Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 9.422
Filtrar
1.
Support Care Cancer ; 29(1): 179-185, 2021 Jan.
Artigo em Inglês | MEDLINE | ID: mdl-32328774

RESUMO

PURPOSE: To characterize the practice of subcutaneous hydration provision in the Beer-Sheva home care hospice unit. We also explore the potential connection between the provision of subcutaneous hydration and the incidence of death rattle. METHODS: This was a prospective observational study involving 120 hospice patients. During the 6 days before death, hospice staff recorded whether or not fluids were administered orally and/or subcutaneously; the duration, timing, and quantity of fluid administration; the incidence, timing, and duration of death rattle; and whether medications that can affect death rattle were given. RESULT: Fifty-three percent of the patients received subcutaneous hydration. The mean daily volume administered in the hydration group was 434 ml. There was a significant association between the duration of treatment in the hospice unit and provision of subcutaneous hydration (mean of 51 days in hydration group vs. 31 days in non-hydration group, p = 0.03). Although not statistically significant, males were more likely to receive subcutaneous hydration than females (62% of males vs. 46% of females, p = 0.09). There was a higher incidence of death rattle in men compared to women (54.7% in men vs. 32.8% in women, p = 0.025). A statistically significant association between death rattle and the provision of subcutaneous hydration wasn't demonstrated. CONCLUSION: The decision of whether to provide subcutaneous hydration is individualized taking into consideration the values of the patients and their families. The provision of 500 ml per day of subcutaneous saline during the last 6 days of life does not significantly increase the incidence of death rattle.


Assuntos
Hidratação/métodos , Sons Respiratórios/fisiologia , Águas Salinas/uso terapêutico , Assistência Terminal/métodos , Adulto , Idoso , Idoso de 80 Anos ou mais , Morte , Feminino , Cuidados Paliativos na Terminalidade da Vida/métodos , Humanos , Masculino , Pessoa de Meia-Idade , Estudos Prospectivos
3.
PLoS One ; 15(12): e0243735, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33315873

RESUMO

INTRODUCTION: Wheezing is a major problem in children, and respiratory viruses are often believed to be the causative agent. While molecular detection tools enable identification of respiratory viruses in wheezing children, it remains unclear if and how these viruses are associated with wheezing. The objective of this systematic review is to clarify the prevalence of different respiratory viruses in children with wheezing. METHODS: We performed an electronic in Pubmed and Global Index Medicus on 01 July 2019 and manual search. We performed search of studies that have detected common respiratory viruses in children ≤18 years with wheezing. We included only studies using polymerase chain reaction (PCR) assays. Study data were extracted and the quality of articles assessed. We conducted sensitivity, subgroup, publication bias, and heterogeneity analyses using a random effects model. RESULTS: The systematic review included 33 studies. Rhinovirus, with a prevalence of 35.6% (95% CI 24.6-47.3, I2 98.4%), and respiratory syncytial virus, at 31.0% (95% CI 19.9-43.3, I2 96.4%), were the most common viruses detected. The prevalence of other respiratory viruses was as follows: human bocavirus 8.1% (95% CI 5.3-11.3, I2 84.6%), human adenovirus 7.7% (95% CI 2.6-15.0, I2 91.0%), influenza virus6.5% (95% CI 2.2-12.6, I2 92.4%), human metapneumovirus5.8% (95% CI 3.4-8.8, I2 89.0%), enterovirus 4.3% (95% CI 0.1-12.9, I2 96.2%), human parainfluenza virus 3.8% (95% CI 1.5-6.9, I2 79.1%), and human coronavirus 2.2% (95% CI 0.6-4.4, I2 79.4%). CONCLUSIONS: Our results suggest that rhinovirus and respiratory syncytial virus may contribute to the etiology of wheezing in children. While the clinical implications of molecular detection of respiratory viruses remains an interesting question, this study helps to illuminate the potential of role respiratory viruses in pediatric wheezing. REVIEW REGISTRATION: PROSPERO, CRD42018115128.


