This face mask hunts for viruses in the air you breathe

Face masks are essential in combating the spread of respiratory viruses like Covid-19 and the flu — there’s no telling whether you’ll encounter these germs when you enter a crowded train or office.

That’s particularly concerning because the people around you may not show signs of illness. They could be experiencing, for example, pre-symptomatic or asymptomatic Covid-19. While we can continue to mask up throughout this pandemic (and during future ones), scientists may have found a way to make these tools even more effective.

What’s new — Scientists from Tongji University in China have created a face mask that can detect common respiratory viruses, like the flu and Covid-19, in aerosols or droplets in the air. It can notify users via their phones within 10 minutes if it finds pathogens floating around, according to a new study published in the journal Matter.

Watch out, germs — This nifty invention is helpful because respiratory pathogens that cause H1N1 influenza and Covid-19 travel through small droplets and aerosols when people cough, talk, and sneeze. The novel coronavirus can live in the air for hours, and H1N1 can sit on some surfaces for several days.

Because these germs tend to stick around, this mask could help people avoid pathogens before they can even get the chance to infect us.

To pick up on viruses in the air, the team designed a small sensor with synthetic molecules that can recognize a pathogen’s unique proteins. The sensor in the new mask can find proteins associated with Covid-19, H5N1 (bird flu), and H1N1. (Last year, another team designed a mask with a sensor that relies on CRISPR enzymes.)

When the molecules in the sensor bind to the pathogen proteins in the air, a transistor sends a signal to the wearer’s phone. Moving forward, the scientists aim to cut down the mask’s detection time and make it more sensitive to pathogens.

“Our mask would work really well in spaces with poor ventilation, such as elevators or enclosed rooms, where the risk of getting infected is high,” says study author Yin Fang, a material scientist at Shanghai Tongji University.

Read more about the study.

On the horizon ...

AI has infiltrated hospitals in recent years, and one of its recent applications is particularly mind-blowing: Scientists have developed a new AI system that can spot signs of pancreatic cancer missed by even the best radiologists, according to a new study published in the journal Radiology.

This matters because pancreatic cancer is one of the most deadly types of the disease (after lung and colorectal cancers). It will kill over 49,000 people in 2022, according to the American Cancer Society, and only about 20 percent of patients survive a year post-diagnosis.

Doctors have trouble finding tumors smaller than 2 centimeters, a critical point at which treatment can halt the deadly disease’s rapid progression. But that could change with the National Taiwan University team's new technology, which has outperformed experienced radiologists in testing.

It’s essentially a combination of five deep-learning models, which the researchers trained with over hundreds of examples of tumors.

It could be deployed across Taiwanese hospitals in less than a year, but it might take longer to be approved internationally. If all goes well, it could make a major difference in the U.S.

Read the full story to find out more.

Here’s what else we’re reading...

• Synthetic milk made from yeast could disrupt the dairy industry. The Guardian takes a sip.
• U.S. Customs stores duplicates of travelers’ phone and laptop contents without much oversight. These files include medical records, photos, and calendar appointments, according to Business Insider.
• A nonprofit launched the world’s largest public fossil fuel database. AP has the details.
• Nearly 20 percent of TikTok search results contain misinformation. Young viewers may encounter false claims on topics like abortion and the 2020 election, CNN Business reports.
• Electric vehicles could rescue the U.S. power grid. WIRED has the scoop.