The ASAP project: A first step to an auscultation's school creation

Article Outline

• Abstract
• Educational aims
• 1. Introduction
  • 1.1. Limits of human audition
  • 1.2. Definition of common markers
  • 1.3. Definition of semiology
• 2. Analysis of pulmonary sounds: state of the art
  • 2.1. Definition of terms
    • 2.1.1. Sounds
    • 2.1.2. Known trackers
    • 2.1.3. Visualisation methods
    • 2.1.4. Analysis methods
  • 2.2. Capture techniques
    • 2.2.1. Acquisition
    • 2.2.2. Filtering and heart sound cancelling
  • 2.3. Lung sound characteristics
    • 2.3.1. Characteristics of wheezes
    • 2.3.2. Characteristics of crackles
  • 2.4. Detection of known markers
• 3. ASAP: description of the project
  • 3.1. Context
  • 3.2. Goal of the project and main technological challenges
  • 3.3. Our value added
  • 3.4. Description of the ASAP project
• 4. Perspectives: the Auscultation's School
• 5. Conclusion/future work
• 6. Grant
• Acknowledgments
• CME section
• Educational questions
• References
• Copyright

Abstract 

Objective

This paper describes an ambitious study of in the so-called ASAP project or “Analyse de Sons Auscultatoires et Pathologiques”.

Results

ASAP is a 3-year-long French collaborative project. It is part of a collaborative telemedicine platform called MERCURE or “ Mobile Et Réseau pour la Clinique, l'Urgence ou la Résidence Externe”. MERCURE deals with projects for remote monitoring or in clinical context thanks to modern tools principally coming from the News Technologies of Information and Communication. ASAP aims at making evolve the auscultation technics: by the development objective tools for the analyse of auscultation sounds: electronic stethoscopes paired with computing device; by the creation of an auscultation sounds' database in order to compare and identify the acoustical and visual signatures of the pathologies; and by the capitalisation of these new auscultation techniques around the creation of a teaching unit: « Ecole de l'Auscultation ». This auscultation's school will be destined to the initial and continuous formation of the medical attendants.

Conclusion

Previous studies demonstrate the need of performing an exhaustive scientific approach. It is precisely the context of the ASAP project.

Keywords: Auscultation, State of the art, Respiratory sounds, Sound analysis

Back to Article Outline

Educational aims 

Back to Article Outline

1. Introduction 

Distinction between normal respiratory sounds and abnormal ones (such as crackles, wheezes…) is important for an accurate medical diagnosis. Respiratory sounds include invaluable information concerning the physiologies and pathologies of lungs and airways obstruction. Thus, the spectral density and amplitude of sounds can indicate the state of the lungs parenchyma, the dimension of the airways and their pathological modification.¹

1.1. Limits of human audition 

Studies were performed in order to test the human's ear capability to detect crackles in an auscultation signal.² The methods used consist in simulated crackles superimposed on real breath sound. The results indicate that the most important detection errors are due to the intensity of the respiratory signal, the type of crackles and the amplitude of crackles. It can be inferred from these studies that the validation of automatic crackles' detection algorithms should not take auscultation as unique reference.

On the contrary, the understanding of mechanisms linked to the creation of breath sounds is, for the moment, imperfect. The recording and analysis of respiratory sounds allow to improve this understanding³ and an objective relationship between abnormal respiratory sounds with respiratory pathology. Besides, an objective analysis allows to develop classification systems⁴ that make it possible to precisely qualify normal and adventitious respiratory sounds. Whilst conventional stethoscope auscultation is subjective and hardly sharable, these systems should provide an objective and early diagnostic help, with a better sensitivity and reproducibility of the results.

Moreover, applications, including diagnosis establishment, monitoring and data exchange through Internet are obviously complementary tools to objective and automatic auscultation sounds analysis. Sensor devices will allow long duration monitoring for patient at home or at hospital. It could also be a useful solution for less-developed countries and remote communities.⁵ In addition, this type of system has the great advantage to keep the non-invasive and less expensive characteristics of auscultation.

