Heart Murmur Detection with Phonocardiogram Recordings: Analysis of Ensemble Learning Model Performance within XAI Framework
Keywords:
Multi-source phonocardiograms, SHAP XAI, Digi Scope dataset, ensemble learningAbstract
Accurate and reliable information on human heart health is key to its prognosis. Most recently, advanced machine learning and deep learning methods are aiding the doctors in decision making. However, it still evades them to understand how a ML or DL model is able to do so. This calls for use of ML/DL model performance interpretation frameworks to correlate a particular model’s performance with its internal architecture and functioning. In this study, an attempt is made to interpret the performance two different classification models that participated in the Physionet Challenge 2022. SHAP XAI framework-based interpretations of the performances of one heart murmur detection model and one clinical outcome prediction model are done. The heart murmur detection model selected for interpretation is a transformer-based deep neural network (T-DNN) whereas the clinical outcome prediction model selected for interpretation is a Random Forest boosted with AdaBoost boosting strategy. The dataset considered for model performance interpretations is the CirCor DigiScope dataset. The dataset contains phonocardiogram recordings, socio-demographic information and other auxiliary information. The T-DNN is trained on DWT features computed from segmented phonocardiogram signals for three-class (Present, Absent, and Unknown) classification task. The AdaBoost-RF is trained on collection of features including statistical measures, wavelet transform features, time-based and frequency-based features. ANOVA method is used to reduce the dimensionality of the total number of features to 110. The AdaBoost-RF performs a binary (Normal and Abnormal) classification task. The T-DNN model performed classification with overall accuracy of 90.23% whereas the AdaBoost-RF model performed classification with overall accuracy of 89.1%. Shapley importance plot, summary plot and Swarm charts are used to interpret the classification performance of the T-DNN and the AdaBoost-RF here. The study provides insights into the workings of advanced machine learning and deep learning models during detection and identification of heart health from phonocardiogram recordings.
Downloads
References
Venkataramani VV, Garg A, Priyakumar UD (2022) Modified Variable Kernel Length ResNets for Heart Murmur Detection and Clinical Outcome Prediction Using Phonocardiogram Recordings. Computing in Cardiology 2022-Septe:1–4. https://doi.org/10.22489/CinC.2022.315
Imran Z,Grooby E,Malgi VV,et al(2022) A Fusion of Handcrafted Feature –Based and Deep Learning Classifiers for Heart Murmur Detection .Computing in Cardiology 2022-septe:1-4.https://doi.org/10.22489/cinC.2022.310
Abdul ZK,AI-Talabani AK(2022) Mel Frequency Cepstral Coeddiciemt and its Applications:AReview.IEEE Access 10:122136-122158.https://doi.org/10.1109/ACCESS.2022.3223444
Chang Y, Liu L, Antonescu C (2022) Multi-Task Prediction of Murmur and Outcome from Heart Sound Recordings. Computing in Cardiology 2022-Septe:7-10. https://doi.org/10.22489/CinC.2022.309
Bai Z, Yan B, Chen X, et al (2022) Murmur Detection and Clinical Outcome Classification Using a VGG-like Network and Combined Time-Frequency Representations of PCG Signals. Computing in Cardiology 2022-Septe: 1-4. https://doi.org/10.22489/CinC.2022.318
Maller K, Goda MA (2022) Heart Murmur Detection in Phonocardiographic Signals Using Breathing Noise Suppression. Computing in Cardiology 2022-Septe:2-5. https://doi.org/10.22489/CinC.2022.280
