A Wearable Stethoscope for Long-Term Ambulatory Respiratory Health Monitoring.

Lung sounds acquired by stethoscopes are extensively used in diagnosing and differentiating respiratory diseases. Although an extensive know-how has been built to interpret these sounds and identify diseases associated with certain patterns, its effective use is limited to individual experience of practitioners. This user-dependency manifests itself as a factor impeding the digital transformation of this valuable diagnostic tool, which can improve patient outcomes by continuous long-term respiratory monitoring under real-life conditions. Particularly patients suffering from respiratory diseases with progressive nature, such as chronic obstructive pulmonary diseases, are expected to benefit from long-term monitoring. Recently, the COVID-19 pandemic has also shown the lack of respiratory monitoring systems which are ready to deploy in operational conditions while requiring minimal patient education. To address particularly the latter subject, in this article, we present a sound acquisition module which can be integrated into a dedicated garment; thus, minimizing the role of the patient for positioning the stethoscope and applying the appropriate pressure. We have implemented a diaphragm-less acousto-electric transducer by stacking a silicone rubber and a piezoelectric film to capture thoracic sounds with minimum attenuation. Furthermore, we benchmarked our device with an electronic stethoscope widely used in clinical practice to quantify its performance.

The Southern Sweden Adolescent Allergy-Cohort: Prevalence of allergic diseases and cross-sectional associations with individual and social factors.

OBJECTIVES: Asthma and allergic diseases are the most frequent chronic diseases in childhood worldwide, and considered a burden for the affected children and their families. The diseases impose an economic burden on society if not diagnosed and treated properly and management of and these diseases are challenging for healthcare professionals. The aim of the present investigation was to assess the prevalence of allergic diseases in an unselected cohort of adolescents in southern Sweden. Additionally, associations with sociodemographic factors were investigated, as well as impact on daily life. METHODS: This cross-sectional study was based on a cohort of n = 1 530 school children, aged 13 to 14, from 13 municipalities in southern Sweden. Data were collected through web-based questionnaires. RESULTS: Of all children 32% reported at least one allergic disease. 67% reported one allergic disease and 33% reported more than one. No allergy-related disease were reported by 68%. Current asthma was reported by 9.8% and current rhino-conjunctivitis was reported by 13%. The prevalence of food hypersensitivity was 12% and the prevalence of eczema was 11%. One to three wheezing attacks were reported from 55% and 40% reported more than four attacks of wheezing in the preceding year. The self-reported allergic diseases were diagnosed by a doctor in; 36% (food hypersensitivity) to 69% (rhinoconjunctivitis) of the cases. CONCLUSIONS: A high number of affected children were identified. Some children being undiagnosed and some not receiving satisfactory treatment. These results suggest that additional studies to evaluate treatment procedures in order to improve healthcare for allergic children are warranted.

Oral Dexamethasone to Control Wheezing in Children at an Outpatient Clinic.

Asthma, a chronic childhood disease, has resulted in increased emergency department (ED) visits with high costs. Many asthma ED visits are nonemergent and could be treated in outpatient clinics. Literature has concluded that a 2-day course of oral dexamethasone has comparable outcomes to a 5-day course of prednisone in the ED and hospital setting. A retrospective chart review was performed on children requiring in-house treatment with a corticosteroid (dexamethasone n = 23, prednisone n = 40) for acute asthma exacerbations at an ambulatory medical home. The rates of hospital admissions, ED visits, and symptom follow-up were similar between the 2 groups ( P > .05). The cost for a course of dexamethasone was US$1.28 versus US$16.20 for prednisolone. The average cost for an asthma exacerbation office visit was US$79.89 compared with US$3113.28 for an ED visit. A 2-day course of oral dexamethasone appears to be a promising clinical and cost-effective treatment for acute asthma exacerbations at the primary care level.

Assessment of Respiratory Symptoms and Pulmonary Function Status among Workers of Flour Mills in Addis Ababa, Ethiopia: Comparative Cross-Sectional Study.