Finally, studies of Sestini and colleagues⁶ indicate that an association between acoustical signal and its image is beneficial to the learning and understanding for students in medical science.

1.2. Definition of common markers 

Nowadays, there are several definitions for the typical markers of wheezes and crackles.⁸ Thus, a universal semantic has to be created. Several works⁹ have attempted to collect definitions of terms relating to respiratory sounds and have arrived at a collection of 162 terms commonly used in the “Computer Respiratory Sound Analysis” (CORSA). Nevertheless, it still doesn't allow physician to have a common definition of terms that are used. For example, a wheeze is still currently associated to a “whistling sound”, and a crackle to “a sound of rice in a frying pan”.

1.3. Definition of semiology 

The article of Rossi and colleagues¹⁰ gives recommendations concerning the experimental conditions required for recording respiratory sounds. It describes the optimal experimental conditions (principally concerning background noise, including sounds other than respiratory such as vocal sounds) and the specific procedures according to the type of sounds he wanted to record (breath, cough, snores), information for the recording (diagnosis, evaluation of a therapy, monitoring), the age of subject, and the recording method (free field, endobronchial microphone). Lastly, for short recordings, a sitting position is recommended, but a lay position is preferably for long recordings.

Back to Article Outline

2. Analysis of pulmonary sounds: state of the art 

2.1. Definition of terms 

The Article of Sovijarvi and colleagues,⁹ published in the European Respiratory Journal, provides accurate definitions of currently used terms in pulmonary auscultation domain and sound analysis; the more pertinent are recalled here:

Adventitious sound: it relates to additional respiratory sounds superimposed on normal breath sounds. It can be continuous (like wheezes) or discontinuous (such as crackles). Some of them (like squawks) have both characteristics. The presence of such sounds usually indicates pulmonary disorders.

Normal breath sound: on the chest wall, respiratory sound is characterized by a low noise during inspiration, and hardly audible during expiration. On trachea, normal respiratory sound is characterized by a broader spectrum of noise, audible both during inspiratory and expiratory phases.

Crackles: these adventitious explosive and discontinuous sounds appear generally during inspiratory phase. They are characterised by their specific waveform, their duration, and their location in the respiratory cycle. A crackle can be characterized by its total duration, as fine (short duration) or coarse (long duration). Occurrences of crackles in lung sounds usually reflect a pathological process in pulmonary tissue or airways.

Rhonchus: rhonchus is a low-pitched wheeze containing rapidly damping periodic waveforms with a duration of >100ms and frequency of <300Hz. Rhonchus can be found, for example, in patients with secretions or narrowing in large airways and with abnormal airway collapsibility.

Wheeze: this adventitious and continuous sound presents a musical character. Acoustically, it is characterized by periodic waveforms with a dominant frequency usually over 100Hz and with duration of ≥100ms. Wheezes are usually associated with airways' obstruction due to various causes.

Phonopneumogram: it is a simultaneous and overlapped display of sound signal and airflow in time domain during breathing:

Spectrogram: it concerns representation in which time is represented in abscises frequency in ordinate, and the intensity of the signal by a palette of colors.

Artificial neural network (ANN): it is a mathematical model based on biological neural networks that consists in an interconnected group of artificial neurons and processes information using a connectionist approach to computation. Generally, it is an adaptive system that changes its structure based on external or internal information that flows through the network during the learning phase.

Genetic algorithm: it is a search technique used to find exact or approximate solutions to optimization and search problems. Genetic algorithms are categorized as global search heuristics. They are a particular class of evolutionary algorithms that use techniques inspired by evolutionary biology such as inheritance, mutation, selection, and crossover.

Fuzzy logic: it is derived from fuzzy set theory dealing with reasoning that is approximate rather than precisely deduced from classical predicate logic. It can be thought of as the application side of fuzzy set theory dealing with well thought out real world expert values for a complex problem.

Wavelet: it is a kind of mathematical function used to divide a given function into different frequency components and study each component with a resolution that matches its scale. Wavelet transforms have advantages over traditional Fourier transforms for representing functions that have discontinuities and sharp peaks, and for accurately deconstructing and reconstructing finite, non-periodic and/or non-stationary signals.

