Heart sound classification based on equal scale frequency cepstral coefficients and deep learning
Xiaoqing Chen1, Hongru Li1, Youhe Huang1
1College of Information Science and Engineering, Northeastern University, Shenyang, China.
Insights
A new Equal-scale Frequency Cepstral Coefficients (EFCC) feature improves early heart disease detection. This method outperforms traditional Mel-scale Frequency Cepstral Coefficients (MFCC) in classifying heart sounds, aiding in real-time monitoring.
Area of Science:
- Biomedical Engineering
- Signal Processing
- Cardiology
Background:
- Heart diseases are a leading cause of mortality, necessitating early detection and prevention strategies.
- Mel-scale Frequency Cepstral Coefficients (MFCC) are commonly used for heart sound analysis but may not be optimal due to their basis in human auditory properties.
- The frequency characteristics of heart sounds differ from those processed by the human auditory system.
Purpose of the Study:
- To introduce a novel feature extraction method, Equal-scale Frequency Cepstral Coefficients (EFCC), for improved heart sound analysis.
- To develop and evaluate advanced classifiers integrating Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Random Forest (RF) for heart sound classification.
- To compare the performance of EFCC with MFCC in identifying cardiac abnormalities.
Main Methods:
- Proposed EFCC feature by replacing Mel-scale filters with equally spaced triangular overlapping filters.
- Developed hybrid CNN-RNN-RF classifiers to capture both spatial and temporal features of heart sounds.
- Validated the algorithm using a private database and the PhysioNet CinC 2016 Challenge Database.
Main Results:
- EFCC features demonstrated superior performance and robustness compared to MFCC features in classifying heart sounds from new patients.
- Ten-fold cross-validation confirmed the effectiveness of the proposed EFCC-based approach.
- The developed algorithm achieved high precision in heart sound classification.
Conclusions:
- EFCC offers a more objective and suitable feature for heart sound signal processing than MFCC.
- The hybrid CNN-RNN-RF classifier effectively extracts relevant information for accurate heart sound classification.
- This research paves the way for advanced, real-time heart monitoring using wearable medical devices.
Abstract:
Heart diseases represent a serious medical condition that can be fatal. Therefore, it is critical to investigate the measures of its early prevention. The Mel-scale frequency cepstral coefficients (MFCC) feature has been widely used in the early diagnosis of heart abnormity and achieved promising results. During feature extraction, the Mel-scale triangular overlapping filter set is applied, which makes the frequency response more in line with the human auditory property. However, the frequency of the heart sound signals has no specific relationship with the human auditory system, which may not be suitable for processing of heart sound signals. To overcome this issue and obtain a more objective feature that can better adapt to practical use, in this work, we propose an equal scale frequency cepstral coefficients (EFCC) feature based on replacing the Mel-scale filter set with a set of equally spaced triangular overlapping filters. We further designed classifiers combining convolutional neural network (CNN), recurrent neural network (RNN) and random forest (RF) layers, which can extract both the spatial and temporal information of the input features. We evaluated the proposed algorithm on our database and the PhysioNet Computational Cardiology (CinC) 2016 Challenge Database. Results from ten-fold cross-validation reveal that the EFCC-based features show considerably better performance and robustness than the MFCC-based features on the task of classifying heart sounds from novel patients. Our algorithm can be further used in wearable medical devices to monitor the heart status of patients in real time with high precision, which is of great clinical importance.
Related Concept Videos
01:15Heart Sounds
Auscultation is the process of listening to these internal body sounds using a stethoscope. The heart produces four types of sounds, but only two—S1 and S2—can usually be heard with a stethoscope.
S1, also known as the "lub" sound, is caused by the closure of atrioventricular (A-V)...
01:30Classification of Signals
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
01:25Assessment of the Cardiovascular System IV: Auscultation
Normal Heart Sounds
S1 (First Heart Sound)-
S1 is made by the closure of the mitral and tricuspid valves (atrioventricular valves), marking the beginning of systole.
S2 (Second Heart Sound)-
S2 is made by the closure of the aortic and pulmonic valves (semilunar valves), marking the end of the systole.
01:21Perceiving Loudness, Pitch, and Location
Place theory, or place coding, suggests that different pitches are heard because various sound waves activate specific locations along the cochlea's basilar membrane. The brain determines the pitch of a sound by...
01:22Force Classification
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
01:31Hearing