...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/13/5835 |
| _version_ | 1797590861946552320 |
|---|---|
| author | Mesut Guven Fatih Uysal |
| author_facet | Mesut Guven Fatih Uysal |
| author_sort | Mesut Guven |
| collection | DOAJ |
| description | Heart sounds have been extensively studied for heart disease diagnosis for several decades. Traditional machine learning algorithms applied in the literature have typically partitioned heart sounds into small windows and employed feature extraction methods to classify samples. However, as there is no optimal window length that can effectively represent the entire signal, windows may not provide a sufficient representation of the underlying data. To address this issue, this study proposes a novel approach that integrates window-based features with features extracted from the entire signal, thereby improving the overall accuracy of traditional machine learning algorithms. Specifically, feature extraction is carried out using two different time scales. Short-term features are computed from five-second fragments of heart sound instances, whereas long-term features are extracted from the entire signal. The long-term features are combined with the short-term features to create a feature pool known as long short-term features, which is then employed for classification. To evaluate the performance of the proposed method, various traditional machine learning algorithms with various models are applied to the PhysioNet/CinC Challenge 2016 dataset, which is a collection of diverse heart sound data. The experimental results demonstrate that the proposed feature extraction approach increases the accuracy of heart disease diagnosis by nearly 10%. |
| first_indexed | 2024-03-11T01:29:29Z |
| format | Article |
| id | doaj.art-89d1f25ed6b34268ba03c6e5da51b9a9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T01:29:29Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-89d1f25ed6b34268ba03c6e5da51b9a92023-11-18T17:27:28ZengMDPI AGSensors1424-82202023-06-012313583510.3390/s23135835A New Method for Heart Disease Detection: Long Short-Term Feature Extraction from Heart Sound DataMesut Guven0Fatih Uysal1Gendarmerie and Coast Guard Academy, Ankara 06805, TurkeyDepartment of Electrical and Electronics Engineering, Faculty of Engineering and Architecture, Kafkas University, Kars 36100, TurkeyHeart sounds have been extensively studied for heart disease diagnosis for several decades. Traditional machine learning algorithms applied in the literature have typically partitioned heart sounds into small windows and employed feature extraction methods to classify samples. However, as there is no optimal window length that can effectively represent the entire signal, windows may not provide a sufficient representation of the underlying data. To address this issue, this study proposes a novel approach that integrates window-based features with features extracted from the entire signal, thereby improving the overall accuracy of traditional machine learning algorithms. Specifically, feature extraction is carried out using two different time scales. Short-term features are computed from five-second fragments of heart sound instances, whereas long-term features are extracted from the entire signal. The long-term features are combined with the short-term features to create a feature pool known as long short-term features, which is then employed for classification. To evaluate the performance of the proposed method, various traditional machine learning algorithms with various models are applied to the PhysioNet/CinC Challenge 2016 dataset, which is a collection of diverse heart sound data. The experimental results demonstrate that the proposed feature extraction approach increases the accuracy of heart disease diagnosis by nearly 10%.https://www.mdpi.com/1424-8220/23/13/5835machine learninglong short-term featuresfeature selectionauscultationheart abnormalitiesheart sound classification |
| spellingShingle | Mesut Guven Fatih Uysal A New Method for Heart Disease Detection: Long Short-Term Feature Extraction from Heart Sound Data Sensors machine learning long short-term features feature selection auscultation heart abnormalities heart sound classification |
| title | A New Method for Heart Disease Detection: Long Short-Term Feature Extraction from Heart Sound Data |
| title_full | A New Method for Heart Disease Detection: Long Short-Term Feature Extraction from Heart Sound Data |
| title_fullStr | A New Method for Heart Disease Detection: Long Short-Term Feature Extraction from Heart Sound Data |
| title_full_unstemmed | A New Method for Heart Disease Detection: Long Short-Term Feature Extraction from Heart Sound Data |
| title_short | A New Method for Heart Disease Detection: Long Short-Term Feature Extraction from Heart Sound Data |
| title_sort | new method for heart disease detection long short term feature extraction from heart sound data |
| topic | machine learning long short-term features feature selection auscultation heart abnormalities heart sound classification |
| url | https://www.mdpi.com/1424-8220/23/13/5835 |
| work_keys_str_mv | AT mesutguven anewmethodforheartdiseasedetectionlongshorttermfeatureextractionfromheartsounddata AT fatihuysal anewmethodforheartdiseasedetectionlongshorttermfeatureextractionfromheartsounddata AT mesutguven newmethodforheartdiseasedetectionlongshorttermfeatureextractionfromheartsounddata AT fatihuysal newmethodforheartdiseasedetectionlongshorttermfeatureextractionfromheartsounddata |