An app can distinguish asymptomatic patients from a healthy person based...

Asymptomatic Patients are part of the population that often goes unnoticed because they even have a coronavirus. By doing this, they can unwittingly pass the virus on to many other people, most of whom can develop serious complications from the virus. A recent development by researchers has now revealed a special model that can identify and distinguish between symptomatic and asymptomatic patients by simply recording their coughs.

The novel application works with an artificial intelligence model and can be used on a smartphone. The app was developed by researchers at the Massachusetts Institute of Technology (MIT) in the USA and can differentiate between healthy people and asymptomatic patients simply by recording cough patterns.

Although such differences are impossible for the human ear to hear and understand, the artificial intelligence model can pick up on these differences and distinguish between them.

The paper describing the development will be published in the IEEE Journal of Engineering in Medicine and Biology. The team describes it as an AI model that can use self-induced cough records to tell the difference between healthy people and people with the virus.

Also read: The “brain fog” among COVID-19 survivors is a sign of post-traumatic stress disorder (PTSD).

These recordings came from various volunteers who came through web browsers and devices such as laptops and cell phones, the study researchers explain.

The researchers then taught the model’s latest record of cough. It accurately identified 98.5% of coughs from people diagnosed with COVID-19.

This also includes 100% of the cough records from asymptomatic individuals. While these people have no symptoms of the deadly virus, they test positive for the virus and have it in their bodies, according to study members.

Currently, the team is spending time integrating this useful model into a neat, easy-to-use application for smartphones. When approved, the tool can be used on a large scale and is not only free to use, but also an option that is non-invasive and convenient for a pre-screening tool. This can then be used to identify those who are most likely to be asymptomatic with COVID-19, the researchers say.

Brian Subirana is a scientist in a laboratory at MIT. He believes this tool, as a diagnostic tool, could go a long way in reducing the rate of infection for the virus if people used it every time before entering a classroom, restaurant, or even factory.

In this way, he means that people can understand whether they are symptomless or not and pose a risk to those around you. Once diagnosed, a person can effectively self-isolate and reduce the main damage they can cause when moving in densely populated areas.

Before the coronavirus pandemic rocked the world, research groups were successful in training algorithms to collect cough records to diagnose conditions like asthma and pneumonia.

The research team has taken more than 70,000 recordings, each of which contains many coughs. This is up to 200,000 samples of forced cough. According to Subirana, this could be the largest data set for cough research to date.

In conclusion, Subirana says that research believes that the way we sound might change with the coronavirus infection, even if the person in question has no symptoms at all. This research offers hope for a non-invasive and more accessible way of diagnosing a virus that has changed the way of life for the entire world we live in.