Machine learning in lung sound analysis: a systematic review

• Autorzy: Palaniappan R. , Sundaraj K. , Ahamed N. U.
• Języki publikacji: EN

Abstrakty

EN

Machine learning has proven to be an effective technique in recent years and machine learning algorithms have been successfully used in a large number of applications. The development of computerized lung sound analysis has attracted many researchers in recent years, which has led to the implementation of machine learning algorithms for the diagnosis of lung sound. This paper highlights the importance of machine learning in computer-based lung sound analysis. Articles on computer-based lung sound analysis using machine learning techniques were identified through searches of electronic resources, such as the IEEE, Springer, Elsevier, PubMed and ACM digital library databases. A brief description of the types of lung sounds and their characteristics is provided. In this review, we examined specific lung sounds/disorders, the number of subjects, the signal processing and classification methods and the outcome of the analyses of lung sounds using machine learning methods that have been performed by previous researchers. A brief description on the previous works is thus included. In conclusion, the review provides recommendations for further improvements.

Słowa kluczowe

EN

review; lung sound; lung disorder; statistical; machine learning

PL

przegląd; osłuch płuc; choroba płuc; uczenie maszynowe

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2013
• Tom: Vol. 33, no. 3
• Strony: 129--135
• Opis fizyczny: Bibliogr. 59 poz., rys., tab.

Twórcy

autor

Palaniappan R.

• AI-Rehab Research Group, Universiti Malaysia Perlis (UniMAP), Kampus Pauh Putra, Perlis, Malaysia

autor

Sundaraj K.

• AI-Rehab Research Group, Universiti Malaysia Perlis (UniMAP), Kampus Pauh Putra, Perlis, Malaysia

autor

Ahamed N. U.

• AI-Rehab Research Group, Universiti Malaysia Perlis (UniMAP), Kampus Pauh Putra, Perlis, Malaysia

