High Schooler Uses AI to Detect Suicide Risk in Text-based Journals

Category Health

tldr #

A high schooler from The Woodlands College Park High School, has developed an AI based app that can detect signs of suicide risk with 98% accuracy and has won 9th place in the 81-year-old Regeneron Science Talent Search competition and winning a $50,000 prize. Despite experts arguing that chatbots are not the silver bullet for detection, they still see promise in the development. Pachipala believes it is time to revolutionize the way in which we approach suicide prevention.

content #

A senior at The Woodlands College Park High School, in a suburb outside Houston, U.S. has designed an app that uses AI to scan text for signs of suicide risk. Siddhu Pachipala believes it could be used to replace outdated methods of diagnosis.

This is according to a report by NPR published on Saturday.

"Our writing patterns can reflect what we're thinking, but it hasn't really been extended to this extent," he told the news outlet.

Pachipala won $50,000 for winning 9th place at the Regeneron Science Talent Search.

Pachipala’s app called SuiSensor is based on sound scientific principles. He used sample data from a medical study, based on journal entries by adults,to provide the foundation for his algorithm.

Now, he says his app predicted suicide risk with 98 percent accuracy and even generated a contact list of local clinicians.

Experts are already seeing promise in the development.

"Machine learning is helping us get better. As we get more and more data, we're able to improve the system," said Matt Nock, a professor of psychology at Harvard University, who studies self-harm in young people. "But chat bots aren't going to be the silver bullet." .

The study Pachipala used as the foundation of his algorithm had sample data from adults.

In addition, Colorado-based psychologist Nathaan Demers, who oversees mental health websites and apps, argued that there is a palace for personalized tools like Pachipala's to help fill a void where needed most.

"When you walk into CVS, there's that blood pressure cuff," Demers said. "And maybe that's the first time that someone realizes, 'Oh, I have high blood pressure. I had no idea.'" .

Entering a competition .

Matt Nock, a professor of psychology at Harvard University, believes machine learning can help improve systems for detecting suicide risk, but says chat bots are not the silver bullet.

To get more exposure the high schooler entered his invention into the Regeneron Science Talent Search, an 81-year-old national science and math competition.

The judges noted that, "His work suggests that the semantics in an individual's writing could be correlated with their psychological health and risk of suicide." .

As a result, he did rather well, placing ninth overall at the competition and winning a $50,000 prize.

Colorado-based psychologist Nathaan Demers believes there is still a need for personalized tools like Pachipala's particularly when detection for high blood pressure may be a substitute for identifying mental health risks.

Pachipala now says its time to revolutionize how we approach suicide prevention.

"I think we don't do that enough: trying to address [suicide intervention] from an innovation perspective," he told NPR. "I think that we've stuck to the status quo for a long time." .

hashtags #
worddensity #