2.2. Capture techniques 

An adapted capture chain of the sound is a relevant point preceding the analysis phase.¹¹, ¹², ¹³ Typically, it is made up of the following elements³: sound capturing (the positioning of the microphone is important; the chest acts like a reducer and a low-pass filter), amplification of the signal, filtering and sampling, reduction of the cardiac sound, and sound recording.

Various methods and tools have been described to capture sound:

-Using a unique microphone: It is the more frequently used method; the sensor is generally an electret microphone, the sampling frequency the most frequently used is the same as the one used for telephony codecs (8kHz). Others make use of an accelerometer; it is less sensitive to background noise¹⁴, but performance is must less than an electret microphone.

In our study, we will focus on the use of a unique microphone.

Heart sounds can introduce perturbations during the analysis of lung sounds. Most of the spectrum of heart sounds is located between 20 and 100Hz. According to the article of Elphick and colleagues²⁰, the attenuation of heart sounds is obtained thanks to a simple band-pass filter [50Hz, 2500Hz]. Nevertheless, a high-pass filter at 100Hz is not a good solution in so far as the main components of lung sounds are also located in this frequency range. Consequently, several methods have been tested²¹: wavelets, adaptative filtering with recursive least squares algorithm, time/frequency filtering, reconstruction, AR/MA estimation (autoregressive/mobile average) in time/frequency domain of wavelet coefficients, independent component analysis, and entropy based method.

2.3. Lung sound characteristics 

It is commonly admitted that lung sounds' frequency is in the frequency range [50, 2500Hz], and that tracheal sounds can reach up to 4000Hz; this allows to define a sampling frequency at 8kHz. The spectrum of heart sounds is defined between 20 and 100Hz for basic signals and higher frequency (upper than 500Hz) for breaths.

Abnormal sounds can be divided into two sub-classes²²: continuous or stationary sounds, like wheezes, rhonchus… and discontinuous or non-stationary sounds like fine or coarse crackles. Now, we are going to detail the characteristics of the two more studied noises: wheezes and crackles.²³

The identification of continuous adventitious breath sounds, such as wheeze in the respiratory cycle, is of great importance in the diagnosis of obstructive airways pathologies.²⁴ In fact, Sovijarvi and colleagues¹ indicate that wheezes can show acoustic characteristics symptomatic, not only of the presence of abnormalities in the respiratory system, but also of the severity and the location of the most frequently found airway obstructions in asthma and respiratory stenoses.

Wheezes, that Laennec calls dry wheezing groan, or wheezing, are sounds that have a duration (according to articles) greater than 50ms²⁵ or 100ms and lower than 250ms²⁴. The frequency of wheezes lies within 100 and 2500Hz, with a fundamental frequency between 100 (or 400²²) and 1000Hz²⁴ (or 1600Hz²⁵). On the other hand, Ref. ²² indicates that wheezes have a dominant frequency greater than 400Hz, contrary to rhonchus whose dominant frequency lies within 200Hz and below. TheFig. 1 shows an example of spectral representation of wheezes.

• 
  • View Large Image
  • Download to PowerPoint

• Fig. 1 

  Spectrogram of a wheeze (bronchiolities).

Finally, asthmatic subjects show wheezes during expiration phase; the latter have a duration range between 80 and 250ms¹⁴. Fiz²⁶ and Albers²⁷ are able to identify objectively the presence of an obstructive pathology. Likewise, Meslier et al.²⁸ associate wheezes to the following pathologies: infections such as croup, whooping cough, laryngitis, acute tracheobronchitis laryngo-, tracheo-, or bronchomalacia, laryngeal or tracheal tumours, tracheal stenosis, emotional laryngeal stenosis, foreign body aspiration, airway compression, and asthma.

