Novel audio characteristic-dependent feature extraction and data augmentation methods for cough-based respiratory disease classification.

Respiratory diseases are one of the major health problems worldwide. Early diagnosis of the disease types is of vital importance. As one of the main symptoms of many respiratory diseases, cough may contain information about different pathological changes in the respiratory system. Therefore, many researchers have used cough sounds to diagnose different diseases through artificial intelligence in recent years. The acoustic features and data augmentation methods commonly used in speech tasks are used to achieve better performance. Although these methods are applicable, previous studies have not considered the characteristics of cough sound signals. In this paper, we designed a cough-based respiratory disease classification system and proposed audio characteristic-dependent feature extraction and data augmentation methods. Firstly, according to the short durations and rapid transition of different cough stages, we proposed maximum overlapping mel-spectrogram to avoid missing inter-frame information caused by traditional framing methods. Secondly, we applied various data augmentation methods to mitigate the problem of limited labeled data. Based on the frequency energy distributions of different diseased cough audios, we proposed a parameter-independent self-energy-based augmentation method to enhance the differences between different frequency bands. Finally, in the model testing stage, we leveraged test-time augmentation to further improve the classification performance by fusing the test results of the original and multiple augmented audios. The proposed methods were validated on the Coswara dataset through stratified four-fold cross-validation. Compared to the baseline model using mel-spectrogram as input, the proposed methods achieved an average absolute performance improvement of 3.33% and 3.10% in macro Area Under the Receiver Operating Characteristic (macro AUC) and Unweighted Average Recall (UAR), respectively. The visualization results through Gradient-weighted Class Activation Mapping (Grad-CAM) showed the contributions of different features to model decisions.

An ensemble learning approach to digital corona virus preliminary screening from cough sounds.

This work develops a robust classifier for a COVID-19 pre-screening model from crowdsourced cough sound data. The crowdsourced cough recordings contain a variable number of coughs, with some input sound files more informative than the others. Accurate detection of COVID-19 from the sound datasets requires overcoming two main challenges (i) the variable number of coughs in each recording and (ii) the low number of COVID-positive cases compared to healthy coughs in the data. We use two open datasets of crowdsourced cough recordings and segment each cough recording into non-overlapping coughs. The segmentation enriches the original data without oversampling by splitting the original cough sound files into non-overlapping segments. Splitting the sound files enables us to increase the samples of the minority class (COVID-19) without changing the feature distribution of the COVID-19 samples resulted from applying oversampling techniques. Each cough sound segment is transformed into six image representations for further analyses. We conduct extensive experiments with shallow machine learning, Convolutional Neural Network (CNN), and pre-trained CNN models. The results of our models were compared to other recently published papers that apply machine learning to cough sound data for COVID-19 detection. Our method demonstrated a high performance using an ensemble model on the testing dataset with area under receiver operating characteristics curve = 0.77, precision = 0.80, recall = 0.71, F1 measure = 0.75, and Kappa = 0.53. The results show an improvement in the prediction accuracy of our COVID-19 pre-screening model compared to the other models.

The Japanese respiratory society guidelines for the management of cough and sputum (digest edition).

Cough and sputum are common complaints at outpatient visits. In this digest version, we provide a general overview of these two symptoms and discuss the management of acute (up to three weeks) and prolonged/chronic cough (longer than three weeks). Flowcharts are provided, along with a step-by-step explanation of their diagnosis and management. Most cases of acute cough are due to an infection. In chronic respiratory illness, a cough could be a symptom of a respiratory infection such as pulmonary tuberculosis, malignancy such as a pulmonary tumor, asthma, chronic obstructive pulmonary disease, chronic bronchitis, bronchiectasis, drug-induced lung injury, heart failure, nasal sinus disease, sinobronchial syndrome, eosinophilic sinusitis, cough variant asthma (CVA), atopic cough, chronic laryngeal allergy, gastroesophageal reflux (GER), and post-infectious cough. Antibiotics should not be prescribed for over-peak cough but can be considered for atypical infections. The exploration of a single/major cause is recommended for persistent/chronic cough. When sputum is present, a sputum smear/culture (general bacteria, mycobacteria), cytology, cell differentiation, chest computed tomography (CT), and sinus X-ray or CT should be performed. There are two types of rhinosinusitis. Conventional sinusitis and eosinophilic rhinosinusitis present primarily with neutrophilic inflammation and eosinophilic inflammation, respectively. The most common causes of dry cough include CVA, atopic cough/laryngeal allergy (chronic), GER, and post-infectious cough. In the last chapter, future challenges and perspectives are discussed. We hope that the clarification of the pathology of cough hypersensitivity syndrome will lead to further development of "pathology-specific non-specific therapeutic drugs" and provide benefits to patients with chronic refractory cough.

