A New Modality Using Breath Sound Analysis to Evaluate the Control Level of Asthma

A Novel Method for Automatic Identification of Breathing State

Sputum deposition blocks the airways of patients and leads to blood oxygen desaturation. Medical staff must periodically check the breathing state of intubated patients. This process increases staff workload. In this paper, we describe a system designed to acquire respiratory sounds from intubated subjects, extract the audio features, and classify these sounds to detect the presence of sputum. Our method uses 13 features extracted from the time-frequency spectrum of the respiratory sounds. To test our system, 220 respiratory sound samples were collected. Half of the samples were collected from patients with sputum present, and the remainder were collected from patients with no sputum present. Testing was performed based on ten-fold cross-validation. In the ten-fold cross-validation experiment, the logistic classifier identified breath sounds with sputum present with a sensitivity of 93.36% and a specificity of 93.36%. The feature extraction and classification methods are useful and reliable for sputum detection. This approach differs from waveform research and can provide a better visualization of sputum conditions. The proposed system can be used in the ICU to inform medical staff when sputum is present in a patient's trachea.

Detection of sputum by interpreting the time-frequency distribution of respiratory sound signal using image processing techniques

Motivation

Sputum in the trachea is hard to expectorate and detect directly for the patients who are unconscious, especially those in Intensive Care Unit. Medical staff should always check the condition of sputum in the trachea. This is time-consuming and the necessary skills are difficult to acquire. Currently, there are few automatic approaches to serve as alternatives to this manual approach.

Results

We develop an automatic approach to diagnose the condition of the sputum. Our approach utilizes a system involving a medical device and quantitative analytic methods. In this approach, the time-frequency distribution of respiratory sound signals, determined from the spectrum, is treated as an image. The sputum detection is performed by interpreting the patterns in the image through the procedure of preprocessing and feature extraction. In this study, 272 respiratory sound samples (145 sputum sound and 127 non-sputum sound samples) are collected from 12 patients. We apply the method of leave-one out cross-validation to the 12 patients to assess the performance of our approach. That is, out of the 12 patients, 11 are randomly selected and their sound samples are used to predict the sound samples in the remaining one patient. The results show that our automatic approach can classify the sputum condition at an accuracy rate of 83.5%.

Availability and implementation

The matlab codes and examples of datasets explored in this work are available at Bioinformatics online.

Contact

yesoyou@gmail.com or douglaszhang@umac.mo.

Supplementary information

Supplementary data are available at Bioinformatics online.

Changes in the breath sound spectrum during methacholine inhalation in children with asthma

BACKGROUND AND OBJECTIVE

An effort-independent breath sound analysis is expected to be a safe and simple method for clinical assessment of changes in airway function. The effects of bronchoconstriction and bronchodilation on novel breath sound parameters in asthmatic children were investigated.

METHODS

The study population included 49 children with atopic asthma (male = 33; mean age: 10.2 years). We evaluated breath sound parameters of the highest frequency of the power spectrum (HFp), frequency limiting 50% and 99% of the power spectrum (F₅₀ and F₉₉ ) and roll-off from 600 Hz to the HFp (Slope). We also assessed new parameters obtained using the ratios of sound spectrum parameters (spectrum curve indices), such as the ratio of the third and fourth power area to the total power area (P₃ /P_T and P₄ /P_T ), the ratio of the third and fourth areas to the total area under the curve (A₃ /A_T and B₄ /A_T ) and the ratio of power and frequency at 75% of HFp and 50% of HFp (RPF₇₅ and RPF₅₀ ). This was measured before and after methacholine inhalation challenge and after β₂ agonist inhalation.

RESULTS

The parameters, F₅₀ and F₉₉ , showed no changes after methacholine inhalation. Conversely, the A₃ /A_T (12.5-10.0%, P < 0.001), B₄ /A_T (7.6-5.5%, P < 0.001), RPF₇₅ (6.7-4.0 dBm/Hz, P < 0.001) and RPF₅₀ (5.8-4.3 dBm/Hz, P < 0.001) were significantly decreased. These values returned to the original level after β₂ agonist inhalation.