Crackles correspond to short explosive sounds, generally associated with pulmonary disorders ²⁹, ³⁰, ³¹ (for instance lungs' infection, pneumonia, pulmonary oedema…). They are generally generated during the airways opening that was abnormally closed during the inspiration phase, or during the closing in end-expiration. Crackles' detection is important in so far as their number is a possible indicator of the severity of a pulmonary affection²⁹, airways disorders³². Nevertheless, all the more as their number, their positioning in the respiratory cycle and the waveform of their signal are characteristics of the lung pathologic case.¹

Crackles generally begin with a width deflection, followed by a long and damped sinusoidal wave³³, ³⁴ such as represented below:

IDW or initial deflection width represents the duration between the beginning of the crackle and the first deflection. 2CD (two-cycle duration) is the duration from the beginning of the crackle to the date at which the waveform did two complete cycles. TDW corresponds to the total duration of the signal crackle. It is accepted (²²) that the duration of a crackle is lower than 20ms and the frequency range is between 100 and 200Hz. TheFig. 2 is a temporal representation of a crackle. In addition, crackles can be divided into two families:

-Fine crackles (Laennec called them wet groan or “crépitations”) that are characterised, according to authors (respectively³⁵, ³⁶) by IDW=0.50ms or 0.90ms, 2CD=3.3ms or 6ms, and TDW=4ms. They are exclusively inspiratory.

-Coarse crackles (“râle muqueux” or “gargouillement” according to Laennec) that are characterised by IDW=1.0ms, 2CD=5.1ms, TDW=6.7ms for Ref.³⁶ and by IDW=1.25ms, 2CD=9.50ms for Ref. ³⁴; they are generally inspiratory, but can also be expiratory.

• 
  • View Large Image
  • Download to PowerPoint

• Fig. 2 

  Waveform of a crackle.

Article of puerile and colleagues²⁹ describes the principal pathologies where crackles can be found: pulmonary fibrosis (2CD<8ms, frequency around 200Hz), asbestosis (crackles' duration around 10ms), bronchiectasis (2CD>9ms, they generally appear late in the inspiratory cycle and have a relatively long duration compared to the respiratory phase), COPD (Chronic obstructive pulmonary disease) (2CD>9ms, generally starting early in inspiration and ending before the mid-point of inspiration), heart failure (2CD>10ms), pneumonia (2CD between 9 and 11ms, they appear mid-point of inspiration), sarcoidosis.

2.4. Detection of known markers 

Known markers are crackles and wheezes. The principal algorithm families of detection of these markers are summarised inTable 1.

Table 1. The principal algorithm families of detection of the known markers.

Signal	Characteristics and processing [7]	Analysis
Normal sounds
Lungs	Low-pass filtering (between 100 and 1000Hz)	Periodogram (power spectral density – PSD), auto-regressive models [37]
Trachea	Noise with resonances (100, 3000Hz)
Adventitious sounds
Wheezes	Sinusoid (range ∼100 and 1000Hz; duration>80ms)	PSD, STFT (short-time Fourier transform) [37], FFT, linear prediction of coefficients [38], genetic algorithms [39], neural networks [39], wavelet [24]
Ronchus	Series of sinusoid (<300Hz and a duration>100ms)
Crackles	Wave deflection (duration typically<20ms)	Temporal analysis [37], FFT, linear prediction of coefficients [38], fuzzy non-stationary filter [38], genetic algorithms [39], neural networks [39], wavelet 36, 40
Snores		Temporal analysis, PSD [37]
Stridors		PSD, STFT, auto-regressive models [37]

Back to Article Outline

3. ASAP: description of the project 

3.1. Context 

ASAP or “Analyse de Sons Auscultatoires et Pathologiques” is a 3-year-long French collaborative project. It is part of a collaborative telemedicine platform called MERCURE or “ Mobile Et Réseau pour la Clinique, l'Urgence ou la Résidence Externe ”. MERCURE (Fig. 3) deals with projects for remote monitoring or in clinical context thanks to modern tools principally coming from the News Technologies of Information and Communication.

• 
  • View Large Image
  • Download to PowerPoint

• Fig. 3 

  The MERCURE platform.

STETAU is the first project of the MERCURE platform; it aims at providing the patient and medical staff, measurement tools that are non-invasive, mobile, communicant and that allows to transmit vital information by a secured way, objectively qualified by signal processing tools. Thus, physicians will have access to a tool for remote monitoring and exploration of cardiac and pulmonary sounds.