Eficacia de la miel para el tratamiento de la tos aguda en niños atendidos en forma ambulatoria / Efficacy of honey for treatment of acute cough in pediatric outpatients

A partir de una consulta en la central de emergencias de un niño con tos aguda, el autor del artículo realiza una búsqueda bibliográfica para revisar la evidencia sobre el uso de la miel para aliviar este síntoma. Luego de la lectura crítica de una revisión sistemática, el autor concluye que ésta podría ser una alternativa elegible frente a los jarabes para la tos, por su perfil de seguridad y su posible beneficio en el alivio de la tos. (AU)

Based on a consultation at the emergency room of a child with acute cough, the author of this article performs a bibliographic search to review the evidence on the use of honey to alleviate this symptom. After the critical appraisal of a systematic review, the author concludes that honey could be an eligible alternative to cough syrups, due to its safety profile and its possible benefit in cough relief. (AU)

Effectiveness of a chronic cough management algorithm at the transitional stage from acute to chronic cough in children: a multicenter, nested, single-blind, randomised controlled trial.

BACKGROUND: Chronic (lasting at least 4 weeks) cough in children is an important cause of morbidity. An algorithmic approach to the management of coughs in children evaluated in observational studies and a randomised controlled trial (RCT) enrolled children referred with median cough duration of 16 weeks to specialist centres. We investigated whether applying an evidence-based cough management algorithm in non-specialist settings earlier, once cough persisted for more than 4 weeks, improved cough resolution compared with usual care. METHODS: We undertook a multicentre, single-blind RCT nested within a prospective cohort study of children (<15 years) in Australia presenting to three primary care or three hospital emergency departments with an acute respiratory illness with cough. Children were excluded if they had a known diagnosis of an underlying chronic medical condition (excluding asthma) or had an immunosuppressive illness or were taking immunomodulating drugs for more than 2 weeks in the preceding 30 days, or had severe symptoms requiring inpatient hospitalisation. Children were followed up for 8 weeks; those with a persistent cough at day 28 were randomly assigned to the cough management algorithm or to usual care. Randomisation was stratified by reason for presentation, study site, and cough duration (4 weeks to <6 weeks vs ≥6 weeks) using computer-generated permuted blocks (block size of four) with a 1:1 allocation. The primary outcome was the proportion of children with cough resolution at day 56 (defined as resolved if the child did not cough for at least 3 days and nights since day 28 or a more than 75% reduction in their average day and night cough score). Absolute risk differences (RDabsolute) were calculated by modified intention-to-treat analysis (ITT). This trial is registered with the Australia New Zealand Clinical Trials Registry, ACTRN12615000132549. FINDINGS: Between July 7, 2015, and Oct 31, 2018, 1018 children were screened, 509 were enrolled in the cohort study, and of 115 children in the ITT analysis, 57 were randomly assigned to the intervention group and 58 to the control group. Children had a median age of 1·6 years (IQR 1·0-4·5); 45 (39%) of 115 were Indigenous, and 59 (51%) were boys. By day 56, 33 (58%) of 57 children in the intervention group achieved cough resolution compared with 23 (40%) 58 in the control group; cough resolution was unknown in 12 (21%) of 57 children receiving the intervention and in 13 (22%) of 58 receiving the control. The RDabsolute assuming children with an unknown cough outcome were still coughing at day 56 was 18·3% (95% CI 0·3-36·2); the number needed-to-treat for benefit was five (95% CI 3-364); the adjusted odds ratio was 1·5 (95% CI 1·3-1·6), favouring the intervention group. INTERPRETATION: This study suggests an evidence-based cough management algorithm improves cough resolution in community-based children in the early phases of chronic cough. However, larger studies to confirm these findings in primary care are required. FUNDING: National Health and Medical Research Council.

