Pulmonary Sounds Research Articles

Intrapulmonary electronic auscultation for asthma and chronic obstructive pulmonary disease

The aim of the study was to develop and perform clinical testing of the intrapulmonary electronic auscultation method for audio and video recording at various levels of the tracheobronchial tree for the diagnosis of asthma and chronic obstructive pulmonary disease (COPD).Methods. We examined 31 patients with moderate (n = 17) and severe (n = 14) COPD with severe symptoms outside of exacerbation and 35 patients with moderate (n = 19) and severe (n = 16) partially controlled asthma. Traditional bronchoscopy was performed, including intrabronchial recording of acoustic noise with a microphone (introduced into the instrumental channel of the bronchoscope) at various levels of the tracheobronchial tree. Video recording in various modes revealed the causes of wheezing. At the same time, pulmonary sounds were recorded in the interscapular region of the chest at the projection points of the bronchoscope in the tracheobronchial tree using a 3M™ Littmann® 3200 electronic stethoscope (USA).Results. The greatest intergroup differences between patients with moderate and severe COPD were demonstrated by intrapulmonary sound parameters (frequency and duration of wheezing, р < 0.0001) and frequency response (amplitude-frequency characteristics) of wheezing in the lumen of the 4th order bronchi (р < 0.0001), significantly exceeded the corresponding sound phenomena during auscultation from the surface of the chest (р < 0.01). The most significant intergroup differences in the groups of BA patients with moderate and severe disease were observed in the frequency response of wheezing during intrapulmonary auscultation in the lumen of the 3rd order (р < 0.0001) and 4th order (р < 0.0001) bronchi; smaller differences were observed in the frequency response during auscultation from the chest surface (р < 0.001).Conclusion. Intrapulmonary auscultation is a modern auscultatory method which can improve the quality and efficiency of diagnosis of asthma and COPD in pulmonology.

DeepRespNet: A deep neural network for classification of respiratory sounds

Respiratory sounds convey significant information about the pulmonary status. This study proposes a deep learning-based framework to create an automatic, non-invasive, diagnostic method of categorizing pulmonary sounds. A labelled database of pulmonary sounds has been collected using an electronic stethoscope and audio recording instrument. Two deep learning architectures, 1D DeepRespNet and 2D DeepRespNet are proposed in this work that were trained and evaluated with normalised 1-D time series and 2-D spectrograms of acoustic signals of six types of lung sounds, respectively. The models were highly optimized to yield superior performance on the considered dataset. Experimental results demonstrate that the 2D DeepRespNet model trained with spectrogram-based representations yields higher accuracy of 95.2% on the test data as compared to the 1D DeepRespNet trained on the time-series data. The proposed model may be deployed on a single board computer or integrated into a smartphone to develop a standalone diagnostic tool to accurately and objectively classify abnormal lung sounds with low time complexity.

Clinical decision support system using a machine learning model to assist simultaneous cardiopulmonary auscultation: Open-label randomized controlled trial.

The utility of a clinical decision support system using a machine learning (ML) model for simultaneous cardiac and pulmonary auscultation is unknown. This study aimed to develop and evaluate an ML system's utility for cardiopulmonary auscultation. First, we developed an ML system for cardiopulmonary auscultation, using cardiopulmonary sound files from our previous study. The technique involved pre-processing, feature extraction, and classification through several neural network layers. After integration, the output class was categorized as "normal," "abnormal," or "undetermined." Second, we evaluated the ML system with 24 junior residents in an open-label randomized controlled trial at a university hospital. Participants were randomly assigned to the ML system group (intervention) or conventional auscultation group (control). During training, participants listened to four cardiac and four pulmonary sounds, all of which were correctly classified. Then, participants classified a series of 16 simultaneous cardiopulmonary sounds. The control group auscultated the sounds using noise-cancelling headphones, while the intervention group did so by watching recommendations from the ML system. The total scores for correctly identified normal or abnormal cardiopulmonary sounds in the intervention group were significantly higher than those in the control group (366/384 [95.3%] vs. 343/384 [89.3%], P = 0.003). The cardiac test score in the intervention group was better (111/192 [57.8%] vs. 90/192 [46.9%], P = 0.04); there was no significant difference in pulmonary auscultation. The ML-based system improved the accuracy of cardiopulmonary auscultation for junior residents. This result suggests that the system can assist early-career physicians in accurate screening.