Bibliografia

• [1] Earis J. Lung sounds. Thorax 1992; 47: 671–2.
• [2] Pasterkamp H, Kraman SS, Wodicika G. Respiratory sounds. Am J Respir Crit Care Med 1997; 156: 974–87.
• [3] Nissan M, Gavriely N. A microcomputer based lung sounds analysis. Comput Methods Programs Biomed 1993; 40: 7–13.
• [4] Wolberg WH, Street WN, Mangasarian OL. Machine learning techniques to diagnose breast cancer from image-processed nuclear features of fine needle aspirates. Cancer Lett 1994; 77: 163–71.
• [5] Kotsiantis SB. Supervised machine learning: a review of classification techniques. Amsterdam, Netherlands: IOS Press; 2007: 3–24.
• [6] Kandaswamy A, Kumar CS, Ramanathan RP, Jayaraman S, Malmurugan N. Neural classification of lung sounds using wavelet coefficients. Comput Biol Med 2004; 34: 523–37.
• [7] Chowdhury SK, Majumder AK. Frequency analysis of adventitious lung sounds. J Biomed Eng 1982; 4: 305–12.
• [8] Korona Z, Kokar MM. Lung sound recognition using model-theory based feature selection and fusion. Appl Sign Proc 1998; 5: 152–69.
• [9] HowellDCJ.In:GeoffreyJL,StevenDS,editors.Signsofrespiratory disease: lung sounds. Oxford: Academic Press; 2006. . pp. 35–41.
• [10] Urquhart RB, McGhee J, Macleod JES, Banham SW, Moran F. The diagnostic value of pulmonary sounds: a preliminary study by computer-aided analysis. Comput Biol Med 1981; 11: 129–39.
• [11] McGee S. Auscultation of the lungs. Philadelphia: W.B. Saunders; 2012: 251–66 [chapter 28].
• [12] Steven M. Auscultation of the lungs. Saint Louis: W.B. Saunders; 2007: 326–45 [chapter 27].
• [13] Welsby PD, Parry G, Smith D. The stethoscope: some preliminary investigations. Postgrad Med J 2003;79:695–8.
• [14] Flietstra B, Markuzon N, Vyshedskiy A, Murphy R. Automated analysis of crackles in patients with interstitial pulmonary fibrosis. Pulm Med 2011.
• [15] Sovijärvi ARA, Vanderschoot J, Earis JE. Standardization of computerized respiratory sound analysis. Eur Resp Rev 2000; 10: 585.
• [16] Gross V, Hadjileontiadis LJ, Penzel T, Koehler U, Vogelmeier C. Multimedia database ‘‘Marburg Respiratory Sounds (MARS)’’, vol. 451. 2003; pp. 456–7.
• [17] RALE: A computer-assisted instructional package. Respir Care 1990; 35: 1006.
• [18] Bobrowski L, Łukaszuk T. Feature selection based on relaxed linear separability. Biocybern Biomed Eng 2009; 29: 43–59.
• [19] Riella RJ, Nohama P, Maia JM. Method for automatic detection of wheezing in lung sounds. Braz J Med Biol Res 2009; 42: 674–84.
• [20] Abbas A, Fahim A. An automated computerized auscultation and diagnostic system for pulmonary diseases. J Med Syst 2010;34:1149–55.
• [21] Azarbarzin A, Moussavi Z. Unsupervised classification of respiratory sound signal into snore/no-snore classes; 2010; 3666–9.
• [22] Bahoura M, Pelletier C. Respiratory sounds classification using Gaussian mixture models; 2004; 1309–12.
• [23] Lu X, Bahoura M. An integrated automated system for crackles extraction and classification. Biomed Signal Process Contr 2008; 3: 244–54.
• [24] Kahya YP, Guler EC, Sahin S. Respiratory disease diagnosis using lung sounds; 1997; 2051–3.
• [25] Cohen L. Time–frequency analysis. Prentice-Hall; 1995.
• [26] Prosser WH, Seale MD, Smith BT. Time–frequency analysis of the dispersion of Lamb modes. J Acoust Soc Am 1999; 105: 2669–76.
• [27] Gu YH, Bollen MHJ. Time–frequency and time-scale domain analysis of voltage disturbances. IEEE Trans Power Deliv 2000; 15: 1279–84.
• [28] Tu JV. Advantages and disadvantages of using artificial neural networks versus logistic regression for predicting medical outcomes. J Clin Epidemiol 1996; 49: 1225–31.
• [29] Raniszewski M. The edited nearest neighbor rule based on the reduced reference set and the consistency criterion. Biocybern Biomed Eng 2010; 30: 31–40.
• [30] Alsmadi S, Kahya YP. Design of a DSP-based instrument for real-time classification of pulmonary sounds. Comput Biol Med 2008; 38: 53–61.
• [31] Meyfroidt G, Güiza F, Ramon J, Bruynooghe M. Machine learning techniques to examine large patient databases. Best Pract Res Clin Anaesthesiol 2009; 23: 127–43.
• [32] Wang S, Summers RM. Machine learning and radiology. Med Image Anal 2012; 16: 933–51.
• [33] Güler İ, Polat H, Ergün U. Combining neural network and genetic algorithm for prediction of lung sounds. J Med Syst 2005; 29: 217–31.
