Unqualified use of the word "predicts" is a little bit of a stretch in this editorialized title.
The study doesn't predict suicide attempts out of some type of biometric or otherwise observable data or surveillance information, it's predicting it from a self-survey. The actual journal article title tells the story much better:
"Using smartphone surveys to predict next-week suicide attempts"
The study doesn't predict suicide attempts out of some type of biometric or otherwise observable data or surveillance information, it's predicting it from a self-survey. The actual journal article title tells the story much better:
"Using smartphone surveys to predict next-week suicide attempts"
https://psycnet.apa.org/doiLanding?doi=10.1037%2Fabn0001117