Cerebral process involved in the memorization of pulmonary sounds: Testing medical students

Cerebral process involved in the memorization of pulmonary sounds: Testing medical students

Exploring classical machine learning for identification of pathological lung auscultations

The use of machine learning in biomedical research has surged in recent years thanks to advances in devices and artificial intelligence. Our aim is to expand this body of knowledge by applying machine learning to pulmonary auscultation signals. Despite improvements in digital stethoscopes and attempts to find synergy between them and artificial intelligence, solutions for their use in clinical settings remain scarce. Physicians continue to infer initial diagnoses with less sophisticated means, resulting in low accuracy, leading to suboptimal patient care. To arrive at a correct preliminary diagnosis, the auscultation diagnostics need to be of high accuracy. Due to the large number of auscultations performed, data availability opens up opportunities for more effective sound analysis. In this study, digital 6-channel auscultations of 45 patients were used in various machine learning scenarios, with the aim of distinguishing between normal and abnormal pulmonary sounds. Audio features (such as fundamental frequencies F0-4, loudness, HNR, DFA, as well as descriptive statistics of log energy, RMS and MFCC) were extracted using the Python library Surfboard. Windowing, feature aggregation, and concatenation strategies were used to prepare data for machine learning algorithms in unsupervised (fair-cut forest, outlier forest) and supervised (random forest, regularized logistic regression) settings. The evaluation was carried out using 9-fold stratified cross-validation repeated 30 times. Decision fusion by averaging the outputs for a subject was also tested and found to be helpful. Supervised models showed a consistent advantage over unsupervised ones, with random forest achieving a mean AUC ROC of 0.691 (accuracy 71.11%, Kappa 0.416, F1-score 0.675) in side-based detection and a mean AUC ROC of 0.721 (accuracy 68.89%, Kappa 0.371, F1-score 0.650) in patient-based detection.

Classification of pulmonary sounds through deep learning for the diagnosis of interstitial lung diseases secondary to connective tissue diseases

Early diagnosis of interstitial lung diseases secondary to connective tissue diseases is critical for the treatment and survival of patients. The symptoms, like dry cough and dyspnea, appear late in the clinical history and are not specific, moreover, the current approach to confirm the diagnosis of interstitial lung disease is based on high resolution computer tomography. However, computer tomography involves x-ray exposure for patients and high costs for the Health System, therefore preventing its use for a massive screening campaign in elder people.In this work we investigate the use of deep learning techniques for the classification of pulmonary sounds acquired from patients affected by connective tissue diseases. The novelty of the work consists of a suitably developed pre-processing pipeline for de-noising and data augmentation. The proposed approach is combined with a clinical study where the ground truth is represented by high resolution computer tomography. Various convolutional neural networks have provided an overall accuracy as high as 91% in the classification of lung sounds and have led to an overwhelming diagnostic accuracy in the range 91%−93%. Modern high performance hardware for edge computing can easily support our algorithms. This solution paves the way for a vast screening campaign of interstitial lung diseases in elder people on the basis of a non-invasive and cheap thoracic auscultation.

Computerized analysis of pulmonary sounds using uniform manifold projection

Respiratory sounds heard through the stethoscope lend useful information for diagnostic purposes. However, the accuracy and efficiency of clinical diagnosis are constrained by subjective interpretations and the level of auscultation expertise of the physician. In this work, Fourier-based signal processing approaches and uniform manifold projection (UMAP) for data visualization, are combined for tackling the computerized analysis of respiratory sounds. The results show that differences and similarities between the signals can be identified trough patterns emerging from the information embedded in stationary and dynamical spectral features from the pulmonary acoustic recordings. The outcomes of these different perspectives evince discriminative ability between the recording devices, the chronic and non-chronic condition of patients, and adventitious sounds. In a contrasting view to the analysis based on machine learning or deep learning, whose implementation is profusely reported in scientific literature, this paper shows that the proposed approach renders an effective analysis of pulmonary sounds, with clinical correlations. Furthermore, the information visualization achieved by means of UMAP can be an attractive tool for assisting physicians during patients auscultation.

