Validated method for automatic detection of lung sound crackles

Abstract

Crackling lung sounds are associated with many pulmonary diseases. Their occurrence reflects the quality and the severity of the disease. An automatic method for crackle detection is developed, based on analysing the spectral stationarity of the lung sound. The method is validated by studying the crackles of 20 adult patients; 10 with fibrosing alveolitis (FA) and 10 with bronchiectasis (BE). The number of crackles detected by the automatic method in inspiratory cycles is compared to the number of crackles counted from time-expanded waveforms by two expert observers. The total number of inspiratory cycles studied is 117 and that of crackles 1064. The method has a sensitivity of 89 per cent and a positive predictivity of 88 per cent for patients with FA, and 80 per cent and 83 per cent respectively, for patients with BE. The linear correlation coefficients between the numbers of crackles counted by the automatic method and by the observers is 0.86 (p less than 0.001) for the patients with FA and 0.93 (p less than 0.001) for the patients with BE. The values refer to whole inspiratory cycles. The new automatic method seems reliable enough for clinical and scientific purposes. It enables a rapid and objective analysis of large materials with crackling lung sounds.

Acoustic properties of the normal chest

“…Mention is sometimes made of difficulties arising from the limited storage capacities for digitized data [29,34,39,[49][50][51], but the situation has changed radically over the last 4 yrs due to the development of efficient data handling software equipping widely available computers with clock speeds of over 33 MHz, capable of writing directly to large-capacity hard discs of 100 Mb or more.…”

“…Successive frequency spectra can be averaged over a fixed period of the signal [29,37,39] (such as inspiration or expiration), or displayed sequentially as a pseudo three-dimensional plot (amplitude-frequency-time) called a "waterfall" [12,34]. Alternatively, frequency spectra may take forms inspired by the work of MCKUSICK et al [9], who in 1955 represented acoustic amplitude by light intensity values or a scale of different colour tones on a time versus frequency graph [38,49].…”

Auditory Detection of Simulated Crackles in Breath Sounds

“…Various methods for automated crackle detection have shown promise. [7][8][9][10][11][12][13][14][15][16] Crackle quantification by computerized lung sound analysis is typically compared to subjective auscultation as the reference standard. 10,14,16 It will be a challenge to devise testing conditions for their validation when auscultation cannot be relied on.…”

“…The timing, pitch, and waveform of crackles reflect different pathophysiology in diseases, 1 such as pneumonia, bronchiectasis, asbestosis, sarcoidosis, fibrosing alveolitis, cystic fibrosis, and pulmonary congestion due to cardiac failure. [2][3][4][5][6] Since 1989, there have been several attempts [7][8][9][10][11][12][13][14][15][16] to detect crackles by automated methods. Some of the investigators employed human auditory identification as the reference standard in developing computerized lung sound analyzers.…”

Computer-based lung sound simulation

“…To our knowledge, no similar device exists for the simulation of lung sounds. Apart from their use as a teaching tool, lung sound simulators might be useful in all applications which require well-defined and easily reproducible lung sounds, such as the evaluation of computerised lung sound analysis systems (COHEN and LANDSBERG, 1984;KAISLA et al, 1991;NISSAN and GAVP~ELY, 1993;SANKUR et al, 1994).…”