BACKGROUND: Flour dust in the respiratory tract affects lung function. Flour dust is a heterogeneous organic substance which can have a tendency to cause respiratory ailments. There is growing consensus on the deleterious effects of flour dust on respiratory symptoms and lung performance of flour mill workers. METHODS: The study design was comparative cross-sectional. A total of 54 flour mill workers who work for more than eight-hour shift per day and 54 control subjects matched for sex, age, weight, height, and area of residence were enrolled. Anthropometric measurement was done. Lung function was measured by using a digital portable spirometer (Spiro Pro) based on the ATS guidelines. FVC, FEV1, FEV1/FVC, PEFR, and FEF25%  -75% were measured. Productive cough, dry cough, wheeze, and breathlessness were evaluated using BMRC questionnaire guidelines, administered through face-to-face interview. RESULT: This study showed statistically significant reduction in the mean values of pulmonary function tests in flour mill workers as compared to their matched controls. Reduction of pulmonary function indices in study subjects was significant for FVC (4.25±0.93 vs. 5.30±0.71, p<0.001), FEV1 (3.46±0.86 vs. 4.50±0.72, p<0.001), PEFR (5.43±2.43 vs. 7.87±2.53, p<0.001), and FEF25%  -75%, (3.87±1.61 vs. 4.60±1.60, p<0.05), but not significant for FEV1/FVC (81.93±12.74 vs. 83.40±12.50, p>0.05). Flour mill workers developed 27.7% of restrictive type and 11.1% of obstructive type of lung disorders. Percentage prevalence of respiratory symptoms was evaluated as dry cough (27.7% vs. 9.3%), productive cough (11.1% vs. 5.6%), wheeze (14.8% vs. 3.8%), and breathlessness (16.6% vs.7.4%) in flour mill workers and controls, respectively. CONCLUSION: Based on the results of the present study, occupational exposure to flour dust could cause respiratory dysfunction, thereby reducing lung efficiency.

Asthmatic Wheeze Detection From Compressively Sensed Respiratory Sound Spectra.

Quantification of wheezing by a sensor system consisting of a wearable wireless acoustic sensor and smartphone performing respiratory sound classification may contribute to the diagnosis, long-term control, and lowering treatment costs of asthma. In such battery-powered sensor system, compressive sensing (CS) was verified as a method for simultaneously cutting down power cost of signal acquisition, compression, and communication on the wearable sensor. Matching real-time CS reconstruction algorithms, such as orthogonal matching pursuit (OMP), have been demonstrated on the smartphone. However, their lossy performance limits the accuracy of wheeze detection from CS-recovered short-term Fourier spectra (STFT), when using existing respiratory sound classification algorithms. Thus, here we present a novel, robust algorithm tailored specifically for wheeze detection from the CS-recovered STFT. The proposed algorithm identifies occurrence and tracks multiple individual wheeze frequency lines using hidden Markov model. The algorithm yields 89.34% of sensitivity, 96.28% of specificity, and 94.91% of accuracy on Nyquist-rate sampled respiratory sounds STFT. It enables for less than 2% loss of classification accuracy when operating over STFT reconstructed by OMP, at the signal compression ratio of up to 4 $\times$ (classification from only 25% signal samples). It features execution speed comparable to referent algorithms, and offers good prospects for parallelism.

Prospective Assessment of Rhinovirus Symptoms and Species Recurrence in Children With and Without an Acute Wheezing Exacerbation.

To assess if the difference in species-specific immune response to RV-C correlates with a higher frequency of reinfection, shorter time to reinfection, or different symptom severity than infections with RV-A or RV-B. Forty-three patients were enrolled of which 34 were successfully tracked longitudinally over 3 months, with nasal swabs and symptom questionnaires provided every 2 weeks to identify rhinovirus (RV) strains and the concurrent symptomatology. No difference was found in the time to reinfection with an RV species between RV-C and RV-A or RV-B (p = 0.866). There was a trend toward more rapid reinfection with the same species in RV-C than RV-A (55.1 days vs. 67.9 days), but this failed to reach statistical significance (p = 0.105). RV infections were generally associated with only minor symptoms, with rhinorrhea being the only significantly associated symptom (p = 0.01). RV-C was shown to have higher levels of lethargy and wheeze than other RV species. Time to reinfection with subsequent RV is not influenced by the species of the preceding RV.

Minimising wheeze in the under-threes: developing a respiratory assessment clinic for children.

A reluctance to diagnose asthma in children under three who have recurrent cough and wheeze causes delays in the commencement of appropriate asthma treatment. Timely inhaled corticosteroid use may reduce asthma exacerbations and unnecessary visits to the emergency department and GPs. To address this delay, an advanced nurse practitioner in one children's community nursing team set up a respiratory assessment clinic for children under three who had recurrent respiratory difficulties. This article describes the rationale and the evidence base that supports a clinic of this kind and reports on its initial results.