Clozapine Toxicity in the Setting of COVID-19: A case of differential diagnosis

IntroductionTogether with agranulocytosis, fever and immflamatory manifestations are clozapine side effects to be monitorized during initial treatment. In the context of COVID-19 pandemic, implied mechanisms, and symptomatology should be carefully controlled.ObjectivesTo analyze the clinical analytic and inflammatory chracterisctics the resembles and differenciates clozapine immune response and SARS-CoV-2 infection. To describe a case of clozapine induced fever and pneumonitis during COVID-19 pandemic.MethodsA case of clozapine-induced pneumonitis during COVID-19 pandemic is described.- A mini-review of clozapine inflamamtory effects, induced-pneumonitis and SARS-CoV-2 was performed.ResultsA 33 year old afrolatin male started treatment with clozapine up to 250 mg daily. He developed fever and respiratory symptoms in the 11th day of treatment. The exploration revealed pulmonary sounds decreased and 91% basal saturation, making the probable causes viral infection (local incidence of SARS-CoV-2 >800/100000hab), nosocomial bacterial infection or pulmonary thromboembolism. The patient was isolated due to probable COVID-19. Blood tests showed leucocytosis (13400/mcL), Lymphocytopenia (11.8%), high PCR (14.4mg/dL), Ferritine (506.9ng/mL), Fibrinigen (663.83 mg/dL), D-Dimer (1.61mg/dL), and Interleukin-9 /25.8pg/mL). The angioTC revealed a pleural efusion and ground glass infiltrates (figure1). Only after 2 weeks eosinophilia was discovered (88/mcL) After 2 negative consecutieve PCRs for SARS-CoV-2, no imrovement with ampirical antibiotics and all infectious pannels negative, we started decreasing clozapine with improvement of the symptoms and resolution after suspending clozapine completely.ConclusionsClozapine may induce a generalize inflammatory response mediated by interleukin-6. Patients treated with clozapine may exhibit fever and rarely, insterstitial lung inflammation. The expression of induced pneumonitis resembles viral infections, particularly SARS-CoV-2DisclosureNo significant relationships.

Classification of Pulmonary Crackle and Normal Lung Sound Using Spectrogram and Support Vector Machine

Crackles is one of the types of adventitious lung sound heard in patients with interstitial pulmonary fibrosis or cystic fibrosis. Pulmonary crackles of discontinuous short duration appear on inspiration, expiration, or both. To differentiate these pulmonary crackles, the medical staff usually uses a manual method, called auscultation. Various methods were developed to recognize pulmonary crackles and distinguish them from normal pulmonary sounds to be applied in digital signal processing technology. This paper demonstrates a feature extraction method to classify pulmonary crackle and normal lung sounds using Support Vector Machine (SVM) method using several kernels by performing spectrograms of the pulmonary sound to generate the frequency profile. Spectrograms with various resolutions and 3-fold cross-validation were used to divide the training data and the test data in the testing process. The resulting accuracy ranges from 81.4% - 100%. More accuracy values of 100% are generated by a feature extraction in several SVM kernels using 256 points FFT with three variations of windowing parameters compared to 512 points, where the best accuracy of 100% was produced by STFT-SVM method. This method has a potential to be used in the classification of other biomedical signals. The advantages of that are that the number of features produced is the same as the N-point FFT used for any signal length, the flexibility in the STFT parameters changes, such as the type of window and the window's length. In this study, only the Keiser window was tested with specific parameters. Exploration with different window types with various parameters is fascinating to do in further research.