CONCLUSION

Spectrum curve indices indicate bronchoconstriction and bronchodilation. These parameters may play a role in the assessment of airway narrowing in asthmatic children.

Lung sound analysis can be an index of the control of bronchial asthma

BACKGROUND

We assessed whether lung sound analysis (LSA) is a valid measure of airway obstruction and inflammation in patients with bronchial asthma during treatment with inhaled corticosteroids (ICSs).

METHODS

63 good adherence patients with bronchial asthma and 18 poor adherence patients were examined by LSA, spirometry, fractional exhaled nitric oxide (FeNO), and induced sputum. The expiration-to-inspiration lung sound power ratio at low frequencies between 100 and 200 Hz (E/I LF) obtained by LSA was compared between healthy volunteers and bronchial asthma patients. Next, post-ICS treatment changes were compared in bronchial asthma patients between the good adherence patients and the poor adherence patients.

RESULTS

E/I LF was significantly higher in bronchial asthma patients (0.62 ± 0.21) than in healthy volunteers (0.44 ± 0.12, p < 0.001). The good adherence patients demonstrated a significant reduction in E/I LF from pre-treatment to post-treatment (0.55 ± 0.21 to 0.46 ± 0.16, p = 0.002), whereas the poor adherence patients did not show a significant change. The decrease of E/I LF correlated with the improvement of FEV₁/FVC ratio during the ICS treatment (r = -0.26, p = 0.04). The subjects with higher pre-treatment E/I LF values had significantly lower FEV₁/FVC and V_50,%pred (p < 0.001), and significantly higher FeNO and sputum eosinophil percentages (p = 0.008 and p < 0.001, respectively).

CONCLUSIONS

The E/I LF measurement obtained by LSA is useful as an indicator of changes in airway obstruction and inflammation and can be used for monitoring the therapeutic course of bronchial asthma patients.

Peripheral bronchial obstruction evaluation in patients with asthma by lung sound analysis and impulse oscillometry

BACKGROUND

Computer-aided lung sound analysis (LSA) has been reported to be useful for evaluating airway inflammation and obstruction in asthma patients. We investigated the relation between LSA and impulse oscillometry with the evaluation of peripheral airway obstruction.

METHODS

A total of 49 inhaled corticosteroid-naive bronchial asthma patients underwent LSA, spirometry, impulse oscillometry, and airway hyperresponsiveness testing. The data were analyzed to assess correlations between the expiration: inspiration lung sound power ratio (dB) at low frequencies between 100 and 195 Hz (E/I LF) and various parameters.

RESULTS

E/I LF and X5 were identified as independent factors that affect V˙_{50,%predicted}. E/I LF showed a positive correlation with R5 (r = 0.34, p = 0.017), R20 (r = 0.34, p = 0.018), reactance area (AX, r = 0.40, p = 0.005), and resonant frequency of reactance (Fres, r = 0.32, p = 0.024). A negative correlation was found between E/I LF and X5 (r = -0.47, p = 0.0006). E/I LF showed a negative correlation with FEV₁/FVC(%), FEV_1,%predicted, V˙_{50,%predicted}, and V˙_{25,%predicted} (r = -0.41, p = 0.003; r = -0.44, p = 0.002; r = -0.49, p = 0.0004; and r = -0.30, p = 0.024, respectively). E/I LF was negatively correlated with log PC₂₀ (r = -0.30, p = 0.024). Log PC₂₀, X5, and past smoking were identified as independent factors that affected E/I LF level.

CONCLUSIONS

E/I LF as with X5 can be an indicator of central and peripheral airway obstruction in bronchial asthma patients.

Changes in lung sounds during asthma progression in a guinea pig model

BACKGROUND

Lung sound analysis is useful for objectively evaluating airways even in children with asymptomatic asthma. However, the relationship between lung sounds and morphological changes in the airways has not been elucidated. We examined the relationship between lung sounds and chronic morphological changes in the airways during the progression of asthma from onset in guinea pigs.