• [34] Tsai C-F, Hsu Y-F, Lin C-Y, Lin W-Y. Intrusion detection by machine learning: a review. Expert Syst Appl 2009; 36: 11994–2000.
• [35] Jang J-SR, Sun C-T, Mizutan E. Neuro-fuzzy and soft computing: a computational approach to learning and machine intelligence. Prentice Hall; 1996.
• [36] Sankur B, Kahya YP, Güler EC, Engin T. Comparison of AR-based algorithms for respiratory sounds classification. Comput Biol Med 1994; 24: 67–76.
• [37] Forkheim KE, Scuse D, Pasterkamp H. A comparison of neural network models for wheeze detection; 1995; 214–9.
• [38] Rietveld S, Oud M, Dooijes EH. Classification of asthmatic breath sounds: preliminary results of the classifying capacity of human examiners versus artificial neural networks. Comput Biomed Res 1999; 32: 440–8.
• [39] Oud M, Dooijes EH, van der Zee JS. Asthmatic airways obstruction assessment based on detailed analysis of respiratory sound spectra. IEEE Trans Biomed Eng 2000; 47: 1450–5.
• [40] Waitman L, Clarkson K, Barwise J, King P. Representation and classification of breath sounds recorded in an intensive care setting using neural networks. J Clin Monit Comput 2000; 16: 95–105.
• [41] Alsmadi SS, Kahya YP. Online classification of lung sounds using DSP; 2002; 1771–2.
• [42] Bahoura M, Pelletier C. New parameters for respiratory sound classification; 2003;1457–60.
• [43] Baydar KS, Ertuzun A, Kahya YP. Analysis and classification of respiratory sounds by signal coherence method; 2003; 2950–3.
• [44] Folland R, Hines E, Dutta R, Boilot P, Morgan D. Comparison of neural network predictors in the classification of tracheal–bronchial breath sounds by respiratory auscultation. Artif Intell Med 2004; 31: 211–20.
• [45] Gnitecki J, Moussavi Z, Pasterkamp H. Classification of lung sounds during bronchial provocation using waveform fractal dimensions; 2004; 3844–7.
• [46] Martinez-Hernandez HG, Aljama-Corrales CT, Gonzalez- Camarena R, Charleston-Villalobos VS, Chi-Lem G. Computerized classification of normal and abnormal lung sounds by multivariate linear autoregressive model; 2005; 5999–6002.
• [47] Jen-Chien C, Huey-Dong W, Fok-Ching C, Chung IL. Wheeze detection using cepstral analysis in Gaussian mixture models; 2007; 3168–71.
• [48] Masada T, Kiyasu S, Miyahara S. Unmixed spectrum clustering for template composition in lung sound classification. Adv Knowledge Discov Data Mining 2008; 5012: 964–9.
• [49] Matsunaga S, Yamauchi K, Yamashita M, Miyahara S. Classification between normal and abnormal respiratory sounds based on maximum likelihood approach; 2009; 517–20.
• [50] Bahoura M. Pattern recognition methods applied to respiratory sounds classification into normal and wheeze classes. Comput Biol Med 2009; 39: 824–43.
• [51] Dokur Z. Respiratory sound classification by using an incremental supervised neural network. Pattern Anal Appl 2009; 12: 309–19.
• [52] Riella RJ, Nohama P, Maia JM. Methodology for automatic classification of adventitious lung sounds. Berlin, Heidelberg/Munich, Germany: Springer; 2010: 1392–5.
• [53] Mayorga P, Druzgalski C, Morelos RL, Gonzalez OH, Vidales J. Acoustics based assessment of respiratory diseases using GMM classification; 2010; 6312–6.
• [54] Zolnoori M, Zarandi M, Moin M, Teimorian S. Fuzzy rule- based expert system for assessment severity of asthma. J Med Syst 2010; 1–11.
• [55] Charleston-Villalobos S, Martinez-Hernandez G, Gonzalez- Camarena R, Chi-Lem G, Carrillo JG, Aljama-Corrales T. Assessment of multichannel lung sounds parameterization for two-class classification in interstitial lung disease patients. Comput Biol Med 2011; 41: 473–82.
• [56] Yamashita M, Matsunaga S, Miyahara S. Discrimination between healthy subjects and patients with pulmonary emphysema by detection of abnormal respiration; 2011; 693–6.
• [57] Feng J, Krishnan S, Sattar F. Adventitious sounds identification and extraction using temporal–spectral dominance-based features. IEEE Trans Biomed Eng 2011; 58: 3078–87.
• [58] Serbes G, Sakar CO, Kahya YP, Aydin N. Feature extraction using time–frequency/scale analysis and ensemble of feature sets for crackle detection; 2011; 3314–7.
• [59] Xie S, Jin F, Krishnan S, Sattar F. Signal feature extraction by multi-scale PCA and its application to respiratory sound classification. Med Biol Eng Comput 2012; 50: 759–68.