ASAP aims at making evolve the auscultation technics:

Auscultation is the first medical act that the medical students can realise on patients; it is realised empirically. Our project proposes to introduce an evidence-based medicine dimension at auscultation thanks to an association with signal processing, visualisation and archiving technologies.⁴³ These new technologies will be considered for the formation of the future physicians and will be accessible by e-learning.

In the same way, the creation of a worldwide database named WebSound is an indispensable asset for capitalising these news technologies around a pertinent and exhaustive knowledge base. An example of interesting utilisation of the auscultation sounds database is the formation and the training of a physician to a specific pathology. Moreover, it will be possible to share auscultation sounds between experts thanks to a unified format. Thus, they will be able to discuss about a case and to affine their diagnosis.

Finally, our project aims at initialising fundamental research works for the definition of a visual and acoustical signature of pathology. The first pathologies studied will be asthma, bronchitis, CODP and cardiac pathologies.

The success of the projects is conditioned by the definition of standard formats of the data and exchange protocols.

3.2. Goal of the project and main technological challenges 

The studied system is a pair:

Our project aims at deploying this system on a medical community and at collecting an important number of qualifying sounds in order to create a referential. Thus, the global system is not only a measurement tool, but also a diagnosis tool that fundamentally replaces the auscultation medical act within clinical semiology.

3.3. Our value added 

Some projects or products already propose an evolution of the stethoscope; we can quote the stethoscope Littmann or Jabes. Some firms propose as well as their stethoscope, a CD-Rom with auscultation sounds… Nevertheless, they only allow a basic consultation with some examples, most theoretical, and that are neither interactive nor a diagnosis support.

In our project, our ambition is not to propose a stethoscope and to provide in addition sounds, but the exact opposite. Indeed, we will propose a worldwide sound database with visual and acoustical signatures, that allow to consult and analyse sounds, realise standard exchange of data. These sounds will, all the more, be a support for learning auscultation. From those data, a worldwide auscultation sounds database could be created. It will list an important quantity of data and will allow to create models or criteria to improve detecting of pulmonary and cardiac diseases. Another innovative aspect of our project is to make diagnosis aid.

3.4. Description of the ASAP project 

As described on theFig. 5, there are some major phases in the project. The first point is the realisation of a worldwide auscultation sounds database (WebSound). Then, health professionals and medical students could use this database. The students would dispose of a diversified palette of sounds via new technologies of communication and information. It will allow to make continuous formations concerning precise pathologies. Thus, the Auscultation's School will be created.

• 
  • View Large Image
  • Download to PowerPoint

• Fig. 5 

  ASAP project.

Besides, in order to allow the inter-connexion of the information systems of the hospitals, we are working on the normalisation of the used formats. Afterwards, it will be possible to exchange sounds between experts, thanks to a unified format. The expert could discuss about a medical case, and refine the diagnosis. A study at the state of the art will be realised for the sounds' analysis, in order to be able to qualify and compare them. Finally, the database will be used to initialise research works concerning the definition of the acoustical signature of a pathology. The aim is to make auscultation more objective and pre-detect pathology.

Back to Article Outline

4. Perspectives: the Auscultation's School 

In a nutshell, it can be said that auscultation is an individual act, difficult to share. On the contrary, the Auscultation's School will lean on an objective definition of the sounds useful for teaching and diagnosis aid. The Auscultation's School will have the purpose for student and professionals to learn the new available tools. In the same way, research programs will try to detect new markers, detect pre-markers from some pathologies…

The project begins by the scientific and clinical validation of the service for several pathologies: COPD, cardiopathies, asthma, and bronchitis. This step allows to collect auscultation sounds that are categorized and qualified thanks to an intelligent comparison and evaluation of the sounds. The final goal is to create a worldwide referential interconnected to medical study centers, pharmaceutical research laboratories and auscultation sounds processing systems.