Nivitha Varghees V, Ramachandran KI (2015) Heart murmur detection and classification using wavelet transform and Hilbert phase envelope. 2015 21st National Conference on Communications, NCC 2015 1-6. https://doi.org/10.1109/NCC.2015.7084904
Petrolis R, Paukstaitiene R, Rudokaite G, et al (2022) Convolutional Neural Network Approach for Heart Murmur Sound Detection in Auscultation Signals Using Wavelet Transform Based Features. Computing in Cardiology 2022-Septe:2-5.https://doi.org/10.22489/CinC.2022.043
Comely AK, Mirsky GM (2022) Heart Murmur Detection Using Wavelet Time Scattering and Support Vector Machines. Computing in Cardiology 2022-Septe:1-4. https://doi.org/10.22489/CinC.2022.251
Touahria R, Hacine-Gharbi A, Ravier P (2023) Feature selection algorithms highlight the importance of the systolic segment for normal/murmur PCG beat classification. Biomedical Signal Processing and Control 86:105288. https://doi.org/10.1016/j.bspc.2023.105288
Xu Y, Bao X, Lam HK, Kamavuako EN (2022) Hierarchical Multi-Scale Convolutional Network for Murmurs Detection on PCG Signals.Computing in Cardiology 2022-Septe: 1-4. https://doi.org/10.22489/CinC.2022.439
Warrick PA, Afilalo J (2022) Phonocardiographic Murmur Detection by Scattering-Recurrent Networks. Computing in Cardiology 2022-Septe:10-13. https://doi.org/10.22489/CinC.2022.408
LiX, Ng GA, Schlindwein FS (2022) Transfer Leaming in Heart Sound Classification using Mel Spectrogram. Computing in Cardiology 2022-Septe: 1-4. https://doi.org/10.22489/CinC.2022.046
Lu H, Yip JB, Steigleder T, et al (2022) A Lightweight Robust Approach for Automatic Heart Murmurs and Clinical Outcomes Classification from Phonocardiogram Recordings. Computing in Cardiology 2022-Septe:4-7. https://do1.org/10.22489/CinC.2022.165
Shin JM, Park SY, Kim HS, et al (2022) Leaming Time-Frequency Representations of Phonocardiogram for Murmur Detection. Computing in Cardiology 2022-Septe: 1-4. https://doi.org/10.22489/CinC.2022.126
Alam S, Banerjee R, Bandyopadhyay S (2018) Murmur Detection Using Parallel Recurrent & Convolutional Neural Networks
Costa JL, Couto P, Rodrigues R (2022) Multitask and Transfer Learning for Cardiac Abnormality Detections in Heart Sounds. Computing in Cardiology 2022-Septe: 1-4. https://doi.org/10.22489/CinC.2022.193
Jain SM (2022) Introduction to transformers for NLP. Springer
Walker B, Krones F, Kiskin I, et al (2022) Dual Bayesian ResNet: A Deep Leaming Approach to Heart Murmur Detection. Computing in Cardiology 2022-Septe: 1-4. https://doi.org/10.22489/CinC.2022.335
Summerton S,Wood D,Murphy D,et al(2022) Two Stage Classification for Detecting Murmurs from Phonocardiograms Using Deep and Expert Features .Computing in Cardiology 2022-septe 3-6 https://doi.org/10.22489/CinC.2022.322
Alkhodari M, Azman SK, Hadjileontiadis LJ, Khandoker AH (2022) Ensemble Transformer-Based Neural Networks Detect Heart Murmur in Phonocardiogram Recordings. In: Computing in Cardiology. IEEE Computer Society
Baydoun M, Safatly L, Ghaziri H, El Hajj A (2020) Analysis of heart sound anomalies using ensemble leaming. Biomed Signal Process Control 62:. https://doi.org/10.1016/j.bspc.2020.102019
Goldberger AL, Amaral LAN, Glass L, et al (2000) PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101:e215-e220
Reyna MA, Kiarashi Y, Elola A, et al (2023) Heart murmur detection from phonocardiogram recordings: The george b. moody physionet challenge 2022. PLOS Digital Health 2:e0000324
Oliveira J, Renna F, Costa PD, et al (2021) The CirCor DigiScope dataset: from murmur detection to murmur classification. IBEE J Biomed Health Inform 26:2524-2535
Deng F, Tu S, Xu L (2021) Multi-source unsupervised domain adaptation for ECG classification. In: 2021 IEEE International Conference on Bioinformatics and Biomedicine(BIBM).pp854-859
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
