Personalized Quality of Life Measurement

PROJECT SUMMARY/ABSTRACT. A lack of outcome-focused quality measures is holding back mental health (MH) progress. This gap means that regulatory bodies and third-party payers do not have a “common denominator” that they can use to compare the impact of MH symptoms and treatment options across all MH and physical health (PH) conditions. For

example, we cannot effectively compare the overall impact of treatment for depression to treatment for other MH conditions such as schizophrenia, or to PH conditions such as diabetes. Quality measurement also underpins cost-effectiveness research, and as a result we cannot accurately allocate resources needed for a

nationwide MH strategy. Furthermore, clinicians and researchers cannot recommend treatments based on overall impact, but rather they are restricted to narrowly focused symptom and outcome measurements. Without addressing problems in outcome-focused quality measures, patients will continue to face a disjointed

MH care system where sufficient resources are not apportioned to their needs, their clinicians cannot select treatments in a way that will maximize their overall functioning, and research to improve their care cannot consistently demonstrate comparative effectiveness. Quality of life (QOL) measures provide a promising approach to serve as a common denominator for outcome-

focused quality measurement across conditions. However, current nomothetic approaches are not specific to MH symptoms, which creates measurement insensitivity and substantially reduces measurement accuracy. There are also many idiographic QOL measures that are tailored to specific disorders, but they are not directly

comparable across MH or PH conditions. New QOL measurement approaches are needed that are both nomothetically comparable across disease conditions and ideographically tailored to MH phenomenology. New developments in unsupervised machine learning (ML) are well suited to address these limitations in QOL

measurement. Specifically, we will use recent advances in mixture modeling to create a new personalized QOL measurement approach that simultaneously produces both nomothetic and idiographic results. The proposed project is significant and impactful because it eliminates a critical bottleneck to efforts by policy makers,

researchers, and clinicians. Results from this work will allow all of these stakeholders to better discern differential impact among MH conditions and interventions. As a result, they will be able to better serve patients who experience MH difficulties. This project is also scientifically and methodologically innovative. It creatively

uses new developments in unsupervised ML to implement a new measurement process while minimizing disruption to current practices. Overall, the proposed project will provide a new standard for outcome-focused measurement of MH care.