A linear optimization approach to decision support with CANS data

Abstract

This research is meant to make a contribution to the field of Communimetric (CMX) algorithms (Lyons, 2004, 2009). This is the science underscoring the behavioral health and child welfare assessment tools such as the Child and Adolescent Needs and Strengths (CANS) assessment, the Adult Needs and Strengths Assessment (ANSA), and the Family Advocacy and Support Tool (FAST), amongst others (https://praedfoundation.org/). These tools are used throughout the US child serving and adult mental health system not only to assure a standardized assessment process, but also to provide real-time Decision Support (DS) to assessors about client treatment planning and disposition. We propose a novel method for developing CMX DS utilizing linear optimization (commonly known also as linear programming (LP) or (mixed) integer linear programming (ILP or MILP)). Using administrative data from Pennsylvania’s Child Medicaid Behavioral Health system, a MILP model is developed to differentiate profiles that benefit from one of two programs in the Pennsylvania child system of care. The programs picked are both for children at risk of out of home placement, but their clinical models are different. There is often debate in the field as to which program is most appropriate for a given family, and thus the MILP model is meant to help facilitate this decision making. We propose both a method for developing a MILP model in Medicaid behavioral health, as well as a method for testing and validating the model. We then propose a method for identifying the impact on care that utilization of the model could have in facilitating improved care matching in a system. We close with a discussion of how this information could also be used for system planning, and program development issues.