MIT is looking into cough to diagnose COVID-19

Can You Diagnose COVID-19 From a Cough?

As we and many others in the field have recorded, COVID-19 poses a more serious risk to people with underlying health conditions and chronic illnesses, such as diabetes. The numbers are alarming – a Lancet Diabetes & Endocrinology study mining 61 million medical records in the United Kingdom reported that 30% of COVID-19 deaths occurred among people with diabetes.

Prevention and good diabetes care are the leading tactics to protect people with diabetes by controlling their blood sugar through diet, exercise, monitoring, and medication. But many don’t feel safe exercising outdoors although they know staying active and maintaining good blood sugar levels may be their best defense against COVID-19. Getting the virus under control is essential for them as it is for all of us.

Some very good news came out this week with the announcement of a vaccine candidate developed by Pfizer and BioNTech that is more than 90% effective in preventing COVID-19. The vaccine has been tested on 43,500 people in six countries and no serious safety concerns have been raised. It’s expected that up to 50 million doses of the vaccine will be produced by the end of the year and up to 1.3 billion doses in 2021. There are still questions to be answered, e.g. how long does immunity last, and how to deal with the significant manufacturing and logistical challenges in immunizing huge numbers of people around the world? But the announcement of the new vaccine has been warmly welcomed around the world with some suggesting life could be back to normal by spring. Let’s hope!

Know your risk of diabetic eye disease

Click here to download the RetinaRisk app now!

Another piece of exciting – if lower profile – news in the last few weeks is innovative technology developed at MIT that could accurately diagnose COVID 19 from your cough. This AI model distinguishes asymptomatic people who are infected with COVID-19 from healthy individuals through forced-cough recordings, which people voluntarily submit through cellphones and laptops.

The researchers trained the model on tens of thousands of samples of coughs, as well as spoken words. When they fed the model new cough recordings, it accurately identified 98.5 percent of coughs from people who were confirmed to have COVID-19, including 100 percent of coughs from asymptomatic people who reported they did not have symptoms but had tested positive for the virus.

The MIT team is working on incorporating the model into a user-friendly app, which if FDA-approved and adopted on a large scale, could be a free, convenient, non-invasive prescreening tool to identify people who are likely to be asymptomatic for COVID-19. A user could log in daily, cough into their phone, and instantly get information on whether they might be infected and therefore should confirm with a formal test. This diagnostic tool could diminish the spread of the pandemic if everyone uses it before going to a classroom, a factory, shop or a restaurant. The research team envisions their AI tool as a low-cost COVID-19 pre-screener that could be deployed in settings where comprehensive diagnostic testing is unavailable or unable to scale for entire populations. So, until the new vaccine is readily available worldwide, this novel technology will complement ongoing efforts to halt the spread of a still vicious Coronavirus.

Similar Posts