For people who are in an unresponsive state, doctors use subjective visual examinations to gauge a person’s level of consciousness. However, they may miss small subtle cues. A new study found that artificial intelligence may help detect these changes. A team of researchers recorded videos of 37 patients with recent brain injuries who outwardly appeared to be in a coma. The team tracked the facial movements with extraordinary detail after each was given a command such as “open your eyes” or “stick out your tongue.” The AI tool spotted eye and mouth movements respectively 4.1 and 8.3 days before clinicians spotted these signs.

Why this matters: “What we found was: patients develop [small] movements before going to more obvious movements,” says Sima Mofakham, a computational neuroscientist at Stony Brook University and senior author of the new study. The results suggest that, in some cases, people are conscious days before doctors notice. Patients with larger and more frequent facial movements also had better clinical outcomes, which shows that the technology may help predict prognoses.

What the experts say: The ability to detect consciousness earlier is clinically meaningful, says Jan Claassen, a neurologist at Columbia University, who wasn’t involved in the new research. Signs of consciousness can provide another layer of information for doctors and family members choosing between a range of treatments, from palliative care to more aggressive therapies. Earlier detection could also allow care teams to start rehabilitation programs used to improve patients’ motor skills sooner. —Andrea Tamayo, newsletter writer

Researchers found that telling voters before voting about the measures that make voting secure were effective in countering misinformation about voting. The scientists call this “prebunking” (a play on debunking) and in experiments with thousands of participants in the U.S. and Brazil, it worked to counter misinformation about voter fraud. Researchers explained to their participants details on exactly how voting security is ensured at the polls and in the counting of votes. In one iteration of the experiment, beliefs in false statements about voting were chopped nearly in half. This tactic was particularly effective among those most skeptical of election security and had a lasting effect.

Why this matters: Claims of faked election results figured into the January 6, 2021, mob assault on the U.S. Capitol and President Donald Trump has made false claims about mail-in ballots and voting machines. Combating election falsehoods ahead of voting may help fortify voter confidence. The reality is that safeguards keep fake ballots from being counted. Election officials regularly update voter lists. And voting machine software undergoes rigorous testing.

What the experts say: “The best way to help guard people against misinformation is to provide accurate countervailing information,” says Gordon Pennycook, a professor of psychology at Cornell University. Although this is a strong research result, experts say, people are immersed in misinformation from podcasts and television personalities (and the U.S. president). “Can just one message in a sea of misinformation offset a diet of misinformation on social media,” and cable television, asks communications scholar Nathan Walter of Northwestern University, who was not part of the study. “Eating one protein shake doesn’t counter all the cheeseburgers you had.”