The purpose of the proposed work is to harness cutting-edge machine learning methods to optimize prediction of future firearm violence in youth ages 18-24 so that prevention resources can be allocated efficiently.

Firearm violence is a public health crisis in the United States, and new epidemiological data suggest we may have reached a new endemic level of firearm mortality in recent years. Youth are disproportionately affected by firearm violence, with those age 18-24 being demonstrably the highest risk group. This study will recruit 1,500 youth age 18-24 from urban emergency departments (EDs) in three broadly different locales-Flint, Philadelphia, and Seattle-and administer a baseline survey covering several domains of potential risk factors for future violence, and follow up with those youth at 6- and 12-months to ascertain the primary outcome-firearm violence involvement (as victim or perpetrator, including threats and sub-clinical injuries)-as well as the secondary outcomes: high-risk firearm behaviors, non-firearm violence, and violent injury. This work will generate new insights into the prediction of firearm violence, and will lay the ground for future research involving the development and testing of interventions for interpersonal firearm violence both by identifying potential high-leverage modifiable predictive factors, and by focusing on youth most in need of intervention.

Inclusion Criteria:

• Flint, Philadelphia, or Seattle Youth between the ages of 18-24 seeking care for any reason at Hurley Medical Center, the Hospital of University of Pennsylvania, Penn Presbyterian Medical Center, or Harborview Medical Center Emergency Department
• Can provide consent for the study

Exclusion Criteria:

• Do not understand English (<1% in prior work)
• Unable to provide consent due to mental status (e.g., alcohol intoxication, acute psychosis) or medical instability.
• ED visit requiring intensive psychosocial services (e.g., sexual assault, psychosis, active suicidal ideation, or child abuse)
• In active police custody/prisoners (as they cannot provide consent)

Youth aged 18-24 seeking care at the Emergency departments of Hurley Medical Center, the Hospital of University of Pennsylvania, Penn Presbyterian Medical Center, or Harborview Medical Center

After study completion, de-identified data will be curated and uploaded through the Inter-University Consortium for Political and Social Research (ICPSR) run through the University of Michigan. ICPSR stores, curates, and provides access to data generated through social research studies in service to open science, which acts in service to optimized data sharing, rigorous detailing of study methods and citations for measures, and ensuring long-term preservation of the study data. Through the data curation process, data are cleaned and standardized for use, and data documentation is rigorously developed so that data sets and the associated documentation can be understood at a basic by any potential users. The uploaded data will be de-identified to ensure no linkages to individual research participants and will exclude variables that could lead to deductive disclosure of the identity of any individual subjects.

After the study is completed, with no specified time for when sharing will end.

Registration with ICPSR and agreement to follow their rules and policies