VECTOR: An algorithm for the detection of COVID-19 pneumonia from velcro-like lung sounds

The coronavirus disease 2019 (COVID-19) has severely stressed the sanitary systems of all countries in the world. One of the main issues that physicians are called to tackle is represented by the monitoring of pauci-symptomatic COVID-19 patients at home and, generally speaking, everyone the access to the hospital might or should be severely reduced. Indeed, the early detection of interstitial pneumonia is particularly relevant for the survival of these patients. Recent studies on rheumatoid arthritis and interstitial lung diseases have shown that pathological pulmonary sounds can be automatically detected by suitably developed algorithms. The scope of this preliminary work consists of proving that the pathological lung sounds evidenced in patients affected by COVID-19 pneumonia can be automatically detected as well by the same class of algorithms. In particular the software VECTOR, suitably devised for interstitial lung diseases, has been employed to process the lung sounds of 28 patient recorded in the emergency room at the university hospital of Modena (Italy) during December 2020. The performance of VECTOR has been compared with diagnostic techniques based on imaging, namely lung ultrasound, chest X-ray and high resolution computed tomography, which have been assumed as ground truth. The results have evidenced a surprising overall diagnostic accuracy of 75% even if the staff of the emergency room has not been suitably trained for lung auscultation and the parameters of the software have not been optimized to detect interstitial pneumonia. These results pave the way to a new approach for monitoring the pulmonary implication in pauci-symptomatic COVID-19 patients.

Pneumonia with empyema: rare complication after sea urchin injury

Staphylococcal pneumonias are rare, especially in immunocompetent children. They can represent a complication of tissue infection with hematogeneous dissemination. Sea urchin injuries can result in local reactions, granulomas and, unfrequently, systemic disease. We describe the case of a 16-year-old boy with a four-day fever and left-sided chest pain, with referral to a sea urchin injury five days before admission. Physical examination revealed diminished pulmonary sounds and crackles in the left lower hemithorax. The chest radiograph showed a pleural effusion. Blood tests showed leukocytosis, neutrophilia, and an elevated C-reactive protein. Empyema was diagnosed after performing a thoracentesis. Subsequently he initiated inflammatory signs with fluctuation on his right heel, with purulent drainage. Suspecting on a staphylococcal etiology, he was treated with flucloxacillin, a suspicion that was confirmed by the isolation of Staphylococcus aureus in pleural liquid and abscess material. After antibiotic treatment was established, there was a favorable clinical and radiological evolution. With this case report, we would like to draw attention to the possibility of hematogenous dissemination of a microorganism after local skin infection, even in immunocompetent individuals.

Tamponamento cardíaco na adolescência: dois casos clínicos

Cardiac tamponade is a medical emergency and is the most serious complication of pericardial effusion. The authors describe two case reports with different etiologies, in adolescence. 17 years old female patient, goes to the emergency department due to polyarthralgia, chest pain, orthopnea and fatigue. At observation: fever, tachycardia, decreased cardiac sounds, decreased pulmonary sounds in bases and tibio-tarsal joint edema. Chest radiography: cardiomegaly and bilateral interstitial infiltrate; electrocardiogram: ST elevation; echocardiogram: massive pericardial effusion (“swinging heart”). Pericardiocentesis was performed, with no significant changes in the pericardial fluid. Therapy with non-steroidal anti-inflammatory drugs (NSAIDs), acetylsalicylic acid (ASA) and colchicine was started. Further investigation led to systemic lupus erythematosus (SLE) diagnosis and improvement happened after correct therapy. 16-year-old male patient with Crohns disease under azathioprine and adalimumab, goes to the emergency department due fever, cough and chest pain. Three days before he had started amoxicillin-clavulanic acid for pneumonia. At observation he was tachycardic, with decreased cardiac sounds, decreased right breath sounds and painful abdomen on palpation. Thoraco-abdominal ultrasound: pleural effusion, hepatomegaly, splenic nodules, adenopathies in the celiac trunk. 72 hours after admission, under triple antibiotical therapy, there was clinical worsening and a thoracoabdominal CT was performed: pericardial and pleural effusion, mediastinal adenomegalies, hepatosplenomegaly, splenic lesions. Echocardiogram: pericardial effusion with collapse of the right cavities. Pericardial fluid showed an adenosine deaminase (ADA) of 53U/L. Clinical improvement after therapy for tuberculosis was started. Clinical suspicion is essential for a rapid therapeutic intervention, with echocardiography being the gold standard.

Differential Diagnosis of Asthma and COPD Based on Multivariate Pulmonary Sounds Analysis.