TussisWatch: A Smart-Phone System to Identify Cough Episodes as Early Symptoms of Chronic Obstructive Pulmonary Disease and Congestive Heart Failure.

Chronic obstructive pulmonary disease (COPD) and congestive heart failure (CHF) are leading chronic health concerns among the aging population today. They are both typically characterized by episodes of cough that share similarities. In this paper, we design TussisWatch, a smart-phone-based system to record and process cough episodes for early identification of COPD or CHF. In our technique, for each cough episode, we do the following: 1) filter noise; 2) use domain expertise to partition each cough episode into multiple segments, indicative of disease or otherwise; 3) identify a limited number of audio features for each cough segment; 4) remove inherent biases as a result of sample size differences; and 5) design a two-level classification scheme, based on the idea of Random Forests, to process a recorded cough segment. Our classifier, at the first-level, identifies whether or not a given cough segment indicates a disease. If yes, the second-level classifier identifies the cough segment as symptomatic of COPD or CHF. Testing with a cohort of 9 COPD, 9 CHF, and 18 CONTROLS subjects spread across both the genders, races, and ages, our system achieves good performance in terms of Sensitivity, Specificity, Accuracy, and Area under ROC curve. The proposed system has the potential to aid early access to healthcare, and may be also used to educate patients on self-care at home.

Automatic Croup Diagnosis Using Cough Sound Recognition.

OBJECTIVE: Croup, a respiratory tract infection common in children, causes an inflammation of the upper airway restricting normal breathing and producing cough sounds typically described as seallike "barking cough." Physicians use the existence of barking cough as the defining characteristic of croup. This paper aims to develop automated cough sound analysis methods to objectively diagnose croup. METHODS: In automating croup diagnosis, we propose the use of mathematical features inspired by the human auditory system. In particular, we utilize the cochleagram for feature extraction, a time-frequency representation where the frequency components are based on the frequency selectivity property of the human cochlea. Speech and cough share some similarities in the generation process and physiological wetware used. As such, we also propose the use of mel-frequency cepstral coefficients which has been shown to capture the relevant aspects of the short-term power spectrum of speech signals. Feature combination and backward sequential feature selection are also experimented with. Experimentation is performed on cough sound recordings from patients presenting various clinically diagnosed respiratory tract infections divided into croup and non-croup. The dataset is divided into training and test sets of 364 and 115 patients, respectively, with automatically segmented cough sound segments. RESULTS: Croup and non-croup patient classification on the test dataset with the proposed methods achieve a sensitivity and specificity of 92.31% and 85.29%, respectively. CONCLUSION: Experimental results show the significant improvement in automatic croup diagnosis against earlier methods. SIGNIFICANCE: This paper has the potential to automate croup diagnosis based solely on cough sound analysis.

A Machine Hearing System for Robust Cough Detection Based on a High-Level Representation of Band-Specific Audio Features.

Cough is a protective reflex conveying information on the state of the respiratory system. Cough assessment has been limited so far to subjective measurement tools or uncomfortable (i.e., non-wearable) cough monitors. This limits the potential of real-time cough monitoring to improve respiratory care. OBJECTIVE: This paper presents a machine hearing system for audio-based robust cough segmentation that can be easily deployed in mobile scenarios. METHODS: Cough detection is performed in two steps. First, a short-term spectral feature set is separately computed in five predefined frequency bands: [0, 0.5), [0.5, 1), [1, 1.5), [1.5, 2), and [2, 5.5125] kHz. Feature selection and combination are then applied to make the short-term feature set robust enough in different noisy scenarios. Second, high-level data representation is achieved by computing the mean and standard deviation of short-term descriptors in 300 ms long-term frames. Finally, cough detection is carried out using a support vector machine trained with data from different noisy scenarios. The system is evaluated using a patient signal database which emulates three real-life scenarios in terms of noise content. RESULTS: The system achieves 92.71% sensitivity, 88.58% specificity, and 90.69% Area Under Receiver Operating Charcteristic (ROC) curve (AUC), outperforming state-of-the-art methods. CONCLUSION: Our research outcome paves the way to create a device for cough monitoring in real-life situations. SIGNIFICANCE: Our proposal is aligned with a more comfortable and less disruptive patient monitoring, with benefits for patients (allows self-monitoring of cough symptoms), practitioners (e.g., assessment of treatments or better clinical understanding of cough patterns), and national health systems (by reducing hospitalizations).