A cross-sectional assessment of the burden of COPD symptoms in the US and Europe using the National Health and Wellness Survey.

INTRODUCTION: Past research has suggested significant relationships between symptoms and health outcomes among patients with COPD. However, these studies have generally focused on a broad COPD sample and may have included those not receiving proper treatment. As a result, the aim of this study was to document the burden of COPD symptoms among those who are currently treated with the standard-of-care (SOC) medications in both the US and Western Europe. METHODS: Data from the 2013 US (N=75,000) and 2011 (N=57,512)/2013 (N=62,000) European (France, Germany, Italy, Spain, and UK; 5EU) National Health and Wellness Survey (NHWS) were used. The NHWS is a health survey administered to a demographically representative sample of the adult population in each country. A total of 1,666 and 2,006 patients with self-reported physician diagnosis of COPD in the 5EU and US, respectively, were being treated with the appropriate SOC (based on self-reported medication use) and were included in the analyses. Symptoms (eg, dyspnea, coughing, wheezing) were reported descriptively and summed to create a symptom score (with higher score indicating more frequent symptoms). The relationships between the symptom score and patient outcomes (eg, health status using the Short Form-36 version 2 [SF-36v2], work productivity and activity impairment [WPAI], and self-reported health care resource use) were explored using regression modeling. RESULTS: Nearly all patients (99.7% and 99.8% in the 5EU and US, respectively) reported experiencing symptoms and >80% reported experiencing at least one symptom "often". Increasing symptom scores were associated with poorer health status (unstandardized beta [b] =-0.87 and -0.78 for mental component summary and physical component summary, respectively, in the US and b =-0.67 and -0.79 in the 5EU, respectively; all P<0.05). Increasing symptom scores were also associated with greater work impairment (b =0.09 and 0.06 for the US and 5EU, respectively), activity impairment (b =0.05 and 0.06, respectively), and health care resource utilization (eg, hospitalizations: b =0.05 and 0.06, respectively) (all P<0.05). Approximately 70% of patients reported some level of non-adherence. Greater non-adherence was significantly associated with more frequent symptoms, poorer health status, and greater work impairment and health care resource use (all P<0.05). CONCLUSION: Patients with COPD who are using the appropriate SOC still experience symptoms, which have a significant effect on both humanistic and economic outcomes.

Population-Attributable Risk of Risk Factors for Recurrent Wheezing in Moderate Preterm Infants During the First Year of Life.

BACKGROUND: Recurrent wheezing in young infants has a high prevalence, influences quality of life, and generates substantial health care costs. We previously showed that respiratory syncytial virus infection is an important mechanism of recurrent wheezing in moderate preterm infants. We aimed to provide population-attributable risks (PAR) of risk factors for recurrent wheezing during the first year of life in otherwise healthy moderate preterm infants. METHODS: RISK is a multicentre prospective birth cohort study of 4424 moderate preterm infants born at 32-35 weeks gestation. We estimated PAR of risk factors for recurrent wheezing, which was defined as three or more parent-reported wheezing episodes during the first year of life. RESULTS: We evaluated 3952 (89%) children at 1 year of age, of whom 705 infants (18%) developed recurrent wheezing. Fourteen variables were independently associated with recurrent wheezing. Hospitalisation for respiratory syncytial virus bronchiolitis had a strong relationship with recurrent wheezing (RR 2.6; 95% confidence interval, CI, 2.2, 3.1), but a relative modest PAR (8%; 95% CI 6, 11%) which can be explained by a low prevalence (13%). Day-care attendance showed a strong relationship with recurrent wheezing (RR 1.9; 95% CI 1.7, 2.2) and the highest PAR (32%; 95% CI 23, 37%) due to a high prevalence (67%). The combined adjusted PAR for the 14 risk factors associated with recurrent wheezing was 49% (95% CI 46, 52%). CONCLUSIONS: In moderate preterm infants, day-care attendance has the largest PAR for recurrent wheezing. Trial evidence is needed to determine the potential benefit of delayed day-care attendance in this population.

Childhood wheezing, asthma, allergy, atopy, and lung function: different socioeconomic patterns for different phenotypes.