Assuntos
Sons Respiratórios/etiologia , Sons Respiratórios/genética , Infecções Respiratórias/diagnóstico , Bocavirus/genética , Bocavirus/isolamento & purificação , Bocavirus/patogenicidade , Criança , Pré-Escolar , Coronavirus/isolamento & purificação , Coronavirus/patogenicidade , Humanos , Orthomyxoviridae/genética , Orthomyxoviridae/isolamento & purificação , Orthomyxoviridae/patogenicidade , Vírus da Parainfluenza 1 Humana/genética , Vírus da Parainfluenza 1 Humana/isolamento & purificação , Vírus da Parainfluenza 1 Humana/patogenicidade , Reação em Cadeia da Polimerase , Sons Respiratórios/fisiopatologia , Sistema Respiratório/patologia , Sistema Respiratório/virologia , Infecções Respiratórias/genética , Infecções Respiratórias/virologia
4.
J Acoust Soc Am ; 148(6): 3385, 2020 12.
Artigo em Inglês | MEDLINE | ID: mdl-33379875

RESUMO

Forced expiratory (FE) noise is a powerful bioacoustic signal containing information on human lung biomechanics. FE noise is attributed to a broadband part and narrowband components-forced expiratory wheezes (FEWs). FE respiratory noise is composed by acoustic and hydrodynamic mechanisms. An origin of the most powerful mid-frequency FEWs (400-600 Hz) is associated with the 0th-3rd levels of bronchial tree in terms of Weibel [(2009). Swiss Med. Wkly. 139(27-28), 375-386], whereas high-frequency FEWs (above 600 Hz) are attributed to the 2nd-6th levels of bronchial tree. The laboratory prototype of the apparatus is developed, which includes the electret microphone sensor with stethoscope head, a laptop with external sound card, and specially developed software. An analysis of signals by the new method, including FE time in the range from 200 to 2000 Hz and band-pass durations and energies in the 200-Hz bands evaluation, is applied instead of FEWs direct measures. It is demonstrated experimentally that developed FE acoustic parameters correspond to basic indices of lung function evaluated by spirometry and body plethysmography and may be even more sensitive to some respiratory deviations. According to preliminary experimental results, the developed technique may be considered as a promising instrument for acoustic monitoring human lung function in extreme conditions, including diving and space flights. The developed technique eliminates the contact of the sensor with the human oral cavity, which is characteristic for spirometry and body plethysmography. It reduces the risk of respiratory cross-contamination, especially during outpatient and field examinations, and may be especially relevant in the context of the COVID-19 pandemic.


Assuntos
Acústica/instrumentação , Expiração/fisiologia , Sons Respiratórios/diagnóstico , Humanos , Ruído
5.
BMJ Case Rep ; 13(12)2020 Dec 13.
Artigo em Inglês | MEDLINE | ID: mdl-33318277

RESUMO

A 59-year-old man presented to the emergency department with recent onset biphasic stridor, dyspnoea and increased work of breathing on the background of prolonged intubation for the novel COVID-19 2 months previously. Flexible laryngoscopy revealed bilateral vocal fold immobility with a soft tissue mass in the interarytenoid region. The patient's symptoms improved with oxygen therapy, nebulised epinephrine (5 mL; 1:10 000) and intravenous dexamethasone (3.3 mg). The following morning, the patient was taken to theatre, underwent suspension microlaryngoscopy and found to have bilateral fixation of the cricoarytenoid joints and a large granuloma in the interarytenoid area. He underwent cold steel resection of the granuloma and balloon dilatation between the arytenoids, with the hope of mobilising the joints. This failed and CO2 laser arytenoidectomy was performed on the left side. The stridor had resolved postoperatively, with normalisation of work of breathing and the patient was discharged home on the first postoperative day.