Diagnosis and treatment of community-acquired pneumonia in patients with acute cough: a quantitative study of decision thresholds in primary care.

BACKGROUND: Test and treatment thresholds have not yet been described for decision-making regarding the likelihood of pneumonia in patients with acute cough. AIM: To determine decision thresholds in the management of patients with acute cough. DESIGN AND SETTING: Set among primary care physicians attending meetings in the US and Switzerland, using data from a prospective cohort of primary care patients. METHOD: Clinical vignettes were used to study the clinical decisions of physicians regarding eight patients with cough that varied by six signs and symptoms. The probability of community-acquired pneumonia (CAP) was determined for each vignette based on a multivariate model. A previously published approach based on logistic regression was used to determine test and treatment thresholds. RESULTS: In total, 256 physicians made 764 clinical decisions. Initial physician estimates systematically overestimated the likelihood of CAP; 75% estimating a higher probability than that predicted by the multivariate model. Given the probability of CAP from a multivariate model, 16.7% (125 of 749) changed their decision from 'treat' to 'test' or 'test' to 'rule out', whereas only 3.5% (26/749) changed their decision from 'rule out' to 'test' or 'test' to 'treat'. Test and treatment thresholds were 9.5% (95% confidence interval (CI) = 8.7 to 10.5) and 43.1% (95% CI = 40.1 to 46.4) and were updated to 12.7% (95% CI = 11.7 to 13.8) and 51.3% (95% CI = 48.3 to 54.9) once the true probability of CAP was given. Test thresholds were consistent between subgroups. Treatment thresholds were higher if radiography was available, for Swiss physicians, and for non-primary care physicians. CONCLUSION: Test and treatment thresholds for CAP in patients with acute cough were 9.5% and 43.1%, respectively. Physicians tended to overestimate the likelihood of CAP, and providing information from a clinical decision rule (CDR) changed about 1 in 6 clinical decisions.

Antibiotics for prolonged wet cough in children.

BACKGROUND: Cough is a frequent symptom presenting to doctors. The most common cause of childhood chronic (greater than fours weeks' duration) wet cough is protracted bacterial bronchitis (PBB) in some settings, although other more serious causes can also present this way. Timely and effective management of chronic wet or productive cough improves quality of life and clinical outcomes. Current international guidelines suggest a course of antibiotics is the first treatment of choice in the absence of signs or symptoms specific to an alternative diagnosis. This review sought to clarify the current evidence to support this recommendation. OBJECTIVES: To determine the efficacy of antibiotics in treating children with prolonged wet cough (excluding children with bronchiectasis or other known underlying respiratory illness) and to assess risk of harm due to adverse events. SEARCH METHODS: We undertook an updated search (from 2008 onwards) using the Cochrane Airways Group Specialised Register, Cochrane Register of Controlled Trials (CENTRAL), MEDLINE, Embase, trials registries, review articles and reference lists of relevant articles. The latest searches were performed in September 2017. SELECTION CRITERIA: We included randomised controlled trials (RCTs) comparing antibiotics with a placebo or a control group in children with chronic wet cough. We excluded cluster and cross-over trials. DATA COLLECTION AND ANALYSIS: We used standard methods as recommended by Cochrane. We reviewed results of searches against predetermined criteria for inclusion. Two independent review authors selected, extracted and assessed the data for inclusion. We contacted authors of eligible studies for further information as needed. We analysed data as 'intention to treat.' MAIN RESULTS: We identified three studies as eligible for inclusion in the review. Two were in the previous review and one new study was included. We considered the older studies to be at high or unclear risk of bias whereas we judged the newly included study at low risk of bias. The studies varied in treatment duration (from 7 to 14 days) and the antibiotic used (two studies used amoxicillin/clavulanate acid and one used erythromycin).We included 190 children (171 completed), mean ages ranged from 21 months to six years, in the meta-analyses. Analysis of all three trials (190 children) found that treatment with antibiotics reduced the proportion of children not cured at follow-up (primary outcome measure) (odds ratio (OR) 0.15, 95% confidence interval (CI) 0.07 to 0.31, using intention-to -treat analysis), which translated to a number needed to treat for an additional beneficial outcome (NNTB) of 3 (95% CI 2 to 4). We identified no significant heterogeneity (for both fixed-effect and random-effects model the I² statistic was 0%). Two older trials assessed progression of illness, defined by requirement for further antibiotics (125 children), which was significantly lower in the antibiotic group (OR 0.10, 95% CI 0.03 to 0.34; NNTB 4, 95% CI 3 to 5). All three trials (190 children) reported adverse events, which were not significantly increased in the antibiotic group compared to the control group (OR 1.88, 95% CI 0.62 to 5.69). We assessed the quality of evidence GRADE rating as moderate for all outcome measures, except adverse events which we assessed as low quality. AUTHORS' CONCLUSIONS: Evidence suggests antibiotics are efficacious for the treatment of children with chronic wet cough (greater than four weeks) with an NNTB of three. However, antibiotics have adverse effects and this review reported only uncertainty as to the risk of increased adverse effects when they were used in this setting. The inclusion of a more robust study strengthened the previous Cochrane review and its results.

