A predictive model to allocate frequent service users of community-based Mental Health Services to different packages of care

Summary Aim – To develop predictive models to allocate patients into frequent and low service users groups within the Italian Community-based Mental Health Services (CMHSs). To allocate frequent users to different packages of care, identifing the costs of these packages. Methods – Socio-demographic and clinical data and GAF scores at baseline were collected for 1250 users attending five CMHSs. All psychiatric contacts made by these patients during six months were recorded. A logistic regression identified frequent service users predictive variables. Multinomial logistic regression identified variables able to predict the most appropriate package of care. A cost function was utilised to estimate costs. Results – Frequent service users were 49%, using nearly 90% of all contacts. The model classified correctly 80% of users in the frequent and low users groups. Three packages of care were identified: Basic Community Treatment (4,133 Euro per six months); Intensive Community Treatment (6,180 Euro) and Rehabilitative Community Treatment (11,984 Euro) for 83%, 6% and 11% of frequent service users respectively. The model was found to be accurate for 85% of users. Conclusion – It is possible to develop predictive models to identify frequent service users and to assign them to pre-defined packages of care, and to use these models to inform the funding of psychiatric care.