JMIR Publications

ABSTRACT

Background:

Background:

Fewer than 10% of individuals seeking behavioral health care receive measurement-based care (MBC). Technology has been called upon to implement MBC in a secure and efficient manner. The NeuroFlow mHealth platform was developed with the goal of making MBC easier to deliver by clinicians and more accessible for patients 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 robust screening measure for depression and anxiety.

Objective:

Objective:

To begin evaluating the potential added value of this new measure, NFSSs were compared with scores from validated assessments for depression and anxiety, the Personal Health Questionnaire-9 (PHQ-9) and Generalized Anxiety Disorder-7 (GAD-7), and clinician assessment.

Methods:

Methods:

The NFSS uses patient-reported and passively collected data related to behavioral health. An artificial-intelligence derived algorithm was developed that condenses behavioral health data into a single, quantifiable measure 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.

Results:

Results:

Linear regression results showed a strong correlation between NFSS and PHQ-9 (r=.74, P<.001) and GAD-7 (r=.80, P<.001) changes. There also was 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.

Conclusions:

Conclusions:

Clinicians can reliably use the NFSS as a proxy measure for screening and monitoring behavioral health symptoms 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.