Asthma and chronic obstructive pulmonary disease (COPD) can be confused in clinical diagnosis due to overlapping symptoms. The purpose of this study is to develop a method based on multivariate pulmonary sounds analysis for differential diagnosis of the two diseases. The recorded 14-channel pulmonary sound data are mathematically modeled using multivariate (or, vector) autoregressive (VAR) model, and the model parameters are fed to the classifier. Separate classifiers are assumed for each of the six sub-phases of flow cycle, namely, early/mid/late inspiration and expiration, and the six decisions are combined to reach the final decision. Parameter classification is performed in the Bayesian framework with the assumption of Gaussian mixture model (GMM) for the likelihoods, and the six sub-phase decisions are combined by voting, where the weights are learned by a linear support vector machine (SVM) classifier. Fifty subjects are incorporated in the study, 30 being diagnosed with asthma and 20 with COPD. The highest accuracy of the classifier is 98 percent, corresponding to correct classification rates of 100 and 95 percent for asthma and COPD, respectively. The prominent sub-phase to differentiate between the two diseases is found to be mid-inspiration. The methodology proves to be promising in terms of asthma-COPD differentiation based on acoustic information. The results also reveal that the six sub-phases are not equally pertinent in the differentiation. Pulmonary sounds analysis may be a complementary tool in clinical practice for differential diagnosis of asthma and COPD, especially in the absence of reliable spirometric testing.

Variety of verbal and amplitude-frequency characteristics of wheezing in patients with bronchial asthma, depending on the severity of bronchial obstruction and shortness of breath

Objective. To study the “language” of whistling wheezing in patients with asthma, the relationship between verbal and amplitude-frequency characteristics (AFC) of wheezing and the severity of bronchial obstruction and dyspnea. Methods. 72 patients with partially controlled asthma were examined. The patients described whistling breathing by comparison and evaluated the degree of intensity of wheezing and dyspnea (Borg CR-10 scale). Spirometry was carried out with Vitalograph ALPHA spirometer (England) according to the rules of ATS/ERS with a bronchodilator test and simultaneous recording of pulmonary sounds with the Littmann 3,200 electronic stethoscope. Results. 2 groups of patients were formed based on verbal characteristics of the whistling wheezing. The 1 st group (38 patients) had wheezes of high-tone AFC (576 ± 33 Hz), 6.5 ± 0.7 points of wheezing intensity, and the degree of dyspnea intensity 4.8 ± 1.2 points on the Borg scale. The 2 nd group (34 patients) had wheezes of medium and low-tone AFC (368 ± 40.2 Hz), 3.8 ± 0.6 points of wheezing intensity, and degree of dyspnea intensity 3.7 ± 0.5 points according to Borg scale. Various “language” characteristics of whistling wheezing are obtained. The direct correlation between the degree of obstruction and subjective sensations of whistling breathing was found. The 1 st group had marked moderate and severe bronchial obstruction (FEV1 < 50%). The 2 nd group had mild and medium degree bronchial obstruction (50 > FEV1 < 80%). A positive bronchodilatator test was recorded in 100% patients in the 1 st group and 37% patients in the 2nd group. Postbronchodilator AFC of the wheezes were comparable between the groups. The decrease in the intensity of wheezing led to a reduced severity of shortness of breath. Dyspnea did not affect the subjective intensity of wheezing. Conclusion . Verbal characteristics of whistling breathing in asthma patients are given. There was a direct strong correlation between the perception of wheezing with the severity of bronchial obstruction and a weak feedback between the intensity of perception of wheezing and shortness of breath before the use of bronchodilator. A direct moderate correlation was found after the bronchodilatator test. The severity of bronchial obstruction in patients with asthma plays a major role in the occurrence of wheezing high-tone AFC. A good response to beta2-agonist inhalation therapy should be expected in these patients.

