A Machine Learning Approach to Sustainable Coding of Measurement-Based Care Fidelity

Summary

There is a critical need to improve the quality of youth mental health care, particularly for youth treated in community mental health centers. It is estimated that 50-70% of youth in these settings drop out of treatment early and more than half fail to improve or deteriorate during treatment. Measurement-based care (MBC) is one potential solution to this public health crisis. This project brings together a team of researchers from the Departments of Psychology and Computer Science to generate a machine learning approach to automated MBC fidelity coding. In partnership with an advisory board of community and academic partners, the project will build an automated MBC fidelity coding algorithm that will form the basis for future grants to further refine the algorithm and deploy it in community settings.

Team

Amanda Doss (Psychology), Mitsunori Ogihara (Computer Science), Jerry Bonnel (Computer Science), Elizabeth Casline (Northwestern University)

A Machine Learning Approach to Sustainable Coding of Measurement-Based Care Fidelity