Automatic Wheezing Detection Based on Signal Processing of Spectrogram and Back‐Propagation Neural Network

Lin, Bor-Shing; Wu, Huey-Dong; Chen, Sao-Jie

doi:10.1260/2040-2295.6.4.649

Cited by 38 publications

(20 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BPNN was also used by [49] to perform recording classification. The study used 58 recordings with 32 of them containing wheezes obtained using an ECM microphone.…”

Section: Resultsmentioning

confidence: 99%

Automatic adventitious respiratory sound analysis: A systematic review

2017

View full text Add to dashboard Cite

BackgroundAutomatic detection or classification of adventitious sounds is useful to assist physicians in diagnosing or monitoring diseases such as asthma, Chronic Obstructive Pulmonary Disease (COPD), and pneumonia. While computerised respiratory sound analysis, specifically for the detection or classification of adventitious sounds, has recently been the focus of an increasing number of studies, a standardised approach and comparison has not been well established.ObjectiveTo provide a review of existing algorithms for the detection or classification of adventitious respiratory sounds. This systematic review provides a complete summary of methods used in the literature to give a baseline for future works.Data sourcesA systematic review of English articles published between 1938 and 2016, searched using the Scopus (1938-2016) and IEEExplore (1984-2016) databases. Additional articles were further obtained by references listed in the articles found. Search terms included adventitious sound detection, adventitious sound classification, abnormal respiratory sound detection, abnormal respiratory sound classification, wheeze detection, wheeze classification, crackle detection, crackle classification, rhonchi detection, rhonchi classification, stridor detection, stridor classification, pleural rub detection, pleural rub classification, squawk detection, and squawk classification.Study selectionOnly articles were included that focused on adventitious sound detection or classification, based on respiratory sounds, with performance reported and sufficient information provided to be approximately repeated.Data extractionInvestigators extracted data about the adventitious sound type analysed, approach and level of analysis, instrumentation or data source, location of sensor, amount of data obtained, data management, features, methods, and performance achieved.Data synthesisA total of 77 reports from the literature were included in this review. 55 (71.43%) of the studies focused on wheeze, 40 (51.95%) on crackle, 9 (11.69%) on stridor, 9 (11.69%) on rhonchi, and 18 (23.38%) on other sounds such as pleural rub, squawk, as well as the pathology. Instrumentation used to collect data included microphones, stethoscopes, and accelerometers. Several references obtained data from online repositories or book audio CD companions. Detection or classification methods used varied from empirically determined thresholds to more complex machine learning techniques. Performance reported in the surveyed works were converted to accuracy measures for data synthesis.LimitationsDirect comparison of the performance of surveyed works cannot be performed as the input data used by each was different. A standard validation method has not been established, resulting in different works using different methods and performance measure definitions.ConclusionA review of the literature was performed to summarise different analysis approaches, features, and methods used for the analysis. The performance of recent studies showed a high agreement with conventiona...

show abstract

“…BPNN was also used by [49] to perform recording classification. The study used 58 recordings with 32 of them containing wheezes obtained using an ECM microphone.…”

Section: Resultsmentioning

confidence: 99%

Automatic adventitious respiratory sound analysis: A systematic review

2017

View full text Add to dashboard Cite

show abstract

“…Both models enhance the diagnostic abilities of the interpreter who listens and visualizes the respective phonogram, promising easier and more objective acquisition of breath sound teaching skills. 17,[20][21][22] Machine learning models in chest auscultation, when combined with machine learning heart sound models, [21][22][23][24] promise an ease of medical education, implementation of telemedicine, screening of cohorts, diagnosis and medical practice in the near future.…”

Section: Discussionmentioning

confidence: 99%

<p>The Machine Learned Stethoscope Provides Accurate Operator Independent Diagnosis of Chest Disease</p>

