Analysis of Respiratory Sounds: State of the Art

Reichert, S.; Gass, Raymond; Brandt, Christian; Andrès, Emmanuel

doi:10.4137/ccrpm.s530

Cited by 195 publications

(152 citation statements)

References 55 publications

Supporting

Mentioning

124

Contrasting

Unclassified

Order By: Relevance

“…Batra et al [2] explored features such as harmonic to noise ratio (HNR), jitter and shimmer in the sustained vowel phonation for identifying asthma patients. There are several works that classify asthma using respiratory sound based on pitch [6], [20], dominant frequency range [11], [12] and duration of the breath [22]. To the best of our knowledge, there is no work reported on predicting spirometry readings from cough and wheeze for asthma level monitoring.…”

Section: Introductionmentioning

confidence: 97%

Automatic prediction of spirometry readings from cough and wheeze for monitoring of asthma severity

Rao

Kausthubha

Yadav

et al. 2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

Abstract-We consider the task of automatically predicting spirometry readings from cough and wheeze audio signals for asthma severity monitoring. Spirometry is a pulmonary function test used to measure forced expiratory volume in one second (FEV1) and forced vital capacity (FVC) when a subject exhales in the spirometry sensor after taking a deep breath. FEV1%, FVC% and their ratio are typically used to determine the asthma severity. Accurate prediction of these spirometry readings from cough and wheeze could help patients to non-invasively monitor their asthma severity in the absence of spirometry. We use statistical spectrum description (SSD) as the cue from cough and wheeze signal to predict the spirometry readings using support vector regression (SVR). We perform experiments with cough and wheeze recordings from 16 healthy persons and 12 patients. We find that the coughs are better predictor of spirometry readings compared to the wheeze signal. FEV1%, FVC% and their ratio are predicted with root mean squared error of 11.06%, 10.3% and 0.08 respectively. We also perform a three class asthma severity level classification with predicted FEV1% and obtain an accuracy of 77.77%.

show abstract

Section: Introductionmentioning

confidence: 97%

Automatic prediction of spirometry readings from cough and wheeze for monitoring of asthma severity

Rao

Kausthubha

Yadav

et al. 2017

2017 25th European Signal Processing Conference (EUSIPCO)

View full text Add to dashboard Cite

show abstract

“…Подобные хрипы обычно ассоциируются с обструк тивными нарушениями дыхания вследствие самых разных причин и если они содержат одинаковые частотные характеристики, то называются моно фоническими (однотонными), а если несколько -полифоническими [16][17][18]. Полифонические сви стящие хрипы указывают на более серьезные обструктивные нарушения [19].…”

Section: дискуссииunclassified

Bronchial asthma, wheezing, flatter: probable relationships

Абросимов

2017

Pulʹmonologiâ (Mosk.)

View full text Add to dashboard Cite

ДискуссииБронхиальная астма (БА) является одним из широко распространенных заболеваний. В соответствии с со временными представлениями БА -это хроничес кое персистирующее воспалительное заболевание, ведущее к структурным изменениям и ремоделиро ванию дыхательных путей (ДП). В понятие «ремо делирование» включены следующие основные ком поненты: гипертрофия гладких мышц, гиперплазия бокаловидных клеток, субэпителиальный (субба зальный) фиброз и ангиогенез [1][2][3][4][5]; развитие брон хиальной гиперреактивности [6].Хронический воспалительный процесс, ремоде лирование ДП, бронхиальная гиперреактивность, бронхиальная обструкция определяют характерные клинические симптомы БА -свистящие хрипы, ка шель, диспноэ [7][8][9], причем свистящее дыхание относится к наиболее частым из них. Так, по данным эпидемиологического исследования ECRHS (Euro pean Community Respiratory Health Survey) о распрост раненности симптомов БА среди лиц (мужчин и жен щин) 20-44 летнего возраста приступы удушья встречаются в среднем у 9,7 %, а свистящее дыха ние -у 32,0 % больных [10]. По результатам эпиде миологического исследования SAPALDIA свистя щие хрипы выявлены у 1 360 (14 %) лиц общей популяции из 9 651 обследованного. У 168 (75 %) из 225 больных БА свистящие хрипы являлись самым распространенным симптомом [11].В большинстве сообщений, включая доклад ра бочей группы GINA (Глобальная стратегия лечения и профилактика бронхиальной астмы, 2015), указы вается, что свистящее дыхание (wheezing) является одним из ключевых диагностических критериев БА [12][13][14]. У больных БА проведен анализ парамет ров легочных звуков в сопоставлении с данными ле гочных функций. Сделано заключение, что оценка легочных звуков может успешно применяться в ка честве биомаркера БА AbstractWheezing is the most common clinical sign and one of the key diagnostic criteria of asthma. Pathophysiology of wheezing is not fully recognized. A theory of hemodynamic flatter is widely adopted. Effects of vibration are actively investigated in patients with snore and obstructive sleep apnea. Vibration can contribute to the upper airway inflammation and endothelial dysfunction in snoring patients. Therefore, the flatter (vibration) effect could be the key mechanism of wheezing in asthma patients and could promote similar changes in the lower airway microvasculature. Recently, CPAP therapy has been shown to reduce asthma symptoms and bronchial hyperresponsiveness and acts as a mechanical bronchodilator is patients with asthma without sleep associated breathing disorders.

