Artificial Intelligence | News | Insights | AiThority
[bsfp-cryptocurrency style=”widget-18″ align=”marquee” columns=”6″ coins=”selected” coins-count=”6″ coins-selected=”BTC,ETH,XRP,LTC,EOS,ADA,XLM,NEO,LTC,EOS,XEM,DASH,USDT,BNB,QTUM,XVG,ONT,ZEC,STEEM” currency=”USD” title=”Cryptocurrency Widget” show_title=”0″ icon=”” scheme=”light” bs-show-desktop=”1″ bs-show-tablet=”1″ bs-show-phone=”1″ custom-css-class=”” custom-id=”” css=”.vc_custom_1523079266073{margin-bottom: 0px !important;padding-top: 0px !important;padding-bottom: 0px !important;}”]

New Artificial Intelligence Model Can Detect COVID-19 Through Cough

Without a promising vaccine candidate, the best way to handle the coronavirus is the early detection of symptomatic people and isolating them. However, the situation can become demanding if the patient carrying the virus does not show any symptoms or is an asymptomatic patient. But now, scientists have developed a new AI model that can detect the presence of the virus from a simple forced cough.

The new Artificial Intelligence model is created at the Massachusetts Institute of Technology lab. The scientists said that even though asymptomatic patients do not show any symptoms, their cough would still sound slightly different from a healthy person’s cough. The reason behind this was cited as per the impact of the virus on the patients’ lungs and vocal cords. The AI model can spot the difference in coughing that can’t be heard by the human ear. Researchers said that if the model can be deployed into smart devices, it can become a vital tool for early screening.

Recommended AI News: Signs $8 Million in Revenue Potential with New Client Wins in the Healthcare Industry

The published paper in the IEEE Journal of Engineering in Medicine and Biology highlights the practical use of the model in the daily screening of students, workers, or pool testing from alerts of outbreaks in groups. The model identified positive COVID-19 patients up to 98 percent and 100 percent of asymptomatic cases.

The research is based on the current developments advancing in Alzheimer’s detection through coughing and talking. The team, however, turned their heads with the spread of the novel coronavirus, after understanding how diseases can cause very small changes to speech and other noises.

Related Posts
1 of 20,749

Analysis performed for Alzheimer’s was restructured by a neural network known as ResNet50 for COVID-19. It was tested in a thousand hours of speech, then in a dataset of words spoken in varying emotional situations, and then in a database of coughs to see lung and respiratory changes.

Now, the researchers want to test the engine using a larger range of data to see whether other factors lead to a high detection score. When it hits the phone app stage, the privacy and approval from the FDA will probably be the concerns.

Recommended AI News: Health & Safety Institute Acquires Vado, Inc.

About 40% of COVID-19 patients are asymptomatic, according to the Centers for Disease Control and Prevention. However, the findings of the research indicate that only as few as 20 percent of patients never show signs or as many as 45 percent.

Although several coronaviral infections are so mild that no signs are created, still, these patients can give viruses to others. This asymptomatic method would cause the virus to spread easily through the communities prior to officials monitoring it without constant, universal testing of COVID-19. As a result, scientists around the world are engaged in creating innovative methods to find the virus until it is too late to avoid transmission.

Recommended AI News: QyPredict: An AI Prediction Technology For Optimizing Patient Selection In Clinical Trials To Be Presented At The CTAD Conference By QYNAPSE

Leave A Reply

Your email address will not be published.