Empirical methods provides already results to show the value added of the analyse and the comparison of the sounds for instance for the correlation between the pulmonary blocking of a patient with cystic fibrosis and the rate of detected crackles, the evolution of the acoustic signature of a cardiac valve…

The main strengths of such a referential are:

The different elements present in the Auscultation's School will be:

The access to the teaching could be initial or ongoing training. Modern learning tools will be privileged. This formation will be accessible by each medical professional, and maybe more.

The first goal of such an initiative is the repositioning of the auscultation as a fundamental non-invasive exam in the medical diagnosis; while pushing to potentialities thanks to the new technologies.

Back to Article Outline

5. Conclusion/future work 

Today we are testing and studying different algorithms in the context of the ASAP project.

The next step will consist in exploiting all the diversity of the sound. This augmentation of the spectrum studied and linked to signal analysis techniques will allow the definition of new characteristic markers.

Previous studies demonstrate the need of performing an exhaustive scientific approach, that accounts of both the definition of a semiology, the consolidation of definition of known characteristics markers, the definition of common or even universal semantics, the development of determinist tools that will allow the detection of these markers. It is precisely the context of an ambitious study of in the so-called ASAP project. This study is handled by a multidisciplinary team including medical from CHRU of Strasbourg, IRCAD for web-based teaching tools, Alcatel-Lucent research teams for the development of the tools and algorithms. Among the most identified outcome from the project, it is force in to create auscultation school hosted by the “ Faculté de Médecine” of Strasbourg.

Back to Article Outline

6. Grant 

ASAP project (ANR convention no. 2006 TLOG 21 04).

Back to Article Outline

Acknowledgments 

This work has been performed in the framework of the projects from the platform MERCURE, and more specifically especially the ASAP project. We would like to acknowledge the partners of the project.

Back to Article Outline

CME section 

This article has been accredited for CME learning by the European Board of Accreditation in Pneumology (EBAP). You can receive 1 CME credit by successfully answering these questions online.

Back to Article Outline

Educational questions 

Answer the following questions:

1.Lung sounds:

A – are included in a frequency range from 50 to 2500Hz

B – are included in a frequency range from 500 to 1500Hz

C – are divided into normal and adventitious sounds

D – are divided into continuous and discontinuous sounds

E – are well acoustically characterized

Please select one correct answer from the list below:

Please select one correct answer from the list below:

3.Wheeze:

A – is adventitious and continuous sound

B – is adventitious and inspiratory sound

C – is acoustically characterized by periodic waveforms with a dominant frequency usually over 100Hz and with duration of ≥100ms

D – is usually associated with airways obstruction

E – is usually associated with pathological process in pulmonary tissue

Please select one correct answer from the list below:

4.Rhonchus:

A – is a low-pitched wheeze

B – is a type of crackles

C – containing rapidly damping periodic waveforms with a duration of >100ms and frequency of <300Hz

D – is often associated with airways obstruction

E – is usually found in interstitial pneumonia

Please select one correct answer from the list below:

Please select one correct answer from the list below:

