[ad_1]
MIT has invented a tool that uses artificial intelligence to identify people with asymptomatic COVID-19 infections. Asymptomatic people are the most difficult to detect and can transmit the infection without knowing they have it. Since they are asymptomatic, they are unlikely to be tested and continue their daily routine infecting others without knowing it.
MIT research found that despite being asymptomatic, some changes accompany COVID-19 infections. The researchers found that asymptomatic people could still differ from healthy people in the way they cough. While the changes are not detectable with the human ear, the AI can discern them by analyzing the recorded coughs.
The system takes a recording of a forced cough that people voluntarily submit via web browsers, cell phones, or laptops. The team trained their AI using tens of thousands of samples using both coughs and spoken words. When cough recordings were sent to the AI, 98.5 percent of coughs from people confirmed with COVID-19 infections were identified.
It was able to identify 100 percent of coughs from asymptomatic people who reported no symptoms but tested positive for the virus. Currently, the team is incorporating their artificial intelligence model into an application seeking FDA approval. If approved, the app would be a free and easy screening tool to identify those who are likely to have asymptomatic COVID-19.
MIT says that by using the app, users can test themselves daily for information on whether they could be infected and whether they should confirm it with a formal test. There is no indication of when or if the MIT system will receive FDA approval. Presumably, the FDA will want to speed up the application approval process to help slow the spread of COVID-19.