Efficient k-NN Implementation for Real-Time Detection of Cough Events in Smartphones.

The potential of telemedicine in respiratory health care has not been completely unveiled in part due to the inexistence of reliable objective measurements of symptoms such as cough. Currently available cough detectors are uncomfortable and expensive at a time when generic smartphones can perform this task. However, two major challenges preclude smartphone-based cough detectors from effective deployment namely, the need to deal with noisy environments and computational cost. This paper focuses on the latter, since complex machine learning algorithms are too slow for real-time use and kill the battery in a few hours unless specific actions are taken. In this paper, we present a robust and efficient implementation of a smartphone-based cough detector. The audio signal acquired from the device's microphone is processed by computing local Hu moments as a robust feature set in the presence of background noise. We previously demonstrated that pairing Hu moments and a standard k-NN classifier achieved accurate cough detection at the expense of computation time. To speed-up k-NN search, many tree structures have been proposed. Our cough detector uses an improved vantage point (vp)-tree with optimized construction methods and a distance function that results in faster searches. We achieve 18× speed-up over classic vp-trees, and 560× over standard implementations of k-NN in state-of-the-art machine learning libraries, with classification accuracies over 93%, enabling real-time performance on low-end smartphones.

Classification of Cough as a Symptom in Adults and Management Algorithms: CHEST Guideline and Expert Panel Report.

BACKGROUND: We performed systematic reviews using the population, intervention, comparison, outcome (PICO) format to answer the following key clinical question: Are the CHEST 2006 classifications of acute, subacute and chronic cough and associated management algorithms in adults that were based on durations of cough useful? METHODS: We used the CHEST Expert Cough Panel's protocol for the systematic reviews and the American College of Chest Physicians (CHEST) methodological guidelines and Grading of Recommendations Assessment, Development, and Evaluation framework. Data from the systematic reviews in conjunction with patient values and preferences and the clinical context were used to form recommendations or suggestions. Delphi methodology was used to obtain the final grading. RESULTS: With respect to acute cough (< 3 weeks), only three studies met our criteria for quality assessment, and all had a high risk of bias. As predicted by the 2006 CHEST Cough Guidelines, the most common causes were respiratory infections, most likely of viral cause, followed by exacerbations of underlying diseases such as asthma and COPD and pneumonia. The subjects resided on three continents: North America, Europe, and Asia. With respect to subacute cough (duration, 3-8 weeks), only two studies met our criteria for quality assessment, and both had a high risk of bias. As predicted by the 2006 guidelines, the most common causes were postinfectious cough and exacerbation of underlying diseases such as asthma, COPD, and upper airway cough syndrome (UACS). The subjects resided in countries in Asia. With respect to chronic cough (> 8 weeks), 11 studies met our criteria for quality assessment, and all had a high risk of bias. As predicted by the 2006 guidelines, the most common causes were UACS from rhinosinus conditions, asthma, gastroesophageal reflux disease, nonasthmatic eosinophilic bronchitis, combinations of these four conditions, and, less commonly, a variety of miscellaneous conditions and atopic cough in Asian countries. The subjects resided on four continents: North America, South America, Europe, and Asia. CONCLUSIONS: Although the quality of evidence was low, the published literature since 2006 suggests that CHEST's 2006 Cough Guidelines and management algorithms for acute, subacute, and chronic cough in adults appeared useful in diagnosing and treating patients with cough around the globe. These same algorithms have been updated to reflect the advances in cough management as of 2017.