Back to Article Outline

References 

1. Sovijarvi AR, Malmberg LP, Charbonneau G, Vandershoot J. Characteristics of breath sounds and adventitious respiratory sounds. European Respiratory Review. 2000;10:591–596
   • View In Article
2. Kiyokawa H, Greenberg M, Shirota K, Pasterkamp H. Auditory detection of stimulated crackles in breath sounds. Chest. 2006;119:1886–1892
   • View In Article
   • MEDLINE
   • CrossRef
3. Bahoura M. Analyse des signaux acoustiques respiratoires: contribution à la detection automatique des sibilants par paquets d'ondelettes. PhD thesis Univ, Univ. Rouen, France, 1999.
   • View In Article
4. Chuah JS, Moussavi ZK. Automated respiratory phase detection by acoustical means. University of Manitoba, Dept. of Electrical and Computer Engineering; May 2004;
   • View In Article
5. Earis JE, Cheetham BM. Future perspectives for respiratory sound research. Techniques for respiratory sound analysis. European Respiratory Review. 2000;10:636–640
   • View In Article
6. Sestini P, Renzoni E, Rossi M, Beltrami V, Vagliasindi M. Multimedia presentation of lung sounds as learning aid for medical students. The European Respiratory Journal. 1995;8:783–788
   • View In Article
7. Pasterkamp H, Kraman SS, Wodicka GR. Respiratory sounds, advances beyond the stethoscope. American Journal of Respiratory and Critical Care Medicine. 1997;156:974–987
   • View In Article
   • MEDLINE
8. Elphick HE, Sherlock P, Foxall G, Simpson EJ, Shiell NA, Primhak RA, et al. Survey of respiratory sounds in infants. Archives of Disease in Childhood. 2001;84:35–39
   • View In Article
   • CrossRef
9. Sovijarvi AR, Dalmasso F, Vanderschoot J, Malmberg LP, Righini G, Stoneman SA. Definition of terms for applications of respiratory sounds. European Respiratory Review. 2000;10:597–610
   • View In Article
10. Rossi M, Sovijarvi AR, Piirila P, Vannuccini L, Dalmasso F, Vanderschoot J. Environmental and subject conditions and breathing manœuvres for respiratory sound recordings. European Respiratory Review. 2000;10:611–615
    • View In Article
11. Vanuccini L, Earis JE, Helisto P, Cheetham BM, Rossi M, Sovijarvi AR, et al. Capturing and pre-processing of respiratory sounds. The European Respiratory Review. 2000;10:616–620
    • View In Article
12. Welsby PD, Parry G, Smith D. The stethoscope: some preliminary investigations. Postgraduate Medical Journal Online. 2003;79:695–698
    • View In Article
13. Kaniusas E, Pfützner H, Saletu B. Acoustical signal properties for cardiac/respiratory activity and apneas. IEEE Transactions on Biomedical Engineering. 2005;52:1812–1822
    • View In Article
    • MEDLINE
    • CrossRef
14. Mazic J, Sovilj S, Magjarevic R. Analysis of respiratory sounds in asthmatic infants. Polytechnic of Dubrovnik, Measurement Science Review. 2003;3:11–21
    • View In Article
15. Kompis M, Pasterkamp H, Wodicka GR. Acoustic imaging of the human chest. Chest. 2001;120:1309–1321
    • View In Article
    • MEDLINE
    • CrossRef
16. Benedetto G, Dalmasso F, Spagnolo R. Surface distribution of crackles sounds. IEEE Transactions on Biomedical Engineering. 1988;35:406–412
    • View In Article
    • MEDLINE
    • CrossRef
17. Hussein M, Richard S. Acoustic detection of respiratory conditions. United States Patent; 2002;US6443907
    • View In Article
18. Laubscher TP, Heinrichs W, Weiler N, Hartmann G, Brunner JX. An adaptive lung ventilation controller. IEEE Transactions on Biomedical Engineering. 1994;41:51–59
    • View In Article
    • MEDLINE
    • CrossRef
19. Gan K, Nishi I, Chin I, Slutsky AS. On-line determination of pulmonary blood flow using respiratory inert gas analysis. IEEE Transactions on Biomedical Engineering. 1993;40:1250–1259
    • View In Article
    • MEDLINE
    • CrossRef
20. Elphick HE, Ritson S, Rodgers H, Everard ML. When a wheeze is not a wheeze: acoustic analysis of breath sounds in infants. The European Respiratory Journal. 2000;16:593–597
    • View In Article
21. Moussavi ZMK. Respiratory and swallowing sound analysis. www.ee.umanitoba.ca/∼moussavi/research/research_acoustic.htm[accessed: 6 June 2007]
    • View In Article
