Research Horizons


How Artificial Intelligence Could Help Reduce Risk of School Violence

After making significant progress using natural language processing to predict a person’s risk of suicide, similar artificial intelligence technology also is showing promise at predicting whether students will become violent at school.

Findings appeared online April 28, 2020, in the International Journal of Medical Informatics. The study was led by Yizhao Ni, PhD, Division of Biomedical Informatics, and Drew Barzman, MD, Director of the Child and Adolescent Forensic Psychiatry Service at Cincinnati Children’s.

The technology detects warning signs that could help experts intervene once the system is more fully developed, the co-authors say.

“Our study demonstrates that overall, our AI system matches the clinical judgments and accuracy of psychiatrists 94 percent of the time. It has tremendous potential to help address youth violence at school and eventually other mental health conditions.”


See past coverage of natural language processing advances at Cincinnati Children’s

Pilot Study Validates AI to Help Predict School Violence

School Violence Research Featured in Cincinnati Magazine

The Language of Suicide: New research analyzes suicide notes for clues to self-destructive mindsets

Using a Patient’s Own Words Machine Learning Automatically Identifies Suicidal Behavior

Pestian Joins Oak Ridge National Laboratory as Joint Faculty