CONCUSSIONS FROM PLAYING SPORTS AMONG HIGH SCHOOL STUDENTS

Objective: This study aims to 1) examine the predictors of concussions from playing a sport 2) build a predictive model for concussions from playing a sport using logistic regression model. 

Methods: Youth Risk Behavior Surveillance System (YRBSS) 2019 data were used for this study.  All the participants who were eligible were randomly assigned into 2 groups: training sample and testing sample. Receiver operating characteristic (ROC) were calculated.

Results:

About 13.31% of 5319 high school students had at least a concussion from playing a sport, about 12.45% among the female and 14.25% among the male.

According to the logistic regression, Q3 (In what grade are you), Q5 (What is your race?), Q6 (How tall are you without your shoes on), QN23 (During the past 12 months, have you ever been bullied on school property?), Q31 (How old were you when you first tried cigarette smoking, even one or two puffs?), Q41 (During the past 30 days, on how many days did you have at least one drink of alcohol?),  Q60 (During your life, with how many people have you had sexual intercourse), Q81(In an average week when you are in school, on how many days do you go to physical education (PE) classes?), Q82 (During the past 12 months, on how many sports teams did you play? (Count any teams run by your school or community groups.)) were significantly associated with the concussions from playing a sport in the high school students.

The area under curve was 0.6837. The optional cutoff time is 0. 8342. The mis-classification error was 0.1339. The sensitivity rate is about 0.5% and the specificity is 99.95%.

Conclusions: In this study, we identified several important predictors for concussions from playing a sport e.g., race, been bullied, how many sports teams did you play on.