Heart Diseases Recognition Model Based on HRV Feature Extraction over 12-Lead ECG Signals
Abstract
:1. Introduction
2. Related Work
3. Materials and Methods
3.1. Motivation
3.2. Dataset
3.3. Heart Disease Identification Flowchart
4. HRV Heart Disease Recognition Model (HHDR)
4.1. Data Denoising
4.2. HRV Signal Extraction
4.3. HRV Signal Calculation Method
4.4. Rule Extraction
Algorithm 1 HHDR Model—HRV Signal Extraction Algorithm |
Input: EC Output: L 1 : Begin 2 : Initialize parameters 3 : the maximum value of EC 4 : the minimum value of EC 5 : 6 : peaks ← an empty list 7 : for i from 1 to len(EC) - 2 do 8 : if and then 9 : Append i to peaks 10 : end if 11 : end for 12 : merged_peaks 13 : for each peak in peaks[1:] do 14 : if peak - last element of merged_peaks > max_distance then 15 : Append peak to merged_peaks 16 : end if 17 : end for 18 : R_intervals ← the difference between successive elements in merged_peaks 19 : the standard deviation of R_intervals 20 : End |
4.5. Matching Rule Establishment Algorithm
Algorithm 2 HHDR Model—Matching Rule Mining Algorithm |
Input: WHRV Output: TNA 1 : Begin 2 : for all WHRV do 3 : MHRV = RebuildSTFT(WAVE(WHRV,0.5,5)) 4 : the sequence MQA is obtained by Spectral Magnitude classification of MHRV 5 : end for 6 : MQA label clustering 7 : for each of labels do 8 : FQ = fp (MQA) 9 : AQA = ARules (FQ) 10 : RN = Mine (F1, AQA) 11 : TNA = RemoveDuplicates(RN) 12 : end for |
4.6. Extraction of Spectral Magnitude Quantization Algorithm Features
4.7. Spectral Magnitude Quantization Algorithm
Algorithm 3 HHDR Model—Spectral Magnitude Quantization Algorithm |
Input: MQA, TNA Output: AC 1: Begin 2: for each quantized sequence in MQA do 3: for each rule in TNA do 4: if quantized sequence matches rule then 5: increment MR by 1 6: end if 7: end for 8: for each rule in TNA do 9: TC = TC + COi 10: TS = TS + SOi 11: end for 12: FR = MR / LE 13: SQ = SQ + SAi 14: SS = SS + 15: SS = SS * 16: for i = 1 to n do 17: SK = SK + 18: end for 19: for each feature in FNNCMSH do 20: FN = FN + 21: end for 22: train RandomForestClassifier with extracted features 23: test RandomForestClassifier 24: AC = calculate final accuracy |
5. Experiment and Results
5.1. Dataset
5.2. HHDR Model Evaluation
6. Discussion
7. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Ketu, S.; Mishra, P.K. An intelligent hybrid classification model for heart disease detection using imbalanced electrocardiogram signals. J. Supercomput. 2024, 80, 4286–4308. [Google Scholar] [CrossRef]
- Chandrasekhar, N.; Peddakrishna, S. Enhancing heart disease prediction accuracy through machine-learning techniques and optimization. Processes 2023, 11, 1210. [Google Scholar] [CrossRef]
- Dhara, S.K.; Bhanja, N.; Khampariya, P. An adaptive heart disease diagnosis via ECG signal analysis with deep feature extraction and enhanced radial basis function. Comput. Methods Biomech. Biomed. Eng. Imaging Vis. 2024, 11, 2245927. [Google Scholar] [CrossRef]
- Eltrass, A.S.; Tayel, M.B.; Ammar, A.I. Automated ECG multi-class classification system based on combining deep-learning features with HRV and ECG measures. Neural Comput. Appl. 2022, 34, 8755–8775. [Google Scholar] [CrossRef]
- Singhal, S.; Kumar, M. A systematic review on artificial intelligence-based techniques for diagnosis of cardiovascular arrhythmia diseases: Challenges and opportunities. Arch. Comput. Methods Eng. 2023, 30, 865–888. [Google Scholar] [CrossRef]
- Sharma, M.; Patel, S.; Acharya, U.R. Expert system for detection of congestive heart failure using optimal wavelet and heart rate variability signals for wireless cloud-based environment. Expert Syst. 2023, 40, e12903. [Google Scholar] [CrossRef]
- Chowdary, K.R.; Bhargav, P.; Nikhil, N.; Varun, K.; Jayanthi, D. Early heart disease prediction using ensemble learning techniques. Proc. J. Phys. Conf. Ser. 2022, 2325, 012051. [Google Scholar]
