A diagnosis of respiratory disease is one of the most common outcomes of visiting a doctor. Respiratory diseases can be caused by inflammation, bacterial infection or viral infection of the respiratory tract. Diseases caused by inflammation include chronic conditions such as asthma, cystic fibrosis, COVID-19 and chronic obstructive pulmonary disease (COPD). Acute conditions, caused by either bacterial or viral infection, can affect either the upper or lower respiratory tract. Upper respiratory tract infections include common colds while lower respiratory tract infections include diseases such as pneumonia. Other infections include influenza, acute bronchitis, and bronchiolitis. Typically, doctors use stethoscopes to listen to the lungs as the first indication of a respiratory problem. The information available from these sounds is compromised as the sound has to first pass through the chest musculature which muffles high-pitched components of respiratory sounds. In contrast, the lungs are directly connected to the atmosphere during respiratory events such as coughs.
These audible sounds, used by our app, contain significantly more information than the sounds picked up by a stethoscope. Our approach is automated and removes the need for human interpretation of respiratory sounds. Plus, we can see lots of spreadable diseases nowadays such as HIV, Coronavirus, etc., so we have to track those patients to stop them from spreading
What it does
We provide a point of care diagnostic solutions for telehealth that are easily integrated into existing platforms. We are working on an app to provide instant clinical quality diagnostic tests and management tools directly to consumers and healthcare providers. Our app is based on the premise that cough and breathing sounds carry vital information on the state of the respiratory tract. It is created to diagnose and measure the severity of a wide range of chronic and acute diseases such as corona, pneumonia, asthma, bronchiolitis and chronic obstructive pulmonary disease (COPD) using this insight. These audible sounds, used by our app, contain significantly more information than the sounds picked up by a stethoscope. app approach is automated and removes the need for human interpretation of respiratory sounds.
The application works according to the following principle: to start the diagnosis, a user would have to fill out a particular form where he (she) describes his (her) symptoms (for example, headache, cough or fever) and plus the app will record his (her) cough sound and shortness of breath by the microphone of the smartphone. After taking all the data with user-selected symptoms, if the AI detects in a cough with some specific patterns inherent in a particular disease, it suggests the disease and searches for an available specialist of that disease. A nearby doctor to the user would get a notification about the case. after that app will provide a doctor with all the selected illness data and audio.(in its special app) The specialist will be overviewing patients' data and providing a patient with either treatment (like medicines) or a suggestion for a hospital. For the first case, the doctor provides the patient with a summary, recommendations, and medicines. In the second case, if the condition is serious of a patient , according to doctor AI will automatically call an ambulance and start tracking that person(in case of spreading disease).
The platform is based on sound alone and does not require physical contact with the patient. With modern smartphones integrating high-quality microphones, the platform can be delivered without the need for additional hardware
How we are going to build it?
We will take a machine learning approach to develop highly-accurate algorithms that diagnose disease from cough and respiratory sounds. Machine learning is an artificial intelligence technique that constructs algorithms with the ability to learn from data. In our approach, signatures that characterize the respiratory tract are extracted from cough and breathing sounds. We start by matching signatures in a large database of sound recordings with known clinical diagnoses. Our machine learning tools then find the optimum combination of these signatures to create an accurate diagnostic test or severity measure (this is called classification). Importantly, we believe these signatures are consistent across the population and not specific to an individual so there is no need for a personalized database Following are the steps app will take-: 1) Receive an audio signal from a microphone 2) Convert at least a portion of an audio signal into a frequency-based matrix representation by removing background sound 3) Transform the frequency-based matrix representation into a lesser dimensional matrix using projections from a set of basis vectors in a cough model 4) Classify audio signal based on a lesser dimensional matrix(predictions through Artificial intelligence and Machine Learning 5) Store features of the audio signal when the classification indicates a cough
Challenges we going to ran into
1) Money 2) Lots of tests need to be done for a perfect result 3) To minimize error as much as possible 4) Need more highly professional people to make the application user friendly 5) We have to work under quarantine conditions
What's next for FACO - Fight Against Corona
we making our detection algorithm perfect, so no error will be faced by doctors while listening, plus we will improve our UI/UX for user-friendly application
Porter P, Claxton S, Wood J, Peltonen V, Brisbane J, Purdie F, Smith C, Bear N, Abeyratne U, Diagnosis of Chronic Obstructive Pulmonary Disease (COPD) Exacerbations Using a Smartphone-Based, Cough Centred Algorithm, ERS 2019, October 1, 2019.
Porter P, Abeyratne U, Swarnkar V, Tan J, Ng T, Brisbane JM, Speldewinde D, Choveaux J, Sharan R, Kosasih K and Della, P, A prospective multicentre study testing the diagnostic accuracy of an automated cough sound centered analytic system for the identification of common respiratory disorders in children, Respiratory Research 20(81), 2019
Moschovis PP, Sampayo EM, Porter P, Abeyratne U, Doros G, Swarnkar V, Sharan R, Carl JC, A Cough Analysis Smartphone Application for Diagnosis of Acute Respiratory Illnesses in Children, ATS 2019, May 19, 2019.
Sharan RV, Abeyratne UR, Swarnkar VR, Porter P, Automatic croup diagnosis using cough sound recognition, IEEE Transactions on Biomedical Engineering 66(2), 2019.
Kosasih K, Abeyratne UR, Swarnkar V, Triasih R, Wavelet augmented cough analysis for rapid childhood pneumonia diagnosis, IEEE Transactions on Biomedical Engineering 62(4), 2015.
Amrulloh YA, Abeyratne UR, Swarnkar V, Triasih R, Setyati A, Automatic cough segmentation from non-contact sound recordings in pediatric wards, Biomedical Signal Processing and Control 21, 2015.
Swarnkar V, Abeyratne UR, Chang AB, Amrulloh YA, Setyati A, Triasih R, Automatic identification of wet and dry cough in pediatric patients with respiratory diseases, Annals Biomedical Engineering 41(5), 2013.
Abeyratne UR, Swarnkar V, Setyati A, Triasih R, Cough sound analysis can rapidly diagnose childhood pneumonia, Annals Biomedical Engineering 41(11), 2013.
android-studio, doubango, google-maps, java, machine-learning, mysql, numpy, pandas, python, pytorch, sklearn, sound-monitoring-and-matching-api, spyder, webrtc