Kotb¹,

Elmahdy²,

Dein³

et al. 2020

MDER

View full text Add to dashboard Cite

Introduction: Contemporary stethoscope has limitations in diagnosis of chest conditions, necessitating further imaging modalities. Methods: We created 2 diagnostic computer aided non-invasive machine-learning models to recognize chest sounds. Model A was interpreter independent based on hidden markov model and mel frequency cepstral coefficient (MFCC). Model B was based on MFCC, hidden markov model, and chest sound wave image interpreter dependent analysis (phonopulmonography (PPG)). Results: We studied 464 records of actual chest sounds belonging to 116 children diagnosed by clinicians and confirmed by other imaging diagnostic modalities. Model A had 96.7% overall correct classification rate (CCR), 100% sensitivity and 100% specificity in discrimination between normal and abnormal sounds. CCR was 100% for normal vesicular sounds, crepitations 89.1%, wheezes 97.6%, and bronchial breathing 100%. Model B's CCR was 100% for normal vesicular sounds, crepitations 97.3%, wheezes 97.6%, and bronchial breathing 100%. The overall CCR was 98.7%, sensitivity and specificity were 100%. Conclusion: Both models demonstrated very high precision in the diagnosis of chest conditions and in differentiating normal from abnormal chest sounds irrespective of operator expertise. Incorporation of computer-aided models in stethoscopes promises prompt, precise, accurate, cost-effective, non-invasive, operator independent, objective diagnosis of chest conditions and reduces number of unnecessary imaging studies.

show abstract

“…We aim to design our sensor such that it resonates within the frequency range of wheezing in order to achieve the maximum output signal. While the frequency of a wheeze from the trachea lies in the range of 100-2500 Hz, it is reduced to 100-1000 Hz from the chest because lung tissue, chest wall, and skin absorb the higher frequencies before they reach our sensor [5,6]. The chest-wall tissue acts as a low-pass spectral constraint on respiratory sounds, which, when measured on the skin surface with an acoustic sensor (microphone or accelerometer) positioned on human chest, back or neck, typically reside in the frequency band below 1 kHz [26].…”

Section: B Diaphragm Material Size and Shape Selectionmentioning

confidence: 99%

“…A study showed that asthma can be diagnosed at an early stage using non-invasive practices by monitoring the airway resistance in the trachea [4]. This airway resistance produces wheezing characterized by musical, sinusoidal sounds superimposed on breathing with frequencies of 100-1000 Hz and a duration of >250ms [5][6][7][8][9]. Similar to the behavior of sound, wheezing travels through a medium in the form of pressure fluctuations.…”

Section: Introductionmentioning

confidence: 99%

Design Analysis and Human Tests of Foil-Based Wheezing Monitoring System for Asthma Detection

Khan

Qaiser

Shaikh

et al. 2020

IEEE Trans. Electron Devices

View full text Add to dashboard Cite

We present a flexible acoustic sensor that has been designed to detect wheezing (a common symptom of asthma) while attached to the chest of a human. We adopted a parallel plate capacitive structure using air as the dielectric material. The pressure (acoustic) waves from wheezing vibrate the top diaphragm of the structure, thereby, changing the output capacitance. The sensor is designed such that it resonates in the frequency range of wheezing (100-1000Hz) which presents twofold benefits. The resonance results in large deflection of the diaphragm that eradicates the need for using signal amplifiers (used in microphones). Secondly, the design itself acts as a low pass filter to reduce the effect of background noise which mostly lies in >1000Hz frequency range. The resulting analog interface is minimal and thus, consumes less power and occupies less space. The sensor is made up of low-cost sustainable materials (aluminum foil) which greatly reduces the cost and complexity of manufacturing processes. A robust wheezing detection (Matched filter) algorithm is used to identify different types of wheezing sounds among the noisy signals originating from the chest that lie in the same frequency range as wheezing. The sensor is connected to a smartphone via Bluetooth, enabling signal processing and further integration into digital medical electronic systems based on the Internet of Things (IoT). Bending, cyclic pressure, heat, and sweat tests are performed on the sensor to evaluate its performance in simulated real-life harsh conditions.

show abstract

Automatic Wheezing Detection Based on Signal Processing of Spectrogram and Back‐Propagation Neural Network

Cited by 38 publications

References 30 publications

Automatic adventitious respiratory sound analysis: A systematic review

Automatic adventitious respiratory sound analysis: A systematic review

<p>The Machine Learned Stethoscope Provides Accurate Operator Independent Diagnosis of Chest Disease</p>

Design Analysis and Human Tests of Foil-Based Wheezing Monitoring System for Asthma Detection

Contact Info

Product

Resources

About