A Harvard scientist wants to use smartphone data to understand suicides

13 years ago today, I woke up to the news that my oldest friend had died by suicide. I had gone back to my parents for the weekend to attend an anniversary dinner for our old Boy Scout troop — my friend and I had been in touch about our plans to go together. Needless to say, it turned into a much more somber evening than expected.

Today when I woke up, I saw a headline in The New York Times asking if smartphone data could be used to help predict suicides. Naturally, it piqued my interest. The article focused largely on the work of Matthew Hock, a Harvard psychologist who researches suicide. Hock acknowledges early on that the success rate in his field is … not particularly great. As he tells The Times:

With all due respect to people who've been doing this work for decades, for a century, we haven't learned a great deal about how to identify people at risk and how to intervene. The suicide rate now is the same it was literally 100 years ago. So just if we're being honest, we're not getting better.

So here's what they're trying to do, using biometric data mostly derived from FitBits or equivalents:

He spent his summer poring through the days and hours of 571 subjects who, after seeking medical care for suicidal thoughts, agreed to be tracked continuously for six months. While they were being tracked, two died by suicide and between 50 and 100 made attempts.

It is, Dr. Nock believes, the largest reservoir of information ever collected about the daily lives of people struggling with suicidal thoughts.

The team is most interested in the days preceding suicide attempts, which would allow time for intervention. Already, some signs have emerged: Although suicidal urges often do not change in the period before an attempt, the ability to resist those urges does seem to diminish. Something simple — sleep deprivation — seems to contribute to that.


The sensor reports that a patient's sleep is disturbed, she reports a low mood on questionnaires and GPS shows she is not leaving the house. But an accelerometer on her phone shows that she is moving around a lot, suggesting agitation. The algorithm flags the patient. A ping sounds on a dashboard. And, at just the right time, a clinician reaches out with a phone call or a message.

There are, of course, privacy concerns here, as with anything involving biometric and healthcare-related data collection; to the article's credit, it does a lot of work to acknowledge those concerns. It also highlights the experiences of one participant in the study, who was already at high risk of suicide, and said it was actually easier at some o her lower points to interact with an anonymous computer than with another human being. "Honestly, it makes me feel a little bit safer to know that somebody cares enough to read that data every day, you know?" she said. "To have somebody know how I feel, that takes some of the weight off."

I don't know what this study will lead to. But hopefully, at the very least, we can learn more about warning signs, and maybe save some other people from the pains of both death, and survival.

As ever, if you are struggling, and overwhelmed with suicidal thoughts, please, please call the National Suicide Prevention Lifeline at 1-800-273-TALK or the Samaritans at 877-870-HOPE. It's OK to have a hard time; it's OK to be down on yourself; just don't keep it in. Please. For your sake, and for mine.

Can smartphones help predict suicide? (Ellen Barry / The New York Times)

Image: Guillaume Paumier via Wikimedia Commons (CC BY-SA 3.0)

Full disclosure: I also write for Wirecutter, which is part of the New York Times Company, which owns the New York Times.