Assuntos
/terapia , Granuloma/cirurgia , Intubação Intratraqueal/efeitos adversos , Doenças da Laringe/cirurgia , Constrição Patológica/etiologia , Constrição Patológica/cirurgia , Dispneia/etiologia , Emergências , Granuloma/etiologia , Humanos , Doenças da Laringe/etiologia , Laringe/patologia , Masculino , Pessoa de Meia-Idade , Sons Respiratórios , Trabalho Respiratório
6.
Respiration ; 99(9): 755-763, 2020.
Artigo em Inglês | MEDLINE | ID: mdl-33147584

RESUMO

BACKGROUND: Effective auscultations are often hard to implement in isolation wards. To date, little is known about the characteristics of pulmonary auscultation in novel coronavirus (COVID-19) pneumonia. OBJECTIVES: The aim of this study was to explore the features and clinical significance of pulmonary auscultation in COVID-19 pneumonia using an electronic stethoscope in isolation wards. METHODS: This cross-sectional, observational study was conducted among patients with laboratory-confirmed COVID-19 at Wuhan Red-Cross Hospital during the period from January 27, 2020, to February 12, 2020. Standard auscultation with an electronic stethoscope was performed and electronic recordings of breath sounds were analyzed. RESULTS: Fifty-seven patients with average age of 60.6 years were enrolled. The most common symptoms were cough (73.7%) during auscultation. Most cases had bilateral lesions (96.4%) such as multiple ground-glass opacities (69.1%) and fibrous stripes (21.8%). High-quality auscultation recordings (98.8%) were obtained, and coarse breath sounds, wheezes, coarse crackles, fine crackles, and Velcro crackles were identified. Most cases had normal breath sounds in upper lungs, but the proportions of abnormal breath sounds increased in the basal fields where Velcro crackles were more commonly identified at the posterior chest. The presence of fine and coarse crackles detected 33/39 patients with ground-glass opacities (sensitivity 84.6% and specificity 12.5%) and 8/9 patients with consolidation (sensitivity 88.9% and specificity 15.2%), while the presence of Velcro crackles identified 16/39 patients with ground-glass opacities (sensitivity 41% and specificity 81.3%). CONCLUSIONS: The abnormal breath sounds in COVID-19 pneumonia had some consistent distributive characteristics and to some extent correlated with the radiologic features. Such evidence suggests that electronic auscultation is useful to aid diagnosis and timely management of the disease. Further studies are indicated to validate the accuracy and potential clinical benefit of auscultation in detecting pulmonary abnormalities in COVID-19 infection.


Assuntos
Auscultação , Pulmão/fisiopatologia , Sons Respiratórios/fisiopatologia , Adulto , Idoso , Idoso de 80 Anos ou mais , Antibacterianos/uso terapêutico , Antivirais/uso terapêutico , /diagnóstico por imagem , /terapia , China , Tosse/fisiopatologia , Estudos Transversais , Equipamentos e Provisões Elétricas , Feminino , Glucocorticoides/uso terapêutico , Humanos , Pulmão/diagnóstico por imagem , Masculino , Pessoa de Meia-Idade , Oxigenoterapia , Respiração Artificial , Sensibilidade e Especificidade , Índice de Gravidade de Doença , Smartphone , Espectrografia do Som , Escarro , Estetoscópios , Tomografia Computadorizada por Raios X , Adulto Jovem
7.
Intern Med ; 59(24): 3213-3216, 2020 Dec 15.
Artigo em Inglês | MEDLINE | ID: mdl-33132331

RESUMO

A 60-year-old woman was admitted to our hospital due to coronavirus disease 2019 (COVID-19) pneumonia with a chief complaint of persistent low-grade fever and dry cough for two weeks. Thoracic computed tomography demonstrated a crazy paving pattern in the bilateral lower lobes. In a COVID-19 ward, we used a novel wireless stethoscope with a telemedicine system and successfully recorded and shared the lung sounds in real-time between the red and green zones. The fine crackles at the posterior right lower lung fields changed from mid-to-late (day 1) to late inspiratory crackles (day 3), which disappeared at day 5 along with an improvement in both the clinical symptoms and thoracic CT findings.


Assuntos
Auscultação/instrumentação , Sons Respiratórios/diagnóstico , Estetoscópios , Telemedicina/métodos , /epidemiologia , Desenho de Equipamento , Feminino , Humanos , Pessoa de Meia-Idade , Tomografia Computadorizada por Raios X/métodos
9.
JAMA Netw Open ; 3(10): e2020671, 2020 10 01.
Artigo em Inglês | MEDLINE | ID: mdl-33048131