Identifying preventable exposures that lead to asthma and associated allergies has proved challenging, partly because of the difficulty in differentiating phenotypes that define homogeneous disease groups. Understanding the socioeconomic patterns of disease phenotypes can help distinguish which exposures are preventable. In the present study, we identified disease phenotypes that are susceptible to socioeconomic variation, and we determined which life-course exposures were associated with these inequalities in a contemporary birth cohort. Participants included children from the Avon Longitudinal Study of Parents and Children, a population-based birth cohort in England, who were born in 1991 and 1992 and attended the clinic at 7-8 years of age (n = 6,378). Disease phenotypes included asthma, atopy, wheezing, altered lung function, and bronchial reactivity phenotypes. Combining atopy with a diagnosis of asthma from a doctor captured the greatest socioeconomic variation, including opposing patterns between phenotype groups: Children with a low socioeconomic position (SEP) had more asthma alone (adjusted multinomial odds ratio = 1.50, 95% confidence interval: 1.21, 1.87) but less atopy alone (adjusted multinomial odds ratio = 0.80, 95% confidence interval: 0.66, 0.98) than did children with high SEP. Adjustment for maternal exposure to tobacco smoke during pregnancy and childhood exposure to tobacco smoke reduced the odds of asthma alone in children with a low SEP. Current inequalities among children who have asthma but not atopy can be prevented by eliminating exposure to tobacco smoke. Other disease phenotypes were not socially patterned or had SEP patterns that were not related to smoke exposure.

Diagnosis, management, and prognosis of preschool wheeze.

Preschool children (ie, those aged 5 years or younger) with wheeze consume a disproportionately high amount of health-care resources compared with older children and adults with wheeze or asthma, representing a diagnostic challenge. Although several phenotype classifications have been described, none have been validated to identify individuals responding to specific therapeutic approaches. Several risk factors related to genetic, prenatal, and postnatal environment are associated with preschool wheezing. Findings from several cohort studies have shown that preschool children with wheeze have deficits in lung function at 6 years of age that persisted until early and middle adulthood, suggesting increased susceptibility in the first years of life that might lead to persistent sequelae. Daily inhaled corticosteroids seem to be the most effective therapy for recurrent wheezing in trials of children with interim symptoms or atopy; intermittent high-dose inhaled corticosteroids are effective in moderate-to-severe viral-induced wheezing without interim symptoms. The role of leukotriene receptor antagonist is less clear. Interventions to modify the short-term and long-term outcomes of preschool wheeze should be a research priority.

A novel scoring system to distinguish vocal cord dysfunction from asthma.

BACKGROUND: Vocal cord dysfunction is often misdiagnosed and mistreated as asthma, which can lead to increased and unnecessary medication use and increased health care utilization. OBJECTIVE: To develop a valid scoring index that could help distinguish vocal cord dysfunction from asthma. METHODS: We compared the demographics, comorbidities, clinical symptoms, and symptom triggers of subjects with vocal cord dysfunction (n = 89) and those with asthma (n = 59). By using multivariable logistic regression, we identified distinguishing features associated with vocal cord dysfunction, which were weighted and used to generate a novel score. The scoring index also was tested in an independent sample with documented vocal cord dysfunction (n = 72). RESULTS: We identified symptoms of throat tightness and dysphonia, the absence of wheezing, and the presence of odors as a symptom trigger as key features of vocal cord dysfunction that distinguish it from asthma. We developed a weighted index based on these characteristics, the Pittsburgh Vocal Cord Dysfunction Index. By using a cutoff of ≥4, this index had good sensitivity (0.83) and specificity (0.95) for the diagnosis of vocal cord dysfunction. The scoring index also performed reasonably well in the independent convenience sample with laryngoscopy-proven vocal cord dysfunction and accurately made the diagnosis in 77.8% of subjects. CONCLUSION: The Pittsburgh Vocal Cord Dysfunction Index is proposed as a simple, valid, and easy-to-use tool for diagnosing vocal cord dysfunction. If confirmed by a prospective evaluation in broader use, it may have significant clinical utility by facilitating a timely and accurate diagnosis of vocal cord dysfunction, thereby preventing misdiagnosis and mistreatment as asthma. Future prospective validation studies will need to be performed.

The acoustic reflection method for the assessment of paediatric upper airways.