- Liu, J.; Dong, X.; Zhao, H.; Tian, Y. Predictive classifier for cardiovascular disease based on stacking model fusion. Processes 2022, 10, 749. [Google Scholar] [CrossRef]
- Faust, O.; Hong, W.; Loh, H.W.; Xu, S.; Tan, R.S.; Chakraborty, S.; Barua, P.D.; Molinari, F.; Acharya, U.R. Heart rate variability for medical decision support systems: A review. Comput. Biol. Med. 2022, 145, 105407. [Google Scholar] [CrossRef]
- Esgalhado, F.; Batista, A.; Vassilenko, V.; Russo, S.; Ortigueira, M. Peak detection and HRV feature evaluation on ECG and PPG signals. Symmetry 2022, 14, 1139. [Google Scholar] [CrossRef]
- Shah, D.; Patel, S.; Bharti, S.K. Heart disease prediction using machine-learning techniques. SN Comput. Sci. 2020, 1, 345. [Google Scholar] [CrossRef]
- Hasan, N.; Bao, Y. Comparing different feature selection algorithms for cardiovascular disease prediction. Health Technol. 2021, 11, 49–62. [Google Scholar] [CrossRef]
- Oh, S.L.; Ng, E.Y.; San Tan, R.; Acharya, U.R. Automated beat-wise arrhythmia diagnosis using modified U-net on extended electrocardiographic recordings with heterogeneous arrhythmia types. Comput. Biol. Med. 2019, 105, 92–101. [Google Scholar] [CrossRef]
- Hou, B.; Yang, J.; Wang, P.; Yan, R. LSTM-based auto-encoder model for ECG arrhythmias classification. IEEE Trans. Instrum. Meas. 2019, 69, 1232–1240. [Google Scholar] [CrossRef]
- Śmigiel, S.; Pałczyński, K.; Ledziński, D. ECG signal classification using deep-learning techniques based on the PTB-XL dataset. Entropy 2021, 23, 1121. [Google Scholar] [CrossRef] [PubMed]
- Pałczyński, K.; Śmigiel, S.; Ledziński, D.; Bujnowski, S. Study of the few-shot learning for ECG classification based on the PTB-XL dataset. Sensors 2022, 22, 904. [Google Scholar] [CrossRef] [PubMed]
- Sieciński, S.; Tkacz, E.J.; Kostka, P.S. Heart rate variability analysis on electrocardiograms, seismocardiograms and gyrocardiograms of healthy volunteers and patients with valvular heart diseases. Sensors 2023, 23, 2152. [Google Scholar] [CrossRef]
- Banu, A.S.; Nagaveni, V. Assessment of Sympathetic and Parasympathetic Activities of Nervous System from Heart Rate Variability Using Machine Learning Techniques. SN Comput. Sci. 2023, 4, 646. [Google Scholar] [CrossRef]
- Li, K.; Cardoso, C.; Moctezuma-Ramirez, A.; Elgalad, A.; Perin, E. Heart Rate Variability Measurement through a Smart Wearable Device: Another Breakthrough for Personal Health Monitoring? Int. J. Environ. Res. Public Health 2023, 20, 7146. [Google Scholar] [CrossRef] [PubMed]
- Bahameish, M.; Stockman, T.; Requena Carrión, J. Strategies for Reliable Stress Recognition: A Machine Learning Approach Using Heart Rate Variability Features. Sensors 2024, 24, 3210. [Google Scholar] [CrossRef]
- Razak, S.F.A.; Ismail, S.S.; Yogarayan, S.; Abdullah, M.F.A.; Kamis, N.H.; Aziz, A.A. Comparative Study of Machine Learning Algorithms in Classifying HRV for the Driver’s Physiological Condition. Civ. Eng. J. 2023, 9, 2272–2285. [Google Scholar] [CrossRef]
- Padovano, D.; Martinez-Rodrigo, A.; Pastor, J.M.; Rieta, J.J.; Alcaraz, R. On the generalization of sleep apnea detection methods based on heart rate variability and machine learning. IEEE Access 2022, 10, 92710–92725. [Google Scholar] [CrossRef]
- Mu, S.; Liao, S.; Tao, K.; Shen, Y. Intelligent fatigue detection based on hierarchical multi-scale ECG representations and HRV measures. Biomed. Signal Process. Control 2024, 92, 106127. [Google Scholar] [CrossRef]
- Wang, L.; Song, F.; Zhou, T.H.; Hao, J.; Ryu, K.H. EEG and ECG-based multi-sensor fusion computing for real-time fatigue driving recognition based on feedback mechanism. Sensors 2023, 23, 8386. [Google Scholar] [CrossRef] [PubMed]
- Wang, L.; Liu, H.; Zhou, T.; Liang, W.; Shan, M. Multidimensional emotion recognition based on semantic analysis of biomedical eeg signal for knowledge discovery in psychological healthcare. Appl. Sci. 2021, 11, 1338. [Google Scholar] [CrossRef]