METHODS

Eleven male guinea pigs were examined; of these, seven were used as asthma models and four as controls. The asthma models were sensitized and repeatedly challenged by inhaling albumin chicken egg. We measured lung sounds and lung function twice a week for 21 weeks. After the final antigen challenge, the lungs were excised for histological examination. We measured the ratio of airway wall thickness to the total airway area and the ratio of the internal area to the total airway area in the trachea, third bronchi, and terminal bronchioles.

RESULTS

Among the lungs sounds, the difference between the two groups was greatest with respect to inspiratory sound intensity. The ratio of airway wall thickness to the total airway area of the terminal bronchioles was greater in the asthma models than in the controls, and it correlated best with the changes in inspiratory sound intensity in the 501-1000-Hz range (r = 0.76, p < 0.003).

CONCLUSIONS

Lung sound intensity in the middle frequency range from 501 to 1000 Hz correlated with peripheral airway wall thickness. Inspiratory sound intensity appeared to be an indicator of morphological changes in small airways in asthma.

Evaluation of airflow limitation using a new modality of lung sound analysis in asthmatic children

BACKGROUND

Reliable assessment of not only symptoms but also lung function is essential in asthma management. We developed a new technology for analyzing lung sounds and assessed its clinical usefulness in asthmatic children.

METHODS

Forty-four children underwent lung sound recording with simultaneous airflow measurement using a sensor on the upper right anterior chest. We calculated a sound parameter index from the amplitude of inspiratory lung sounds at 700 Hz (ic700). ic700 were compared depending on flow and body size. In addition, 184 asthmatic children and 16 non-asthmatic children underwent lung sound analysis and lung function test in an asymptomatic state. In the asthma group, 135 children received treatment continually. The untreated asthma group included 28 children who had never received treatment continually and 21 children who had not been treated for at least 1 year. The asthmatic children were divided into four classes according to asthma severity. ic700 were compared depending on spirometric parameters and asthma severity classification.

RESULTS

The influences of flow and body size were negligible for ic700. ic700 correlated with FEV1%, MMF and FEF50 (r = -0.436, -0.339 and -0.302, respectively). There was a significant difference of ic700 between asthmatic and non-asthmatic children (p < 0.001), and ic700 correlated with the classification of asthma severity (p < 0.001). The ic700 scores of the severe group were higher than those of the intermittent group and non-asthmatic children.

CONCLUSIONS

It was possible to evaluate airway dysfunction of asthma using ic700, which was calculated non-invasively by analyzing lung sounds alone, without measuring body size and airflow.

Getting control of uncontrolled asthma

Despite various treatment modalities, a large proportion of patients have asthma that remains uncontrolled. These patients remain at an increased risk of developing severe exacerbations, have a poor quality of life, and pose a high economic healthcare burden, with an estimated mean annual cost more than double that of patients with good symptom control. It is therefore important to accurately diagnose asthma and continually assess asthma control. Several validated tools are available to do this, including questionnaires, biomarker analysis, and bronchoscopy. Current guidelines advise physicians to establish a self-management program for the patient to assess and monitor asthma control. A further recommendation is the establishment of an educational action plan to increase treatment adherence and to improve asthma control. National and international guidelines provide long-term management strategies for these patients and recommend a stepwise approach for achieving and maintaining asthma control. Despite availability of a wide range of controller and reliever therapies, uncontrolled asthma remains a challenge and reflects the need for new therapeutic options. This review discusses current global guidelines for the assessment and management of asthma control and summarizes the broad spectrum of novel therapeutic agents currently under development for the treatment of asthma, including anticholinergics, chemoattractant receptor-homologous molecules expressed on T-helper 2 lymphocyte antagonists, and anti-interleukin (IL)-5, anti-IL-13, and anti-IL-4 agents.