RESUMO

Importance: Use of e-cigarettes (ECs) among youths has increased in recent years. e-Cigarette aerosol contains chemical constituents, such as diacetyl or benzaldehyde, which are known to affect the respiratory system. Objective: To examine the association between EC use and self-reported wheezing in a cohort of US adolescents. Design, Setting, and Participants: This cohort study used data from waves 3 and 4 (October 19, 2015, to January 3, 2018) of the Population Assessment of Tobacco and Health (PATH) study, a longitudinal, nationally representative cohort survey. Adolescent respondents aged 12 to 17 years who did not have asthma were included. Exposures: e-Cigarette use during the previous year. Main Outcomes and Measures: Self-reported wheezing in the past 12 months (yes or no) and EC use (no use in past year or never use, use in past year, use in past 30 days, and use in past 7 days). Survey-weighted logistic regression models adjusted for demographic characteristics and other risk factors. Results: Among 7049 adolescents without asthma from waves 3 and 4 of the PATH study, 49.9% were female and 54.4% were non-Hispanic White. In unadjusted models, the odds of wheezing in the past 12 months were higher for youths who had used ECs in the past year compared with those who had not (odds ratio, 1.74; 95% CI, 1.22-2.48; P = .003). In the adjusted model, after controlling for the variables of race/ethnicity, household rules about the use of tobacco, contact with a smoker in the previous 7 days, and current use of combustible tobacco products, the association of EC use with wheezing was not significant (adjusted odds ratio for EC use in the past year, 1.37 [95% CI, 0.91-2.05]; in the past 30 days, 1.35 [95% CI, 0.63-2.88]; in the past 7 days, 0.74 [95% CI, 0.28-1.97]; P = .33). Conclusions and Relevance: In this cohort study, use of ECs alone was not associated with increased odds of experiencing wheezing episodes. Future studies incorporating the use of objective data appear to be needed to more accurately understand the potential respiratory harms associated with vaping among adolescents.


Assuntos
Comportamento do Adolescente/psicologia , Sistemas Eletrônicos de Liberação de Nicotina/estatística & dados numéricos , Sons Respiratórios/etiologia , Vaping/efeitos adversos , Adolescente , Estudos de Coortes , Feminino , Humanos , Masculino , Fatores de Risco , Autorrelato , Vaping/epidemiologia
10.
JAMA Netw Open ; 3(10): e2018534, 2020 10 01.
Artigo em Inglês | MEDLINE | ID: mdl-33006618

RESUMO

Importance: Children with food allergies may develop asthma or recurrent wheeze. Objective: To evaluate whether asthma or recurrent wheeze among children were changed by avoiding supplementing breastfeeding (BF) with cow's milk formula (CMF) in the first 3 days of life. Design, Setting, and Participants: This randomized, unmasked, clinical trial was conducted at 1 university hospital in Japan beginning October 2013 with follow-up examinations occurring until January 2020. A total of 312 newborns at risk for atopy were randomized and assigned to either BF with or without amino acid-based elemental formula (EF) or BF with CMF, with follow-up examinations for participants showing signs of atopy conducted at 24 months. Follow-up examinations ran through January 2020. Interventions: Immediately after birth, newborns were randomly assigned (1:1 ratio) to either breastfeeding with or without amino acid-based elemental formula for at least the first 3 days of life (no CMF group) or breastfeeding supplemented with CMF (≥5 mL/d) from the first day of life to 5 months of age (CMF group). Main Outcomes and Measures: Asthma or recurrent wheeze diagnosed by the pediatric allergy specialists of this trial; subgroups were stratified by serum levels of 25-hydroxyvitamin D and IgE. Results: Of 312 infants (156 [50.0%] randomized to the no CMF group), 302 (96.8%) were followed up at their second birthday: 77 of 151 (51.0%) in the no CMF group and 81 of 151 (53.6%) in the CMF group underwent extended follow-up because of having atopic conditions. Asthma or recurrent wheeze developed in 15 (9.9%) of the children in the no CMF group, significantly less than the children in the CMF group (27 [17.9%]; risk difference, -0.079; 95% CI, -0.157 to -0.002). In participants with vitamin D levels above the median at 5 months of age, asthma or recurrent wheeze developled in 5 (6.4%) children in the no CMF group, significantly less than in the children in the CMF group (17 [24.6%]; risk difference, -0.182; 95% CI, -0.298 to -0.067; P for interaction = .04). In the highest quartile group of total IgE at age 24 months, asthma or recurrent wheeze developed in 2 children (5.3%) in the no CMF group, significantly less than the children in the CMF group (14 [43.8%]; risk difference, -0.385; 95% CI, -0.571 to -0.199; P for interaction = .004). Conclusions and Relevance: The findings of this study suggest that avoiding CMF supplementation in the first 3 days of life has the potential to reduce the risk of asthma or recurrent wheeze in young children, especially among those with high vitamin D or high IgE levels. Trial Registration: umin.ac.jp/ctr Identifier: UMIN000011577.