The acoustic reflection method (ARM) is based on the analysis of the reflection of an acoustic wave in the airway, allowing the calculation of its longitudinal cross-sectional area profile and airway resistance. The ARM represents a simple, quick and totally non invasive tool for the investigation of the upper airways, requiring minimal cooperation, which makes this technique particularly suitable for children. Normal values of the minimal cross sectional area of the upper airways in children have been recently published. The ARM has shown its utility in the investigation of the nasal cavity in healthy and diseased children and of the upper airways in children with various diseases such as mucopolysaccharidosis and cystic fibrosis. This simple, rapid, and inexpensive technique seems promising for the non-invasive investigation of the whole upper airway during wakefulness in children, both in health and disease, and may constitute a complementary or alternative method to explore and follow children with anomalies of the upper airways.

Bayesian mixed hidden Markov models: a multi-level approach to modeling categorical outcomes with differential misclassification.

Questionnaire-based health status outcomes are often prone to misclassification. When studying the effect of risk factors on such outcomes, ignoring any potential misclassification may lead to biased effect estimates. Analytical challenges posed by these misclassified outcomes are further complicated when simultaneously exploring factors for both the misclassification and health processes in a multi-level setting. To address these challenges, we propose a fully Bayesian mixed hidden Markov model (BMHMM) for handling differential misclassification in categorical outcomes in a multi-level setting. The BMHMM generalizes the traditional hidden Markov model (HMM) by introducing random effects into three sets of HMM parameters for joint estimation of the prevalence, transition, and misclassification probabilities. This formulation not only allows joint estimation of all three sets of parameters but also accounts for cluster-level heterogeneity based on a multi-level model structure. Using this novel approach, both the true health status prevalence and the transition probabilities between the health states during follow-up are modeled as functions of covariates. The observed, possibly misclassified, health states are related to the true, but unobserved, health states and covariates. Results from simulation studies are presented to validate the estimation procedure, to show the computational efficiency due to the Bayesian approach and also to illustrate the gains from the proposed method compared to existing methods that ignore outcome misclassification and cluster-level heterogeneity. We apply the proposed method to examine the risk factors for both asthma transition and misclassification in the Southern California Children's Health Study.

Sleep-quality assessment from full night audio recordings of sleep apnea patients.

In this work, a novel system (method) for sleep quality analysis is proposed. Its purpose is to assist an alternative non-contact method for detecting and diagnosing sleep related disorders based on acoustic signal processing. In this work, audio signals of 145 patients with obstructive sleep apnea were recorded (more than 1000 hours) in a sleep laboratory and analyzed. The method is based on the assumption that during sleep the respiratory efforts are more periodically patterned and consistent relative to a waking state; furthermore, the sound intensity of those efforts is higher, making the pattern more noticeable relative to the background noise level. The system was trained on 50 subjects and validated on 95 subjects. The system accuracy for detecting sleep/wake state is 82.1% (epoch by epoch), resulting in 3.9% error (difference) in detecting sleep latency, 11.4% error in estimating total sleep time, and 11.4% error in estimating sleep efficiency.

Assessment of obstructive sleep apnea and its severity during wakefulness.

In this article, a novel technique for assessment of obstructive sleep apnea (OSA) during wakefulness is proposed; the technique is based on tracheal breath sound analysis of normal breathing in upright sitting and supine body positions. We recorded tracheal breath sounds of 17 non-apneic individuals and 35 people with various degrees of severity of OSA in supine and upright sitting positions during both nose and mouth breathing at medium flow rate. We calculated the power spectrum, Kurtosis, and Katz fractal dimensions of the recorded signals and used the one-way analysis of variance to select the features, which were statistically significant between the groups. Then, the maximum relevancy minimum redundancy method was used to reduce the number of characteristic features to two. Using the best two selected features, we classified the participant into severe OSA and non-OSA groups as well as non-OSA or mild vs. moderate and severe OSA groups; the results showed more than 91 and 83% accuracy; 85 and 81% specificity; 92 and 95% sensitivity, for the two types of classification, respectively. The results are encouraging for identifying people with OSA and also prediction of OSA severity. Once verified on a larger population, the proposed method offers a simple and non-invasive screening tool for prediction of OSA during wakefulness.

Antibiotic prescribing pattern in paediatric in patients with first time wheezing.

