ABSTRACTPurposeAlthough depression and anxiety are the leading causes of disability in the United States, respectively, fewer than half of people diagnosed with these conditions receive appropriate treatment, and fewer than 10% receive measurement-based care (MBC), which is defined as behavioral health care based on and adapted in response to patient outcomes data collected throughout treatment. The NeuroFlow platform was developed with the goal of making MBC easier to deliver and more accessible within integrated behavioral health care. Data from over 3,000 users of the NeuroFlow platform were used to develop the NeuroFlow Severity Score (NFSS), a potential new measure for depression and anxiety. To begin evaluating the potential usefulness of this new measure, NFSSs were compared with validated measures for depression and anxiety, the Personal Health Questionnaire-9 (PHQ-9) and Generalized Anxiety Disorder-7 (GAD-7) scale, and clinician assessment.MethodsThe NFSS platform is used to record patient-reported and passively collected data related to behavioral health. An artificial-intelligence derived algorithm was developed that condenses this large number of measurements into a single score for longitudinal tracking of an individual’s depression and anxiety symptoms. Linear regression and Bland-Altman analyses were used to evaluate relationships and differences between NFSS and PHQ-9 or GAD-7 scores from over 35,000 NeuroFlow users. The NFSS was also compared to assessment by a panel of expert clinicians for a subset of 250 individuals.ResultsLinear regression results showed a strong correlation between NFSS and PHQ-9 (r=.74, P<.001) and GAD-7 (r=.80, P<.001) changes. There was also a strong positive correlation between the NFSS and expert panel clinical assessment (r=.80-.84, P<.001). Bland-Altman analysis and evaluation of outliers on regression analysis, however, show that the NFSS has significant differences from the PHQ-9.ConclusionsClinicians can reliably use the NFSS as a proxy measure for monitoring symptoms of depression and anxiety longitudinally. The NFSS may identify at-risk individuals who are not identified by the PHQ-9. Further research is warranted to evaluate the sensitivity and specificity of the NFSS.