- Wang, L.; Hao, J.; Zhou, T.H. ECG Multi-Emotion Recognition Based on Heart Rate Variability Signal Features Mining. Sensors 2023, 23, 8636. [Google Scholar] [CrossRef] [PubMed]
- Wagner, P.; Strodthoff, N.; Bousseljot, R.D.; Kreiseler, D.; Lunze, F.I.; Samek, W.; Schaeffter, T. PTB-XL, a large publicly available electrocardiography dataset. Sci. Data 2020, 7, 154. [Google Scholar] [CrossRef] [PubMed]
- Botros, J.; Mourad-Chehade, F.; Laplanche, D. Cnn and svm-based models for the detection of heart failure using electrocardiogram signals. Sensors 2022, 22, 9190. [Google Scholar] [CrossRef]
- Shin, S.; Kang, M.; Zhang, G.; Jung, J.; Kim, Y.T. Lightweight Ensemble Network for detecting heart disease using ECG signals. Appl. Sci. 2022, 12, 3291. [Google Scholar] [CrossRef]
- Ahmed, A.A.; Ali, W.; Abdullah, T.A.; Malebary, S.J. Classifying cardiac arrhythmia from ECG signal using 1D CNN deep learning model. Mathematics 2023, 11, 562. [Google Scholar] [CrossRef]
Records (Vol.) | Superclass | Description |
---|---|---|
5469 | MI | Myocardial Infarction |
9514 | NORM | Normal ECG |
2649 | HYP | Hypertrophy |
5235 | STTC | ST/T Change |
4898 | CD | Conduction Disturbance |
Parameter | Description |
---|---|
Yci | Difference from the i-th to the subsequent signal points |
Xci | i-th signal point |
E | Overall signal data array |
I | Starting index |
W | Window size |
T | Threshold |
Ci | Value at the i-th position in the signal data E |
EI | I-th signal data point |
L | HRV sequence signal |
Ri | i-th peak position |
Pi | i-th element in the peak value list position |
DMAX | Maximum distance |
VMAX/VMIN | Maximum value/Minimum value |
MLAST | Position of the last element in the merged peak value list |
max{, , } | Maximum value in E within the range from I − 1 to I + 1 |
LEN() | Length of the R-peak position list |
max_index | Index position of the local maximum |
EC | Original ECG signal |
Frequency Segment | Frequency Span |
---|---|
HF2 | 0.25–0.4 Hz |
HF1 | 0.15–0.25 Hz |
LF | 0–0.15 Hz |
Parameter | Description |
---|---|
MHRV | Frequency-divided HRV signal |
WHRV | HRV signal sequence |
MQA | Magnitude Quantization Levels |
RebuildSTFT | STFT-based reconstruction function |
WaveSTFT | STFT-based decomposition function |
Qe | amplitude value |
Amax | absolute value of the peak in the amplitude series |
FQ | frequent itemset |
AQA | potential rule set |
RN | merged rule set |
TNA | deduplicated rule set |
Parameter | Description |
---|---|
MR | Number of Matched Rules |
MQAi | The i-th spectral magnitude quantization sequence in the sequence |
TNAi | i-th rule in the set |
TS | Overall support |
SOi | Rule i support |
TC | Overall confidence |
COi | Rule i confidence |
FR | Frequency |
LE | Sliding window extraction of spectral magnitude quantifying sequences |
SQ | Support score |
FNNCMSH | The collective term for the five newly generated features |
SS | Support skewness |
s | The standard deviation of the support of matching sequences |
SK | Support kurtosis |
AC | Accuracy in feature recognition classification |
OF | Original features |
The support of the i-th matching sequence |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Wang, L.; Bi, T.; Hao, J.; Zhou, T.H. Heart Diseases Recognition Model Based on HRV Feature Extraction over 12-Lead ECG Signals. Sensors 2024, 24, 5296. https://doi.org/10.3390/s24165296
Wang L, Bi T, Hao J, Zhou TH. Heart Diseases Recognition Model Based on HRV Feature Extraction over 12-Lead ECG Signals. Sensors. 2024; 24(16):5296. https://doi.org/10.3390/s24165296
Chicago/Turabian StyleWang, Ling, Tianshuo Bi, Jiayu Hao, and Tie Hua Zhou. 2024. "Heart Diseases Recognition Model Based on HRV Feature Extraction over 12-Lead ECG Signals" Sensors 24, no. 16: 5296. https://doi.org/10.3390/s24165296