Noninvasive ventilation for avoidance of reintubation in patients with various cough strength.

BACKGROUND: Reintubation is associated with high mortality. Identification of methods to avoid reintubation is needed. The aim of this study was to assess whether prophylactic noninvasive ventilation (NIV) would benefit patients with various cough strengths. METHODS: We prospectively enrolled 356 patients who successfully passed a spontaneous breathing trial in a respiratory intensive care unit. Before extubation, cough peak flow was measured. After extubation, attending physicians determined whether the patients would receive prophylactic NIV or conventional oxygen treatment (control group). Patients were followed up to 90 days postextubation or death, whichever came first. RESULTS: The median value of cough peak flow was 70 L/minute. Among the patients with cough peak flow ≤70 L/minute, 108 received NIV and 72 received conventional oxygen treatment. In this cohort, NIV reduced reintubation (9 % vs. 35 % at postextubation 72 h, p < 0.01; and 24 % vs. 49 % at postextubation 7 days, p < 0.01) and postextubation 90-day mortality (43 % vs. 61 %, p = 0.02) compared with the control group. Further, use of NIV was an independent protective factor for reintubation (OR = 0.19, p < 0.01 at 72 h postextubation; and OR = 0.33, p < 0.01 at 7 days postextubation) and for death at 90 days postextubation (OR = 0.40, p = 0.02). Among patients with cough peak flow >70 L/minute, 71 received NIV and 105 received conventional oxygen treatment. In this cohort, NIV did not reduce reintubation (6 % vs. 6 % at 72 h postextubation, p > 0.99; and 9 % vs. 9 % at 7 days postextubation, p > 0.99) or postextubation 90-day mortality (21 % vs. 15 %, p = 0.32) compared with the control group. Further, use of NIV was not associated with reintubation or postextubation 90-day mortality. CONCLUSION: In a planned extubated population, prophylactic NIV benefited patients with weak cough but possibly not in patients with strong cough.

[Automatic Classification of Dry Cough and Wet Cough Based on Improved Reverse Mel Frequency Cepstrum Coefficients].

Automatic classification of different types of cough plays an important role in clinical.In the previous research of cough classification or cough recognition,traditional Mel frequency cepstrum coefficients(MFCC)which extracts feature mainly from low frequency band is usually used as feature expression.In this paper,by analyzing the distributions of spectral energy of dry/wet cough,it is found that spectral difference of two types of cough exits mainly in middle frequency band and high frequency band.To better reflect the spectral difference of dry cough and wet cough,an improved method of extracting reverse MFCC is proposed.In this method,reverse Mel filter-bank in which filters are allocated in reverse Mel scale is adopted and is improved by placing filters only in the frequency band with high spectral energy.As a result,features are mainly extracted from the frequency band where two types of cough show both high spectral energy and distinguished difference.Detailed process of accessing improved reverse MFCC was introduced and hidden Markov models trained by 60 dry cough and 60 wet cough were used as cough classification model.Classification experiment results for 120 dry cough and 85 wet cough showed that,compared to traditional MFCC,better classification performance was achieved by the proposed method and the total classification accuracy was raised from 89.76%to 93.66%.

Cough event classification by pretrained deep neural network.

BACKGROUND: Cough is an essential symptom in respiratory diseases. In the measurement of cough severity, an accurate and objective cough monitor is expected by respiratory disease society. This paper aims to introduce a better performed algorithm, pretrained deep neural network (DNN), to the cough classification problem, which is a key step in the cough monitor. METHOD: The deep neural network models are built from two steps, pretrain and fine-tuning, followed by a Hidden Markov Model (HMM) decoder to capture tamporal information of the audio signals. By unsupervised pretraining a deep belief network, a good initialization for a deep neural network is learned. Then the fine-tuning step is a back propogation tuning the neural network so that it can predict the observation probability associated with each HMM states, where the HMM states are originally achieved by force-alignment with a Gaussian Mixture Model Hidden Markov Model (GMM-HMM) on the training samples. Three cough HMMs and one noncough HMM are employed to model coughs and noncoughs respectively. The final decision is made based on viterbi decoding algorihtm that generates the most likely HMM sequence for each sample. A sample is labeled as cough if a cough HMM is found in the sequence. RESULTS: The experiments were conducted on a dataset that was collected from 22 patients with respiratory diseases. Patient dependent (PD) and patient independent (PI) experimental settings were used to evaluate the models. Five criteria, sensitivity, specificity, F1, macro average and micro average are shown to depict different aspects of the models. From overall evaluation criteria, the DNN based methods are superior to traditional GMM-HMM based method on F1 and micro average with maximal 14% and 11% error reduction in PD and 7% and 10% in PI, meanwhile keep similar performances on macro average. They also surpass GMM-HMM model on specificity with maximal 14% error reduction on both PD and PI. CONCLUSIONS: In this paper, we tried pretrained deep neural network in cough classification problem. Our results showed that comparing with the conventional GMM-HMM framework, the HMM-DNN could get better overall performance on cough classification task.

