Suicide is a national and international public health priority, and suicidal behavior among children is common, costly, and preventable. Systematic, accurate, and equitable detection of children who present to medical care for suicidal thoughts and behaviors is challenging. In turn, suicide and self-harm prediction models and evidence-based personalized decision support tools to reduce suicide risk hold promise for prevention efforts, but are seldom adopted in clinical practice for children. This talk highlights new and innovative research applying computational methods, such as machine learning, to medical record datasets to advance the accuracy and equity of detecting children experiencing suicidal thoughts and behaviors. The talk asks and answers questions such as: Who is being missed? and What does improved detection mean for prediction and prevention of youth suicide?
Please use #BBRFWebinar when sharing or posting about our Meet the Scientist Webinars on social media.