Innovative approaches to formation of practical skills in medical students during teaching the basics of child pulmonology

The training of future doctors in the conditions of reforming the Health Care in Ukraine requires the introduction of new methods, information and communication technologies, modern pedagogical and scientific innovations in accordance with world standards in the educational process. The purpose of the work was to improve the educational process on the Department of Propedeutics of pediatric diseases while teaching the students the basics of pediatric pulmonology. The article describes the stages of conducting practical classes, describes the method of forming practical skills in students during teaching children's pulmonology. In order to improve the practical training of students at the department, simulation methods are actively used, which allow to master the technique of auscultation in children, to differentiate acoustic phenomena in different pathological conditions. During the curation, future doctors will consolidate practical skills in the examination of the patient, summarize the data obtained. Digital respiratory sonography allows us to analyze whether the findings of the research students on the acoustic picture, obtained while listening to the lungs with stethoscopes, coincide with the results of a computer analysis of pulmonary sounds. As the results show, students' acquisition of practical skills on virtual simulators contributes to a more successful mastering of methods of physical examination of the patient, correct assessment of a particular clinical situation. Combining traditional teaching methods with innovative methods contributes to improving the quality of students' education and training of a new generation of highly skilled health care workers. Bringing to the international standards the educational and methodological support of the educational process, on the one hand, will reduce the outflow of young people, who want to study outside Ukraine, on the other hand – will allow to attract foreign students to Ukrainian medical universitets, which can become an additional source of state income in the form of tuition fees, and also contribute to the inflow of labor into domestic medicine

Emergency typhlectomy for caecal strangulation caused by chronic diaphragmatic hernia in a dog

A two‐year‐old female entire Catahoula leopard dog was referred for investigation and management of suspected chronic diaphragmatic hernia, 11 months post road traffic accident. The dog had a two‐month history of progressive lethargy and one‐week history of vomiting and anorexia. Physical examination revealed a slight increase in respiratory effort with normal respiratory rate. Cardiac and pulmonary sounds were muffled on thoracic auscultation and intestinal loops were not immediately palpable in the abdomen. Thoracic radiographs acquired before referral were suggestive of a diaphragmatic hernia, which was later confirmed on abdominal and thoracic ultrasound. Cardiorespiratory deterioration was evident eight hours post presentation and an emergency exploratory laparotomy was performed. The small intestines, caecum, and the ascending and transverse colon were found to have herniated into the thorax. Marked caecal necrosis was found intraoperatively. A typhlectomy and repair of the diaphragmatic defect were performed. The patient recovered uneventfully and was in good health nine months postoperatively.

Diagnostic accuracy of a velcro sound detector (VECTOR) for interstitial lung disease in rheumatoid arthritis patients: the InSPIRAtE validation study (INterStitial pneumonia in rheumatoid ArThritis with an electronic device)

BackgroundInterstitial lung disease (ILD) is a severe systemic manifestation of rheumatoid arthritis (RA). High-resolution computed tomography (HRCT) represents the gold standard for the diagnosis of ILD, but its routine use for screening programs is not advisable because of both high cost and X-ray exposure. Velcro crackles at lung auscultation occur very early in the course of interstitial pneumonia, and their detection is an indication for HRCT. Recently, we developed an algorithm (VECTOR) to detect the presence of Velcro crackles in pulmonary sounds and showed good results in a small sample of RA patients.The aim of the present investigation was to validate the diagnostic accuracy of VECTOR in a larger population of RA patients, compared with that of the reference standard of HRCT, from a multicentre study.MethodsTo avoid X-ray exposure, we enrolled 137 consecutive RA patients who had recently undergone HRCT. Lung sounds of all patients were recorded in 4 pulmonary fields bilaterally with a commercial electronic stethoscope (ES); subsequently, all HRCT images were blindly evaluated by a radiologist, and audio data were analysed by means of VECTOR.ResultsFifty-nine of 137 patients showed ILD (43.1%). VECTOR correctly classified 115/137 patients, showing a diagnostic accuracy of 83.9% and a sensitivity and specificity of 93.2 and 76.9%, respectively.ConclusionsVECTOR may represent the first validated tool for the screening of RA patients who are suspected for ILD and who should be directed to HRCT for the diagnosis.Moreover, early identification of RA-ILD could contribute to the design of prospective studies aimed at elucidating unclear aspects of the disease.