Assuntos
Asma/etiologia , Asma/prevenção & controle , Asma/fisiopatologia , Fórmulas Infantis/efeitos adversos , Hipersensibilidade a Leite/fisiopatologia , Leite/efeitos adversos , Sons Respiratórios/fisiopatologia , Animais , Bovinos , Feminino , Seguimentos , Humanos , Lactente , Recém-Nascido , Japão , Masculino
11.
Phys Eng Sci Med ; 43(4): 1339-1347, 2020 Dec.
Artigo em Inglês | MEDLINE | ID: mdl-33057901

RESUMO

Since the outbreak of the pandemic Coronavirus Disease 2019, the world is in search of novel non-invasive methods for safer and early detection of lung diseases. The pulmonary pathological symptoms reflected through the lung sound opens a possibility of detection through auscultation and of employing spectral, fractal, nonlinear time series and principal component analyses. Thirty-five signals of vesicular and expiratory wheezing breath sound, subjected to spectral analyses shows a clear distinction in terms of time duration, intensity, and the number of frequency components. An investigation of the dynamics of air molecules during respiration using phase portrait, Lyapunov exponent, sample entropy, fractal dimension, and Hurst exponent helps in understanding the degree of complexity arising due to the presence of mucus secretions and constrictions in the respiratory airways. The feature extraction of the power spectral density data and the application of principal component analysis helps in distinguishing vesicular and expiratory wheezing and thereby, giving a ray of hope in accomplishing an early detection of pulmonary diseases through sound signal analysis.


Assuntos
Fractais , Sons Respiratórios/fisiopatologia , Humanos , Análise de Componente Principal , Respiração , Processamento de Sinais Assistido por Computador , Fatores de Tempo , Análise de Ondaletas
12.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 2740-2743, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018573

RESUMO

Lung sound (LS) signals are often contaminated by impulsive artifacts that complicate the estimation of lung sound intensity (LSI) using conventional amplitude estimators. Fixed sample entropy (fSampEn) has proven to be robust to cardiac artifacts in myographic respiratory signals. Similarly, fSampEn is expected to be robust to artifacts in LS signals, thus providing accurate LSI estimates. However, the choice of fSampEn parameters depends on the application and fSampEn has not previously been applied to LS signals. This study aimed to perform an evaluation of the performance of the most relevant fSampEn parameters on LS signals, and to propose optimal fSampEn parameters for LSI estimation. Different combinations of fSampEn parameters were analyzed in LS signals recorded in a heterogeneous population of healthy subjects and chronic obstructive pulmonary disease patients during loaded breathing. The performance of fSampEn was assessed by means of its cross-covariance with flow signals, and optimal fSampEn parameters for LSI estimation were proposed.


Assuntos
Sons Respiratórios , Processamento de Sinais Assistido por Computador , Artefatos , Entropia , Coração , Humanos
13.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 2744-2747, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018574

RESUMO

Respiratory sounds yield pertinent information about respiratory function in both health and disease. Normal lung sound intensity is a characteristic that correlates well with airflow and it can therefore be used to quantify the airflow changes and limitations imposed by respiratory diseases. The dual aims of this study are firstly to establish whether previously reported asymmetries in normal lung sound intensity are affected by varying the inspiratory threshold load or the airflow of respiration, and secondly to investigate whether fixed sample entropy can be used as a valid measure of lung sound intensity. Respiratory sounds were acquired from twelve healthy individuals using four contact microphones on the posterior skin surface during an inspiratory threshold loading protocol and a varying airflow protocol. The spatial distribution of the normal lung sounds intensity was examined. During the protocols explored here the normal lung sound intensity in the left and right lungs in healthy populations was found to be similar, with asymmetries of less than 3 dB. This agrees with values reported in other studies. The fixed sample entropy of the respiratory sound signal was also calculated and compared with the gold standard root mean square representation of lung sound intensity showing good agreement.


