*CONTENT WARNING: This article contains mentions of teenage suicidality.*
PROVO (ABC4) – Algorithm can be a scary word, as Brigham Young University computer science professor Quinn Snell admits.
The term, which has since reached a commonplace status in the modern-day lexicon, can conjure up imaginings of intrusive data analysis by artificial intelligence-led supercomputers that can understand human nature better than we as a species understand ourselves.
Snell acknowledges that the expression can be a scary one for many, but when used properly, algorithms can be used to create impactful and positive change in human society.
“When we say algorithm it can throw people off and make people nervous with artificial intelligence and all the hype surrounding that. But what we’re really talking about is, the data is telling us a story,” Quinn explains to ABC4.com. “And we’re just trying to figure out what that story is, and all the program does is try to figure out what that story is.”
The story that Snell and his university cohorts, Associate Dean of the College of Life Sciences Michael Barnes and Public Health professor Carl Hanson, are finding from the data on their latest research involving the use of computer learning; what are the key predictors of suicidal thoughts and behavior among adolescents.
Using a massive amount of data, including surveys from nearly 180,000 Utah junior high and high school students that consisted of 300-plus questions and included 8,000-plus bits of demographic details, the trio, along with help from Johns Hopkins and Harvard researchers, found an algorithm that could predict harmful thoughts and behavior with a stunning 91% accuracy rate.
Hanson feels the findings could and should make a major difference in potential measures and changes to public health that may ultimately be lifesaving.
“We feel there were certain things in our particular analysis that percolated to the top as most important risk factors for suicidal thought and behavior,” Hanson says, noting that suicide is the second leading cause of death for American adolescents. “And it’s those important things that we believe if addressed, could begin to address the ultimate problem of suicide in our communities with adolescents.”
Using the data, the team was able to nail down which risk factors were most impactful and predictable for suicidal thoughts and behavior. The factors could be boiled down into two broad ‘piles’ of interactions for young people; the connections between peers and the connections at home.
While two of the main risk factors that predicted harmful behavior with the highest measure of accuracy were arguments at home and being bullied at school, the most predictable factor of self-harming thoughts or behavior was online harassment or bullying.
Although the researchers were already aware of how dangerous those three environments could be, they were surprised at how severe and predictable online bullying, in-person bullying, and an argumentative home life would be in causing a teenager to consider or act by desperate measures.
“I think we’ve known for a long time, that there are negatives to the online world,” Barnes states. “And obviously, there are positives and there are some good things that are part of that but the ugly side comes out in moments like this. Our results definitely show kind of a glass half empty approach to the online world.”
It goes to show that relationship health, whether online, as many young people experience through social media and other platforms, maybe as important to a person’s overall well-being as any other aspect of health. Barnes imagines a future where data that illustrates that importance leads to an evolution in what healthcare can look like in the future.
“What would a health clinic look like if our focus is on relationships, and not just physiology? It is as important as, not just the food we eat, but the people that we have a chance to be able to enjoy food with,” he projects.
And even though technology may have opened the door to a major problem in the form of online harassment, innovations such as the computer science that found the algorithm may also lead a path to the solution. The convergence of public health, life sciences, and computer learning technologies such as the research that BYU has published relating to adolescent suicide prevention illustrate how different disciplines can work in harmony to create real-world solutions.
Computer science may have a large impact on a better understanding of how to heal and treat the humans living behind the screens and keyboards.
“We’d like to continue working with this data, not just on this, but also looking at other things with this data,” Snell says. “Computational health sciences is our focus those which is looking at ways that the computer science and data analysis can affect our public health.”
If you are contemplating suicide, help is available. The National Suicide Prevention Lifeline is available 24/7 at 1-800-273-8255 or online at suicidepreventionlifeline.org.