According to the researchers, including those from the University of Science and Technology of China, current Covid-19 testing is a time-consuming laboratory procedure in addition to being uncomfortable.
In order to reduce transmission and mortality rates, they said healthcare systems need quick, inexpensive, and easy-to-use tests.
In the current study, published in the journal ACS Nano, the scientists developed a sensor based on special materials made of ultrasmall nanoparticles that could detect Covid-19 in exhaled breath, similar to a breathalyser test for alcohol intoxication.
The device is made of an array of gold nanoparticles linked to molecules that are sensitive to various volatile organic compounds (VOCs), which the researchers said are emitted by viruses and the cells they infect.
When the VOCs interact with the molecules on a nanoparticle, the electrical resistance of the material changes, the scientists added.
They trained the sensor in the device to detect Covid-19 by using machine learning (ML) to compare the pattern of electrical resistance signals obtained from the breath of 49 confirmed Covid-19 patients with those from 58 healthy controls and 33 non-Covid lung infection patients in Wuhan, China.
In this process, each study participant blew into the device for two to three seconds from a distance of one to two centimetres, the study noted.
When the ML application identified a potential Covid-19 signature, the team tested the accuracy of the device on a subset of the participants.
According to the researchers, the device showed 76 per cent accuracy in the test set in distinguishing Covid-19 cases from controls, and 95 per cent accuracy in discriminating people with the deadly disease from those with other lung infections.
They said the sensor could also distinguish, with 88 per cent accuracy, between sick and recovered Covid-19 patients.
Although the test needs to be validated in more patients, the scientists said if the method is confirmed to be effective, it could be useful for screening large populations to determine which individuals need further testing.