Automatic Robust Crackle Detection and Localization Approach Using AR-Based Spectral Estimation and Support Vector Machine

• Published in: Applied sciences Vol. 13; no. 19; p. 10683
• Main Authors: Mang, Loredana Daria, Carabias-Orti, Julio José, Canadas-Quesada, Francisco Jesús, de la Torre-Cruz, Juan, Muñoz-Montoro, Antonio, Revuelta-Sanz, Pablo, Combarro, Eilas Fernandez
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.10.2023
• Subjects: accuracy; Algorithms; AR model; Auscultation; crackle; detection; Fractals; Lung diseases; Lungs; Neural networks; Pneumonia; respiratory; Signal processing; Sound; Support vector machines; SVM; Wavelet transforms
• ISSN: 2076-3417; 2076-3417
• DOI: 10.3390/app131910683

Auscultation primarily relies upon the acoustic expertise of individual doctors in identifying, through the use of a stethoscope, the presence of abnormal sounds such as crackles because the recognition of these sound patterns has critical importance in the context of early detection and diagnosis of respiratory pathologies. In this paper, we propose a novel method combining autoregressive (AR)-based spectral features and a support vector machine (SVM) classifier to detect the presence of crackle events and their temporal location within the input signal. A preprocessing stage is performed to discard information out of the band of interest and define the segments for short-time signal analysis. The AR parameters are estimated for each segment to be classified by means of support vector machine (SVM) classifier into crackles and normal lung sounds using a set of synthetic crackle waveforms that have been modeled to train the classifier. A dataset composed of simulated and real coarse and fine crackles sound signals was created with several signal-to-noise (SNR) ratios to evaluate the robustness of the proposed method. Each simulated and real signal was mixed with noise that shows the same spectral energy distribution as typically found in breath noise from a healthy subject. This study makes a significant contribution by achieving competitive results. The proposed method yields values ranging from 80% in the lowest signal-to-noise ratio scenario to a perfect 100% in the highest signal-to-noise ratio scenario. Notably, these results surpass those of other methods presented by a margin of at least 15%. The combination of an autoregressive (AR) model with a support vector machine (SVM) classifier offers an effective solution for detecting the presented events. This approach exhibits enhanced robustness against variations in the signal-to-noise ratio that the input signals may encounter.