App Uses Machine Learning to Detect Suicide Risk

High school senior Siddhu Pachipala uses teens’ digital footprints to detect early warning signs of suicide. The app uses artificial intelligence to comb data and look for risk factors.

Often it’s hard to spot early warning signs of suicide, including persistent feelings of hopelessness, changes in mood, and sleep patterns. In an interview with NPR, Pachipala said the goal is to get people help before it’s too late.

Judges from the Regeneron Science Talent Search found that Pachipala’s work “suggests that the semantics in an individual’s writing could be correlated with their psychological health and risk of suicide.”

Although the app can help many people, some data privacy experts are concerned about how machine learning will work with the data.

Matt Nock, a professor of psychology at Harvard University, who studies self-harm in young people, told NPR that he used electronic health records and AI to identify suicide risk. A lot of the predictions were false positives. “Is there a cost there?” Nock said. “Does it do harm to tell someone that they’re at risk of suicide when really they’re not?”

Researchers acknowledge that it is crucial to do everything possible to prevent people from harming themselves. However, AI-backed tools can cause more harm than good and lead to punishment instead of help.

Still, suicide is the second leading cause of death for people ages 10 to 24 in the U.S.; finding help is a top priority for medical professionals.

“Technology is going to help us, we hope, get better at knowing who is at risk and knowing when,” Nock said. “But people want to see humans; they want to talk to humans.”

SuiSensor offers a self-assessment for suicide risk that then connects users with advocates and mental health professionals.

“I think we don’t do that enough: trying to address [suicide intervention] from an innovation perspective,” Pachipala said. “I think that we’ve stuck to the status quo for a long time.”

Diall, a mental-health awareness and content app, is also trying to revolutionize how we think about mental health. The app offers tools and resources to help people. Diall is working to create an inclusive community with mental health resources, free of stigma and open to everyone. Like Pachipala, the founders of Diall realized they needed to create something accessible for everyone to help more people.

Psychologist Nathan Demers told NPR that personalized tools could help people who do not see the early warning signs. Demers says that taking this tool could help the public and become a key innovation for mental health self-awareness.

Psychologist Nathan Demers told NPR that personalized tools could help people who do not see the early warning signs. Demers says that taking this tool could help the public and become a key innovation for mental health self-awareness.

• Americans Face an Epidemic of Loneliness
• Senators Propose Social Media Ban for Kids
• What Is ChatGPT and Is It Safe for Kids?
• Is TikTok Safe? Here's what you need to know
• How to Keep Your Family Safe in Any Situation