show abstract

“…[4][5][6][7][8][9][10] Computerized lung sound analysis involves recording the patient lung sound via an electronic device, followed by computer analysis and classification of lung sounds based on specific signal characteristics. [2,11] Gurung et al conducted a review and an in-depth analysis of relevant classification studies using a computerized lung sound analysis in which the overall sensitivity and specificity of implemented algorithms were estimated. [12] Nowadays, the use of computerized diagnostic tools enjoys wide popularity in the healthcare facilities.…”

Section: What This Study Adds To the Fieldmentioning

confidence: 99%

An alternative respiratory sounds classification system utilizing artificial neural networks

et al. 2015

View full text Add to dashboard Cite

R espiratory sound (RS) is regarded one of the most significant biosignals used to diagnose certain respiratory abnormalities. It is established that breath sounds are created in the larger airways as a result of vibrations that are generated due to air velocity and turbulence. RSs are known to be highly non-stationary and non-linear due to variations in the airflow rate and airflow volumes during the respiratory cycle. The non-linearity of the RS stems mainly from the complex turbulent flow dynamics and its structural interaction with the larger airway walls.RSs detected from the chest wall and mouth may be classified as normal and adventitious sounds. Owing to the presence of adventitious (abnormal) sounds, such signals convey valuable information pertaining to the underlying malfunctioning of the pulmonary system. On the other hand, normal sounds include those generated by healthy Original Article An Alternative Respiratory Sounds Classification System Utilizing Artificial Neural NetworksRami J. Oweis, Enas W. Abdulhay, Amer Khayal, Areen AwadBackground: Computerized lung sound analysis involves recording lung sound via an electronic device, followed by computer analysis and classification based on specific signal characteristics as non-linearity and nonstationarity caused by air turbulence. An automatic analysis is necessary to avoid dependence on expert skills. Methods:This work revolves around exploiting autocorrelation in the feature extraction stage. All process stages were implemented in MATLAB. The classification process was performed comparatively using both artificial neural networks (ANNs) and adaptive neuro-fuzzy inference systems (ANFIS) toolboxes. The methods have been applied to 10 different respiratory sounds for classification. Results:The ANN was superior to the ANFIS system and returned superior performance parameters. Its accuracy, specificity, and sensitivity were 98.6%, 100%, and 97.8%, respectively. The obtained parameters showed superiority to many recent approaches. Conclusions: The promising proposed method is an efficient fast tool for the intended purpose as manifested in the performance parameters, specifically, accuracy, specificity, and sensitivity. Furthermore, it may be added that utilizing the autocorrelation function in the feature extraction in such applications results in enhanced performance and avoids undesired computation complexities compared to other techniques. (Biomed J 2015;38:153-161)

show abstract

Analysis of Respiratory Sounds: State of the Art

Cited by 195 publications

References 55 publications

Automatic prediction of spirometry readings from cough and wheeze for monitoring of asthma severity

Automatic prediction of spirometry readings from cough and wheeze for monitoring of asthma severity

Bronchial asthma, wheezing, flatter: probable relationships

An alternative respiratory sounds classification system utilizing artificial neural networks

Contact Info

Product

Resources

About