Assuntos
Pulmão , Sons Respiratórios , Nível de Saúde , Humanos , Respiração , Som
15.
Rev Assoc Med Bras (1992) ; 66(9): 1270-1276, 2020 Sep.
Artigo em Inglês | MEDLINE | ID: mdl-33027457

RESUMO

OBJECTIVES: To evaluate the treatment of wheezing and exacerbation of asthma in a pediatric emergency unit (ED), comparing it to that recommended by the guidelines for this purpose. METHODS: Descriptive cross-sectional study through medical records survey of children and adolescents (0-15 years of age) who received medication for wheezing or asthma exacerbation from January to April 2015 in the ED. The selected treatment was compared to that recommended by the guidelines, being analyzed the variables related to the medication (number and dose of short-acting ß2 agonist, associated or not with anticholinergic, oral or parenteral corticosteroid) and the length of stay in ED (≤1 h, ≥8 h and hospital admission). RESULTS: One-thousand eleven patients were selected with 56.7% between 3 and 15 years and 56% male. Although the selected drugs were in accordance with what was recommended, errors were observed in relation to dose, drug of choice, and method and time of use with the most frequent finding being incorrect dose (short-acting ß2 agonist: 66% and ipratropium bromide: 95.2%). CONCLUSION: The level of use of the measures recommended by the guidelines was low but compatible with other studies, leading to an increased risk of treatment failure and higher costs. Despite wide dissemination, the established concepts have not been sufficiently incorporated into clinical practice, suggesting the need for more effective educational actions for this process to occur.


Assuntos
Asma , Sons Respiratórios , Adolescente , Criança , Pré-Escolar , Estudos Transversais , Serviço Hospitalar de Emergência , Feminino , Humanos , Lactente , Recém-Nascido , Ipratrópio , Masculino
16.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 164-167, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33017955

RESUMO

This paper presents a robust deep learning framework developed to detect respiratory diseases from recordings of respiratory sounds. The complete detection process firstly involves front end feature extraction where recordings are transformed into spectrograms that convey both spectral and temporal information. Then a back-end deep learning model classifies the features into classes of respiratory disease or anomaly. Experiments, conducted over the ICBHI benchmark dataset of respiratory sounds, evaluate the ability of the framework to classify sounds. Two main contributions are made in this paper. Firstly, we provide an extensive analysis of how factors such as respiratory cycle length, time resolution, and network architecture, affect final prediction accuracy. Secondly, a novel deep learning based framework is proposed for detection of respiratory diseases and shown to perform extremely well compared to state of the art methods.


Assuntos
Aprendizado Profundo , Redes Neurais de Computação , Humanos , Sons Respiratórios
17.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 754-759, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018096

RESUMO

This paper focuses on the use of an attention-based encoder-decoder model for the task of breathing sound segmentation and detection. This study aims to accurately segment the inspiration and expiration of patients with pulmonary diseases using the proposed model. Spectrograms of the lung sound signals and labels for every time segment were used to train the model. The model would first encode the spectrogram and then detect inspiratory or expiratory sounds using the encoded image on an attention-based decoder. Physicians would be able to make a more precise diagnosis based on the more interpretable outputs with the assistance of the attention mechanism.The respiratory sounds used for training and testing were recorded from 22 participants using digital stethoscopes or anti-noising microphone sets. Experimental results showed a high 92.006% accuracy when applied 0.5 second time segments and ResNet101 as encoder. Consistent performance of the proposed method can be observed from ten-fold cross-validation experiments.


