Simple and Powerful PCG Classification Method Based on Selection and Transfer Learning for Precision Medicine Application
The World Health Organization (WHO) highlights that cardiovascular diseases (CVDs) are one of the leading causes of death globally, with an estimated rise to over 23.6 million deaths by 2030. This alarming trend can be attributed to our unhealthy lifestyles and lack of attention towards early CVD di...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/10/3/294 |
| _version_ | 1797613409053704192 |
|---|---|
| author | Ahmed Barnawi Mehrez Boulares Rim Somai |
| author_facet | Ahmed Barnawi Mehrez Boulares Rim Somai |
| author_sort | Ahmed Barnawi |
| collection | DOAJ |
| description | The World Health Organization (WHO) highlights that cardiovascular diseases (CVDs) are one of the leading causes of death globally, with an estimated rise to over 23.6 million deaths by 2030. This alarming trend can be attributed to our unhealthy lifestyles and lack of attention towards early CVD diagnosis. Traditional cardiac auscultation, where a highly qualified cardiologist listens to the heart sounds, is a crucial diagnostic method, but not always feasible or affordable. Therefore, developing accessible and user-friendly CVD recognition solutions can encourage individuals to integrate regular heart screenings into their routine. Although many automatic CVD screening methods have been proposed, most of them rely on complex prepocessing steps and heart cycle segmentation processes. In this work, we introduce a simple and efficient approach for recognizing normal and abnormal PCG signals using Physionet data. We employ data selection techniques such as kernel density estimation (KDE) for signal duration extraction, signal-to-noise Ratio (SNR), and GMM clustering to improve the performance of 17 pretrained Keras CNN models. Our results indicate that using KDE to select the appropriate signal duration and fine-tuning the VGG19 model results in excellent classification performance with an overall accuracy of 0.97, sensitivity of 0.946, precision of 0.944, and specificity of 0.946. |
| first_indexed | 2024-03-11T06:55:24Z |
| format | Article |
| id | doaj.art-5604a980c314437fafd2f772f9cb2749 |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-11T06:55:24Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-5604a980c314437fafd2f772f9cb27492023-11-17T09:39:15ZengMDPI AGBioengineering2306-53542023-02-0110329410.3390/bioengineering10030294Simple and Powerful PCG Classification Method Based on Selection and Transfer Learning for Precision Medicine ApplicationAhmed Barnawi0Mehrez Boulares1Rim Somai2Information Technology Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi ArabiaInformation Technology Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi ArabiaESPRIT School of Engineering, Tunis 2035, TunisiaThe World Health Organization (WHO) highlights that cardiovascular diseases (CVDs) are one of the leading causes of death globally, with an estimated rise to over 23.6 million deaths by 2030. This alarming trend can be attributed to our unhealthy lifestyles and lack of attention towards early CVD diagnosis. Traditional cardiac auscultation, where a highly qualified cardiologist listens to the heart sounds, is a crucial diagnostic method, but not always feasible or affordable. Therefore, developing accessible and user-friendly CVD recognition solutions can encourage individuals to integrate regular heart screenings into their routine. Although many automatic CVD screening methods have been proposed, most of them rely on complex prepocessing steps and heart cycle segmentation processes. In this work, we introduce a simple and efficient approach for recognizing normal and abnormal PCG signals using Physionet data. We employ data selection techniques such as kernel density estimation (KDE) for signal duration extraction, signal-to-noise Ratio (SNR), and GMM clustering to improve the performance of 17 pretrained Keras CNN models. Our results indicate that using KDE to select the appropriate signal duration and fine-tuning the VGG19 model results in excellent classification performance with an overall accuracy of 0.97, sensitivity of 0.946, precision of 0.944, and specificity of 0.946.https://www.mdpi.com/2306-5354/10/3/294CVD classificationdata selectionconvolutional neural networkpretrained modeldeep learningtransfer learning |
| spellingShingle | Ahmed Barnawi Mehrez Boulares Rim Somai Simple and Powerful PCG Classification Method Based on Selection and Transfer Learning for Precision Medicine Application Bioengineering CVD classification data selection convolutional neural network pretrained model deep learning transfer learning |
| title | Simple and Powerful PCG Classification Method Based on Selection and Transfer Learning for Precision Medicine Application |
| title_full | Simple and Powerful PCG Classification Method Based on Selection and Transfer Learning for Precision Medicine Application |
| title_fullStr | Simple and Powerful PCG Classification Method Based on Selection and Transfer Learning for Precision Medicine Application |
| title_full_unstemmed | Simple and Powerful PCG Classification Method Based on Selection and Transfer Learning for Precision Medicine Application |
| title_short | Simple and Powerful PCG Classification Method Based on Selection and Transfer Learning for Precision Medicine Application |
| title_sort | simple and powerful pcg classification method based on selection and transfer learning for precision medicine application |
| topic | CVD classification data selection convolutional neural network pretrained model deep learning transfer learning |
| url | https://www.mdpi.com/2306-5354/10/3/294 |
| work_keys_str_mv | AT ahmedbarnawi simpleandpowerfulpcgclassificationmethodbasedonselectionandtransferlearningforprecisionmedicineapplication AT mehrezboulares simpleandpowerfulpcgclassificationmethodbasedonselectionandtransferlearningforprecisionmedicineapplication AT rimsomai simpleandpowerfulpcgclassificationmethodbasedonselectionandtransferlearningforprecisionmedicineapplication |