The U.S. Food and Drug Administration (FDA) has approved the first artificial intelligence device to detect latent signs of COVID-19 in asymptomatic vectors. This was reported by the press service of the agency.
The Tiger Tech COVID Plus Monitor is a dressing that uses light sensors and a small computer processor to check for biomarkers of the virus, such as hypercoagulation, a common COVID-19 anomaly that causes blood to clot more easily.
The device’s sensors collect pulsed blood flow signals over a period of three to five minutes. The processor then extracts key information from the measurements and runs them through a machine learning model.
Final results, including whether the test shows positive biomarkers, are presented in different colors.
Clinical trials of the effectiveness of the dressing were carried out by the developers in hospitals and schools. In a hospital setting, she correctly identified COVID-19 biomarkers in 98.6% of patients.
The device also identified the absence of control signs in people with a negative test – at the level of 94.5%. School trials have confirmed these results, according to the FDA.
The department stressed that the device is not intended to diagnose coronavirus infection and does not replace a conventional test. It will also not help treat symptomatic patients. The dressing should serve as an additional diagnostic measure, especially in potentially asymptomatic cases.
The developers of the device and the FDA are confident that the use of various methods in combination is useful in containing the spread of the virus in public places, including hospitals, schools, workplaces, parks, stadiums and airports.
Recall that in 2021, scientists presented a machine learning algorithm that with a probability of up to 90% can determine whether an uninfected person will die from COVID-19.
The researchers believe that their development will help hospitals effectively allocate resources to help patients with coronavirus infection.
In February, an artificial intelligence algorithm calculated that the number of cases of COVID-19 infection in the United States is three times more than official statistics say.
In March, British scientists created a COVID-19 screening tool that can diagnose the virus with 98% accuracy by analyzing the sound of a cough using AI.