Suicide Prevalence In The US: Identifying Risk Factors and Taking Data Driven Decisions

The Youth Risk Behavior Surveillance System (YRBSS) is a set of surveys that monitor priority health risk behaviors and experiences that contribute markedly to the leading causes of death, disability, and social problems among youth of grade 9 -12 in the United States. The surveys are administered every other year and it is maintained by the Centers for Disease Control and Prevention (CDC). A total of 107 questionnaire are asked. Some of the health-related behaviors and experiences monitored are:

* Student demographics: sex, sexual identity, race and ethnicity, and grade
* Youth health behaviors and conditions: sexual, injury and violence, bullying, diet and physical activity, obesity, and mental health, suicide attempt
* Substance use behaviors: electronic vapor product and tobacco product use, alcohol use, and other drug use
* Student experiences: parental monitoring, school connectedness, unstable housing, and exposure to community violence

The dataset is used by a group of graduate students from Texas State University for 2025 TXST Open Datathon. The main YRBSS dataset includes data of multiple years, various states, district. For analyzing demographic variations associated with suicide, the 1991–2023 combined district dataset (https://www.cdc.gov/yrbs/files/sadc_2023/HS/sadc_2023_district.dat) is used, which offers a broad historical perspective on trends across different groups. To examine the preventive measures and develop a predictive model for suicide risk, the 2023 dataset (https://www.cdc.gov/yrbs/files/2023/XXH2023_YRBS_Data.zip) was used, ensuring the inclusion of the most recent behavioral and attributes.

Please review the 2023 YRBS Data User's Guide by CDC for further information.