Right to left patent ductus arteriosus, acute bronchointerstitial pneumonia, pulmonary hypertension and cor pulmonale in a foal

SummaryPatent ductus arteriosus (PDA) is a rare congenital cardiac defect in foals causing left to right shunting from the aorta to pulmonary artery. In extremely rare conditions, complications with pulmonary hypertension can result in right to left shunting (Eisenmenger's physiology); however, reversed or right to left shunting has not yet been precisely described in PDA‐affected equids. This report describes a unique and unusual case of right to left PDA associated with acute respiratory distress syndrome in a 20‐day‐old male foal. A holosystolic murmur over the tricuspid valve area and adventitious pulmonary sounds respectively on cardiac and thoracic auscultations, caudodorsally interstitial and bronchointerstitial pulmonary opacities on thoracic radiography, right atrial and ventricular dilatations with paradoxical ventricular septal motion, increased ratio of pulmonary artery internal diameter to the aorta and tricuspid valve regurgitation on echocardiography were detected. Post‐mortem and histopathological examinations revealed consolidated, dark red and diffusely enlarged lungs with granular appearance, marked enlargement of the right atrium and ventricle, pulmonary artery thickening and enlargement, patency of the ductus arteriosus, hyaline membrane formation, type II pneumocyte proliferation, hypertrophy and thickening of the pulmonary arteries medial layers and right ventricular myocardial cells distortion and hypertrophy. The findings suggest a right to left shunting through the persistent patency of the ductus arteriosus, pulmonary hypertension and cor pulmonale. We proposed pulmonary hypertension associated with bronchointerstitial pneumonia as a cause of this unusual case of PDA with reversed shunt direction.

Wheeze type classification using non-dyadic wavelet transform based optimal energy ratio technique

Background and objectiveWheezes in pulmonary sounds are anomalies which are often associated with obstructive type of lung diseases. The previous works on wheeze-type classification focused mainly on using fixed time-frequency/scale resolution based on Fourier and wavelet transforms. The main contribution of the proposed method, in which the time-scale resolution can be tuned according to the signal of interest, is to discriminate monophonic and polyphonic wheezes with higher accuracy than previously suggested time and time-frequency/scale based methods. MethodsAn optimal Rational Dilation Wavelet Transform (RADWT) based peak energy ratio (PER) parameter selection method is proposed to discriminate wheeze types. Previously suggested Quartile Frequency Ratios, Mean Crossing Irregularity, Multiple Signal Classification, Mel-frequency Cepstrum and Dyadic Discrete Wavelet Transform approaches are also applied and the superiority of the proposed method is demonstrated in leave-one-out (LOO) and leave-one-subject-out (LOSO) cross validation schemes with support vector machine (SVM), k nearest neighbor (k-NN) and extreme learning machine (ELM) classifiers. ResultsThe results show that the proposed RADWT based method outperforms the state-of-the-art time, frequency, time-frequency and time-scale domain approaches for all classifiers in both LOO and LOSO cross validation settings. The highest accuracy values are obtained as 86% and 82.9% in LOO and LOSO respectively when the proposed PER features are fed into SVM. ConclusionsIt is concluded that time and frequency domain characteristics of wheezes are not steady and hence, tunable time-scale representations are more successful in discriminating polyphonic and monophonic wheezes when compared with conventional fixed resolution representations.

FPGA implementation of an automatic wheezing detection system

Abstract This paper presents a new hardware architecture for real-time wheezing detection in pulmonary sounds. The proposed architecture is based on Mel-frequency cepstral coefficients (MFCC) and artificial neural network (ANN). It has been implemented on field programmable gate array (FPGA) chip using a rapid prototyping design tool, Xilinx system generator (XSG), that provides a high-level of abstraction. The proposed architecture has been optimized, in terms of the required resources, to fit in a low cost FPGA chip. It has been also pipelined to ensure real-time performance. Resources utilization, maximum operating frequency and total power consumption obtained for an Artix-7 FPGA chip are presented and discussed. The wheezing detection/classifications rates of the proposed architecture have been evaluated using normal and wheezing respiratory sounds. Sensitivity, specificity, performance and accuracy obtained by the proposed hardware architecture are almost the same as those obtained by MATLAB software.