Abstract
AIMS: In order to uphold and enhance the emergency psychiatric care system, a thorough comprehension of the characteristics of patients who require a high-acuity psychiatry unit is indispensable. We aimed to clarify the most important predictors of the need for a high-acuity psychiatry unit using a random forest model. METHODS: This cross-sectional study encompassed patients admitted to psychiatric emergency hospitals at 161 medical institutions across Japan between December 8, 2022, and January 31, 2023. Questionnaires were completed by psychiatrists, with a maximum of 30 patients assessed per medical institution. The questionnaires included psychiatrists' assessment of the patient's condition (exposure variables) and the need for a high-acuity psychiatry unit (outcome variables). The exposure variables consisted of 32 binary variables, including age, diagnoses, and clinical condition (i.e., factors on the clinical profile, emergency treatment requirements, and purpose of hospitalization). The outcome variable was the need for a high-acuity psychiatry unit, scored from 0 to 10. To identify the most important predictors of the need for a high-acuity psychiatry unit, we used a random forest model. As a sensitivity analysis, multivariate linear regression analysis was performed. RESULTS: Data on 2,164 patients from 81 medical institutions were obtained (response rate, 50.3%). After excluding participants with missing values, this analysis included 2,064 patients. Of the 32 items, the top-5 predictors of the need for a high-acuity psychiatry unit were the essentiality of inpatient treatment (otherwise, symptoms will worsen or linger), need for 24-hour professional care, symptom severity, safety ensured by specialized equipment, and medication management. These items were each significantly and positively associated with the need for a high-acuity psychiatry unit in linear regression analyses (p < 0.001 for all). Conversely, items on age and diagnosis were lower in the ranking and were not statistically significant in linear regression models. CONCLUSION: Items related to the patient's clinical profile might hold greater importance in predicting the need for a high-acuity psychiatry unit than do items associated with age and diagnosis.