22. Bahoura M, Lu X. Separation of crackles from vesicular sounds using wavelet packet transform. Acoustics, Speech and Signal Processing ICASSP. 2006;2:1076–1079
    • View In Article
23. Pasika H, Pengelly D. Lung sound crackle analysis using generalized time-frequency representations. Medical and Biological Engineering and Computing. 1994;32:688–690
    • View In Article
24. Hadjileontiadis L, Panoulas K, Penzel T, Gross V, Panas S. On applying continuous wavelet transform in wheeze analysis. Engineering in Medicine and Biology Society IEEE. 2004;2:3832–3835
    • View In Article
25. Yi GA. A software toolkit for respiratory analysis. MIT Computer Sound and Artificial Intelligence Laboratory. 2004;1:215–216
    • View In Article
26. Fiz JA, Jane R, Homs A, Izquiero J, Garcia MA, Morera J. Detection of wheezing during maximal forced exhalation in patents with obstructed airways. Chest. 2002;122:186–191
    • View In Article
    • MEDLINE
    • CrossRef
27. Albers M, Schermer T, van den Boom G, Akkermans R, van Schayck C, van Herwaarden C, et al. Efficacy of inhaled steroids in undiagnosed subjects at high risk for COPD: results of the detection, intervention, and monitoring of COPD and asthma. Chest. 2004;126:1815–1824
    • View In Article
    • MEDLINE
    • CrossRef
28. Meslier N, Charbonneau G, Racineux J-L. Wheezes. The European Respiratory Journal. 1995;8:1942–1948
    • View In Article
29. Piirila P, Sovijarvi AR. Crackles: recording, analysis and clinical significance. The European Respiratory Journal. 1995;8:2139–2148
    • View In Article
30. Hantos Z, Aszalos T, Tolnai J, Petaz F, Suki B. Volume incroments and crackles sounds during lung reinflation. IEEE, Proceedings of the First Joint EMBS/BMES Conference. 1999;354
    • View In Article
31. Mascagni O, Doyle GA. Infant distress vocalizations in the southern african lesser bushbaby. International Journal of Primatology. 1993;14:41–60
    • View In Article
32. Suki B, Alencar AM, Hantos Z, Stanley HE. Generation and propagation of crackle sound and it's relation to lung structure. Bioengineering Conference, BED-ASME. 2001;50:639–640
    • View In Article
33. Yeginerand M, Kahya YP. Modeling of pulmonary crackles using wavelet networks. Engineering in Medicine and Biology Society IEEE-EMBS. 2005;8:7560–7563
    • View In Article
34. Vannuccini L, Rossi M, Pasquali G. A new method to detect crackles in respiratory sounds. Technology and Health Care. 1998;6:75–79
    • View In Article
35. Tolias Y, Hadjileontiadis L, Panas S. A fuzzy rule-based system for real-time separation of crackles from vesicular sounds. Engineering in Medicine and Biology Society IEEE. 1997;3:1115–1118
    • View In Article
36. Hadjileontiadis L, Rekanos L. Detection of explosive lung and bowel sounds by means of fractal dimension. Signal Processing Letters IEEE. 2003;10:311–314
    • View In Article
37. Charbonneau G, Ademovic E, Cheetham BM, Malmberg LP, Vanderschoot J, Sovijarvi AR. Basic techniques for respiratory sound analysis. European Respiratory Review. 2000;10:625–635
    • View In Article
38. Cohen A, Landsberg D. Analysis and automatic classification of breath sounds. IEEE Transactions on Biomedical Engineering. 1984;31:585–590
    • View In Article
    • MEDLINE
39. Guler , Polat H, Ergun U. Combining neural network and genetic algorithm for prediction of lung sounds. Journal of Medical Systems. 2005;29:217–231
    • View In Article
    • MEDLINE
    • CrossRef
40. Du M, Chan FHY, Lam FK, Sun J. Crackles detection and classification based on matched wavelet analysis. IEEE/EMBS. 1997;32:1638–1641
    • View In Article
41. Reichert S, Gass R, Brandt C, Andrès E. Analysis of respiratory sounds: state of the art. Clinical Medicine Circulatory Respiratory Pulmonary Medicine. 2008;2:45–58
    • View In Article
42. Reichert S, Gass R, Brandt C, Andrès E. L'auscultation pulmonaire à l'ère de la médecine factuelle. Revue des Maladies Respiratoires. 2008;25:1–9
    • View In Article
    • CrossRef
43. Andrès E, Brandt C, Gass R. De l'intérêt de caractériser les sons de l'auscultation pulmonaire à la création d'une école de l'auscultation…. Presse Médicale. 2008;37:925–927
    • View In Article