Wavelet augmented cough analysis for rapid childhood pneumonia diagnosis.

Pneumonia is the cause of death for over a million children each year around the world, largely in resource poor regions such as sub-Saharan Africa and remote Asia. One of the biggest challenges faced by pneumonia endemic countries is the absence of a field deployable diagnostic tool that is rapid, low-cost and accurate. In this paper, we address this issue and propose a method to screen pneumonia based on the mathematical analysis of cough sounds. In particular, we propose a novel cough feature inspired by wavelet-based crackle detection work in lung sound analysis. These features are then combined with other mathematical features to develop an automated machine classifier, which can separate pneumonia from a range of other respiratory diseases. Both cough and crackles are symptoms of pneumonia, but their existence alone is not a specific enough marker of the disease. In this paper, we hypothesize that the mathematical analysis of cough sounds allows us to diagnose pneumonia with sufficient sensitivity and specificity. Using a bedside microphone, we collected 815 cough sounds from 91 patients with respiratory illnesses such as pneumonia, asthma, and bronchitis. We extracted wavelet features from cough sounds and combined them with other features such as Mel Cepstral coefficients and non-Gaussianity index. We then trained a logistic regression classifier to separate pneumonia from other diseases. As the reference standard, we used the diagnosis by physicians aided with laboratory and radiological results as deemed necessary for a clinical decision. The methods proposed in this paper achieved a sensitivity and specificity of 94% and 63%, respectively, in separating pneumonia patients from non-pneumonia patients based on wavelet features alone. Combining the wavelets with features from our previous work improves the performance further to 94% and 88% sensitivity and specificity. The performance far surpasses that of the WHO criteria currently in common use in resource-limited settings.

[Diagnosing and treating cough]. / Udredning og behandling af hoste.

Cough is frequently a reason for seeing a doctor. Cough has a wide range of causes and the diagnosis can be difficult to make. Cough is often benign and self-limiting but can also be the first sign of malignancy. Especially chronic cough reduces the patients' quality of life. The purpose of this review was to present the most common reasons for cough, a rational method of investigation and a management protocol. Cough is a condition, which in most cases can be treated when using a systematic approach.

Phenotyping airways disease: an A to E approach.

The airway diseases asthma and chronic obstructive pulmonary disease (COPD) are heterogeneous conditions with overlapping pathophysiological and clinical features. It has previously been proposed that this heterogeneity may be characterized in terms of five relatively independent domains labelled from A to E, namely airway hyperresponsiveness (AHR), bronchitis, cough reflex hypersensitivity, damage to the airways and surrounding lung parenchyma, and extrapulmonary factors. Airway hyperresponsiveness occurs in both asthma and COPD, accounting for variable day to day symptoms, although the mechanisms most likely differ between the two conditions. Bronchitis, or airway inflammation, may be predominantly eosinophilic or neutrophilic, with different treatments required for each. Cough reflex hypersensitivity is thought to underlie the chronic dry cough out of proportion to other symptoms that can occur in association with airways disease. Structural changes associated with airway disease (damage) include bronchial wall thickening, airway smooth muscle hypertrophy, bronchiectasis and emphysema. Finally, a variety of extrapulmonary factors may impact upon airway disease, including rhinosinusitis, gastroesophageal reflux disease, obesity and dysfunctional breathing. This article discusses the A to E concept in detail and describes how this framework may be used to assess and treat patients with airway diseases in the clinic.