Master of Arts (MA)
First Committee Member
Second Committee Member
Third Committee Member
Fourth Committee Member
Number of Pages
Traditionally, treatment option for psychiatric crises was limited to psychiatric hospitalization. However, psychiatric hospitals are expensive and little evidence supports their utility. Youth returning from psychiatric hospitalizations often have difficulties readjusting to everyday life which can increase risk for negative outcomes. Alternative treatment options such as mobile crisis services might be useful for stabilizing youth in the community and garnering better long-term outcomes. For alternative treatment options to work, clinicians must be able to efficiently and accurately distinguish youth in need of psychiatric hospitalization and youth who could be served via an alternative service. Therefore, the purpose of the present study is to examine the predictive utility of risk factors available at the time of the hospitalization decision and develop a decision tree that clinicians could use to aid in the decision-making process. Data consisted of 2,605 youth aged 4.0 – 19.5 years (M = 14.07, SD = 2.73, 56% female) who utilized the Mobile Crisis Response Team in the State of Nevada between 2014 and 2017. Using Random Forest, the 13 most important risk factors were identified. Classification and Regression Tree provided an interpretable, easy to use decision tree (accuracy = .88, AUC = .82). In summary, the most important risk factors for hospitalization reflected current functioning. Lifetime risk factors (e.g., diagnosis) were not strong predictors of acute decision-making when acute risk factors were available. Clinicians should attend to current symptoms (e.g., suicide behaviors, danger to others, poor judgment, psychotic symptoms) and environmental factors (e.g., poor functioning at home, poor caregiver supervision) that increase a youth’s risk for harming oneself or others when deciding whether to hospitalize or stabilize a youth in psychiatric crisis.
University of Nevada, Las Vegas
Chen, Yen-Ling, "Identifying Risk Factors for Youth Hospitalization in Crisis Settings: A Classification and Regression Tree Analysis" (2019). UNLV Theses, Dissertations, Professional Papers, and Capstones. 3588.
IN COPYRIGHT. For more information about this rights statement, please visit http://rightsstatements.org/vocab/InC/1.0/