Assuntos
Respiração , Sons Respiratórios , Atenção , Expiração , Humanos , Aprendizado de Máquina
18.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 760-763, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018097

RESUMO

We propose a robust and efficient lung sound classification system using a snapshot ensemble of convolutional neural networks (CNNs). A robust CNN architecture is used to extract high-level features from log mel spectrograms. The CNN architecture is trained on a cosine cycle learning rate schedule. Capturing the best model of each training cycle allows to obtain multiple models settled on various local optima from cycle to cycle at the cost of training a single mode. Therefore, the snapshot ensemble boosts performance of the proposed system while keeping the drawback of expensive training of ensembles moderate. To deal with the class-imbalance of the dataset, temporal stretching and vocal tract length perturbation (VTLP) for data augmentation and the focal loss objective are used. Empirically, our system outperforms state-of-the-art systems for the prediction task of four classes (normal, crackles, wheezes, and both crackles and wheezes) and two classes (normal and abnormal (i.e. crackles, wheezes, and both crackles and wheezes)) and achieves 78.4% and 83.7% ICBHI specific micro-averaged accuracy, respectively. The average accuracy is repeated on ten random splittings of 80% training and 20% testing data using the ICBHI 2017 dataset of respiratory cycles.


Assuntos
Redes Neurais de Computação , Sons Respiratórios , Humanos , Aprendizagem , Aprendizado de Máquina
19.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 764-767, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018098

RESUMO

Tracheal sounds represent information about the upper airway and respiratory airflow, however, they can be contaminated by the snoring sounds. The sound of snoring has spectral content in a wide range that overlaps with that of breathing sounds during sleep. For assessing respiratory airflow using tracheal breathing sound, it is essential to remove the effect of snoring. In this paper, an automatic and unsupervised wavelet-based snoring removal algorithm is presented. Simultaneously with full-night polysomnography, the tracheal sound signals of 9 subjects with different levels of airway obstruction were recorded by a microphone placed over the trachea during sleep. The segments of tracheal sounds that were contaminated by snoring were manually identified through listening to the recordings. The selected segments were automatically categorized based on including discrete or continuous snoring pattern. Segments with discrete snoring were analyzed by an iterative wave-based filtering optimized to separate large spectral components related to snoring from smaller ones corresponded to breathing. Those with continuous snoring were first segmented into shorter segments. Then, each short segments were similarly analyzed along with a segment of normal breathing extracted from the recordings during wakefulness. The algorithm was evaluated by visual inspection of the denoised sound energy and comparison of the spectral densities before and after removing snores, where the overall rate of detectability of snoring was less than 2%.Clinical Relevance- The algorithm provides a way of separating snoring pattern from the tracheal breathing sounds. Therefore, each of them can be analyzed separately to assess respiratory airflow and the pathophysiology of the upper airway during sleep.


Assuntos
Sons Respiratórios , Ronco , Algoritmos , Auscultação , Humanos , Polissonografia , Ronco/diagnóstico
20.
Annu Int Conf IEEE Eng Med Biol Soc ; 2020: 768-771, 2020 07.
Artigo em Inglês | MEDLINE | ID: mdl-33018099

RESUMO

Respiratory condition has received a great amount of attention nowadays since respiratory diseases recently become the globally leading causes of death. Traditionally, stethoscope is applied in early diagnosis but it requires clinician with extensive training experience to provide accurate diagnosis. Accordingly, a subjective and fast diagnosing solution of respiratory diseases is highly demanded. Adventitious respiratory sounds (ARSs), such as crackle, are mainly concerned during diagnosis since they are indication of various respiratory diseases. Therefore, the characteristics of crackle are informative and valuable regarding to develop a computerised approach for pathology-based diagnosis. In this work, we propose a framework combining random forest classifier and Empirical Mode Decomposition (EMD) method focusing on a multi-classification task of identifying subjects in 6 respiratory conditions (healthy, bronchiectasis, bronchiolitis, COPD, pneumonia and URTI). Specifically, 14 combinations of respiratory sound segments were compared and we found segmentation plays an important role in classifying different respiratory conditions. The classifier with best performance (accuracy = 0.88, precision = 0.91, recall = 0.87, specificity = 0.91, F1-score = 0.81) was trained with features extracted from the combination of early inspiratory phase and entire inspiratory phase. To our best knowledge, we are the first to address the challenging multi-classification problem.


Assuntos
Pneumonia , Transtornos Respiratórios , Estetoscópios , Humanos , Respiração , Sons Respiratórios/diagnóstico
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA