Brief Review — Construction and validation of a method for automated time label segmentation of heart sounds
Audio Data Analysis Tool for Heart Sound Segmentation
Construction and validation of a method for automated time label segmentation of heart sounds
Audio Data Analysis Tool, by Zigong First People’s Hospital, Chengdu Medical College, The First Aliated Hospital of Zhengzhou University, Southwest Minzu University, and University of Electronic Science and Technology of China
2024 Frontiers in AI (Sik-Ho Tsang @ Medium)Phonocardiogram (PCG)/Heart Sound Classification
2013 … 2023 … [CTENN] [Bispectrum + ViT] 2024 [MWRS-BFSC + CNN2D]
Summary: My Healthcare and Medical Related Paper Readings and Tutorials
==== My Other Paper Readings Are Also Over Here ====
- An audio data analysis tool is designed to segment the heart sounds from single heart cycle, and validated the heart rate using a finger oxygen meter.
Outline
- Audio Data Analysis Tool For Heart Sound Segmentation
- Results
1. Audio Data Analysis Tool For Heart Sound Segmentation
1.1. Workflow
- First, the electronic stethoscope is connected and the mp3 recorder is turned on while keeping the environment quiet.
- The candidate was asked to sit or take up a supine position with chest exposure.
- Next, a recorder was placed at the auscultation head with appropriate pressure on each of the five valve areas in turn: the mitral valve area (M), pulmonary valve area (P), first aortic auscultation area (A), second aortic auscultation area (E), and the tricuspid valve area (T), to record heart sounds for a period of at least 1 min.
- Data from each candidate were collected on three consecutive days, twice a day (8:00–11:00, 14:30–17:00), and 30 audio files were created for each person.
- Healthy adults from Chengdu Medical College with no underlying chronic disease were included. Long-term users of drugs that may cause arrhythmia were excluded.
- A total of 12 students were recruited, aged between 20 and 22.
The mp3 files are fed into the Audio Data Analysis Tool to automatically cut the audio data representing a cycle into four audio clips (S1, S2, systole, diastole).
1.2. Getting the Starting Point of Heart Sound
- To ensure that the starting point in the audio file was the first heart sound, and to eliminate interference from breathing and external noise, Audacity (version 1.3.3) software was used to display the phonocardiogram.
- Authors searched for the most regular, characteristic heart sound signals for segmentation.
- (I am not sure if this process is automatic or manual operation.)
- The heart sound is also standardized to increase amplitude.
1.3. Heart Sound Segmentation Using Proposed Audio Analysis Data Tool
First, the proposed Audio Analysis Data Tool automatically screened the amplitude and time axis of the S1 vertex, and calculated the frequency range of the S1 peak and the previous wave of the valley. In this way, the start and end times of S1 could be located.
Next, the S2 peak with the second peak is extracted between two adjacent S1 peaks as the features and filtered out the S2 peak, which showed a large difference from the average value.
- Finally, using the statistical data, the start and ending times, state, decibels, amplitude, and other information were calculated for each state. The systolic period, the diastolic period, and the starting time were calculated for S1 and S2.
The systolic period was defined as the time from the start of the first heart sound (S1) to the start of the second heart sound (S2).
The diastolic period was defined as the start of the second heart sound (S2) to the start of the first heart sound (S1) in the next cardiac cycle.
2. Results
2.1. Visualization of heart sound waves via audacity software
Segmentation of multiple cardiac cycles from the audio files was carried out based on localization of two adjacent “similar images” (defined as two adjacent images with similar amplitude and duration) in the PCG.
- The start and end positions of S1 and S2 are identified.
- When S1 and S2 are identified and located, the label value information (Figure 6) can be calculated and the clips are cut accurately.
2.2. Duration of S1, S2, Systolic, and Diastolic Periods
- After obtaining the start and end times of the first and second heart sounds, the duration of the cardiac cycle and the S1, S2, systolic and diastolic periods were calculated.
2.3. Cross-Validation
- To cross-validate the accuracy of the segmentation results, a finger oxygen monitor is used to record the heart rates of the participants during the data collection process.
- The above result of a paired t-test indicated that no significant difference was found between the two methods.
- (It seems that this paper mainly propose the software that they developed, with no AI algorithm.)
