Predicting Future Hospital Utilization for Mental Health Conditions

摘要: To develop a model using administrative variables to predict number of days in the hospital for mental health condition year after discharge from hospitalization. Background, index hospitalization and preindex inpatient, emergency room, outpatient utilization information were collected 766 adult members discharged during 1-year period. A regression was developed hospitalized discharge. created containing five statistically significant predictors: Medicare insurance coverage, inpatient days, length stay, depression diagnosis, visits with professional provider. It is possible future at time data, thus allowing disease managers better identify greatest need additional services interventions.