scholarly journals Deep Neural Network-Based Respiratory Pathology Classification Using Cough Sounds

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5555
Author(s):  
B T Balamurali ◽  
Hwan Ing Hee ◽  
Saumitra Kapoor ◽  
Oon Hoe Teoh ◽  
Sung Shin Teng ◽  
...  

Intelligent systems are transforming the world, as well as our healthcare system. We propose a deep learning-based cough sound classification model that can distinguish between children with healthy versus pathological coughs such as asthma, upper respiratory tract infection (URTI), and lower respiratory tract infection (LRTI). To train a deep neural network model, we collected a new dataset of cough sounds, labelled with a clinician’s diagnosis. The chosen model is a bidirectional long–short-term memory network (BiLSTM) based on Mel-Frequency Cepstral Coefficients (MFCCs) features. The resulting trained model when trained for classifying two classes of coughs—healthy or pathology (in general or belonging to a specific respiratory pathology)—reaches accuracy exceeding 84% when classifying the cough to the label provided by the physicians’ diagnosis. To classify the subject’s respiratory pathology condition, results of multiple cough epochs per subject were combined. The resulting prediction accuracy exceeds 91% for all three respiratory pathologies. However, when the model is trained to classify and discriminate among four classes of coughs, overall accuracy dropped: one class of pathological coughs is often misclassified as the other. However, if one considers the healthy cough classified as healthy and pathological cough classified to have some kind of pathology, then the overall accuracy of the four-class model is above 84%. A longitudinal study of MFCC feature space when comparing pathological and recovered coughs collected from the same subjects revealed the fact that pathological coughs, irrespective of the underlying conditions, occupy the same feature space making it harder to differentiate only using MFCC features.

Author(s):  
Balamurali B T ◽  
Hwan Ing Hee ◽  
Saumitra Kapoor ◽  
Oon Hoe Teoh ◽  
Sung Shin Teng ◽  
...  

Intelligent systems are transforming the world, as well as our healthcare system. We propose a deep learning-based cough sound classification model that can distinguish between children with healthy versus pathological coughs such as asthma, upper respiratory tract infection (URTI), and lower respiratory tract infection (LRTI). In order to train a deep neural network model, we collected a new dataset of cough sounds, labelled with clinician's diagnosis. The chosen model is a bidirectional long-short term memory network (BiLSTM) based on Mel Frequency Cepstral Coefficients (MFCCs) features. The resulting trained model when trained for classifying two classes of coughs -- healthy or pathology (in general or belonging to a specific respiratory pathology), reaches accuracy exceeding 84\% when classifying cough to the label provided by the physicians' diagnosis. In order to classify subject's respiratory pathology condition, results of multiple cough epochs per subject were combined. The resulting prediction accuracy exceeds 91\% for all three respiratory pathologies. However, when the model is trained to classify and discriminate among the four classes of coughs, overall accuracy dropped: one class of pathological coughs are often misclassified as other. However, if one consider the healthy cough classified as healthy and pathological cough classified to have some kind of pathologies, then the overall accuracy of four class model is above 84\%. A longitudinal study of MFCC feature space when comparing pathologicial and recovered coughs collected from the same subjects revealed the fact that pathological cough irrespective of the underlying conditions occupy the same feature space making it harder to differentiate only using MFCC features.


2021 ◽  
Vol 22 (15) ◽  
pp. 7868
Author(s):  
Su Young Jung ◽  
Dokyoung Kim ◽  
Dong Choon Park ◽  
Sung Soo Kim ◽  
Tong In Oh ◽  
...  

Otitis media is mainly caused by upper respiratory tract infection and eustachian tube dysfunction. If external upper respiratory tract infection is not detected early in the middle ear, or an appropriate immune response does not occur, otitis media can become a chronic state or complications may occur. Therefore, given the important role of Toll-like receptors (TLRs) in the early response to external antigens, we surveyed the role of TLRs in otitis media. To summarize the role of TLR in otitis media, we reviewed articles on the expression of TLRs in acute otitis media (AOM), otitis media with effusion (OME), chronic otitis media (COM) with cholesteatoma, and COM without cholesteatoma. Many studies showed that TLRs 1–10 are expressed in AOM, OME, COM with cholesteatoma, and COM without cholesteatoma. TLR expression in the normal middle ear mucosa is absent or weak, but is increased in inflammatory fluid of AOM, effusion of OME, and granulation tissue and cholesteatoma of COM. In addition, TLRs show increased or decreased expression depending on the presence or absence of bacteria, recurrence of disease, tissue type, and repeated surgery. In conclusion, expression of TLRs is associated with otitis media. Inappropriate TLR expression, or delayed or absent induction, are associated with the occurrence, recurrence, chronicization, and complications of otitis media. Therefore, TLRs are very important in otitis media and closely related to its etiology.


2014 ◽  
Vol 32 (6) ◽  
pp. 509-511 ◽  
Author(s):  
SeungWon Kwon ◽  
KyoungHo Shin ◽  
WooSang Jung ◽  
SangKwan Moon ◽  
KiHo Cho

We report the cases of eight military patients with fever (≥38°C) induced by viral upper respiratory tract infection (URTI) who requested treatment with acupuncture in the military medical service room. All patients were treated immediately after diagnosis with classical acupuncture (GV14, GB20, TE8 points) and a new type of acupuncture, equilibrium acupuncture ( Feibing and Ganmao points). After one treatment session (20 min), reduction of body temperature was confirmed in all patients. Accompanying symptoms such as headache, myalgia and nasal obstruction also showed a tendency to decrease. Within 3 days of treatment, six of the eight patients had recovered from the URTI. No adverse effects of acupuncture treatment were reported.


Sign in / Sign up

Export Citation Format

Share Document