BACKGROUND: Acute wheezers for the first time in life are an important target group for efforts aimed at reducing unnecessary antibiotic use. OBJECTIVE: To evaluate the effect of clinical, laboratory and radiological data on the decision to prescribe antibiotics to paediatric patients with first time wheezing as well as to seek criteria that would justify antibiotic use. METHODS: A prospective study was made of 47 previous healthy children admitted to our hospital with first time wheezing in life between October 2008- March 2009. All the patients were treated as per the treating unit's protocol with oxygen, bronchodilators with or without antibiotics. The cases were analyzed after discharge and the characteristics of those treated with antibiotics (n = 23) were compared with those who were not (n = 24) and analyzed statistically to find the predictors for antibiotic usage. RESULTS: The mean age of the study groups was 5.8 (+/- 5.1) months. Among the clinical and investigational parameters, presence of predominant crackles and abnormalities on radiograph were the major determinants for antibiotic usage. There were no significant differences in final outcome between these groups. CONCLUSION: Antibiotic usage in first time wheezers is still quite prevalent. Presence of crackles and radiological abnormalities often prompt the usage of antibiotics in such cases.

Assessment of multichannel lung sounds parameterization for two-class classification in interstitial lung disease patients.

This work deals with the assessment of different parameterization techniques for lung sounds (LS) acquired on the whole posterior thoracic surface for normal versus abnormal LS classification. Besides the conventional technique of power spectral density (PSD), the eigenvalues of the covariance matrix and both the univariate autoregressive (UAR) and the multivariate autoregressive models (MAR) were applied for constructing feature vectors as input to a supervised neural network (SNN). The results showed the effectiveness of the UAR modeling for multichannel LS parameterization, using new data, with classification accuracy of 75% and 93% for healthy subjects and patients, respectively.

Assessment and validation of bronchodilation using the interrupter technique in preschool children.

OBJECTIVE: To determine and validate a cut-off value for bronchodilation using the interrupter resistance (Rint) in preschool children. PATIENTS AND METHODS: Rint was measured in 60 healthy children (age range 2.7-6.4 years) before and after salbutamol inhalation (200 microg). Four potential methods for assessing BDR were evaluated: percent change from baseline, percent change of predicted values, absolute change in Rint, and change in Z-score. These cut-off values, determined as the fifth percentile of the healthy group, were applied to children referred for the assessment of recurrent wheezing, classified on the basis of acute symptoms and/or abnormal chest examination into symptomatic (n = 60, age range 2.9-6.1 years) and asymptomatic (n = 60, age range 2.5-5.7 years) groups. RESULTS: The cut-off values for bronchodilation calculated in healthy children were: -32% baseline; -33% predicted; -0.26 kPa L(-1) sec; and -1.25 Z-scores. Assessing BDR in children with a history of wheezing by either a decrease in absolute Rint or a decrease in Z-score gave sensitivity, specificity, negative predictive value, and positive predictive value all >80% for detecting children with current respiratory symptoms. CONCLUSIONS: Both a decrease in Rint > or =0.26 kPa L(-1) sec and a decrease in Z-score of > or =1.25 are appropriate for assessing BDR in preschool children with a history of recurrent wheezing. As Z-score is a more general solution, we recommend using a change in Z-score to determine BDR in preschool children. Further longitudinal studies will be required to determine the clinical utility of measuring BDR in managing lung disease in such children.

Automatic detection system for cough sounds as a symptom of abnormal health condition.

The problem of attending to the health of the aged who live alone has became an important issue in developed countries. One way of solving the problem is to check their health condition by a remote-monitoring technique and support them with well-timed treatment. The purpose of this study is to develop an automatic system that can monitor a health condition in real time using acoustical information and detect an abnormal symptom. In this study, cough sound was chosen as a representative acoustical symptom of abnormal health conditions. For the development of the system distinguishing a cough sound from other environmental sounds, a hybrid model was proposed that consists of an artificial neural network (ANN) model and a hidden Markov model (HMM). The ANN model used energy cepstral coefficients obtained by filter banks based on human auditory characteristics as input parameters representing a spectral feature of a sound signal. Subsequently, an output of this ANN model and a filtered envelope of the signal were used for making an input sequence for the HMM that deals with the temporal variation of the sound signal. Compared with the conventional HMM using Mel-frequency cepstral coefficients, the proposed hybrid model improved recognition rates on low SNR from 5 dB down to -10 dB. Finally, a preliminary prototype of the automatic detection system was simply illustrated.