A Study of Novel Exploratory Tools, Digital Technologies, and Central Nervous System Biomarkers to Characterize Unipolar Depression

Abstract

Background: Digital technologies have the potential to provide objective and precise tools to detect depression-related symptoms. Deployment of digital technologies in clinical research can enable collection of large volumes of clinically relevant data that may not be captured using conventional psychometric questionnaires and patient-reported outcomes. Rigorous methodology studies to develop novel digital endpoints in depression are warranted. Objective: We conducted an exploratory, cross-sectional study to evaluate several digital technologies in subjects with major depressive disorder (MDD) and persistent depressive disorder (PDD), and healthy controls. The study aimed at assessing utility and accuracy of the digital technologies as potential diagnostic tools for unipolar depression, as well as correlating digital biomarkers to clinically validated psychometric questionnaires in depression. Methods: A cross-sectional, non-interventional study of 20 participants with unipolar depression (MDD and PDD/dysthymia) and 20 healthy controls was conducted at the Centre for Human Drug Research (CHDR), the Netherlands. Eligible participants attended three in-clinic visits (days 1, 7, and 14), at which they underwent a series of assessments, including conventional clinical psychometric questionnaires and digital technologies. Between the visits, there was at-home collection of data through mobile applications. In all, seven digital technologies were evaluated in this study. Three technologies were administered via mobile applications: an interactive tool for the self-assessment of mood, and a cognitive test; a passive behavioral monitor to assess social interactions and global mobility; and a platform to perform voice recordings and obtain vocal biomarkers. Four technologies were evaluated in the clinic: a neuropsychological test battery; an eye motor tracking system; a standard high-density electroencephalogram (EEG)-based technology to analyze the brain network activity during cognitive testing; and a task quantifying bias in emotion perception. Results: Our data analysis was organized by technology - to better understand individual features of various technologies. In many cases, we obtained simple, parsimonious models that have reasonably high diagnostic accuracy and potential to predict standard clinical outcome in depression. Conclusion: This study generated many useful insights for future methodology studies of digital technologies and proof-of-concept clinical trials in depression and possibly other indications.

Keywords: digital biomarkers; major depression; mobile health; novel endpoints; variable selection.

Figure 1

Study design schematic.

Figure 2

MADRS total score per group (healthy and unipolar depression) and per visit.

Figure 3

Observed vs. predicted average total MADRS score using different digital technology features. The green diagonal line represents a perfect match between observed and predicted MADRS total scores. In case of a strong linear relationship between MADRS total score and selected features, the observations are expected to fall along the green diagonal line. The gray dashed horizontal line at 10.5 represents a classification threshold: when predicted MADRS total scores for healthy subjects are above 10.5 or similar values for depressed subjects are below 10.5, these observations would be misclassified based on the linear model classifier. PHQ2 is a self-reported score of mood assessment. SMI is a subjective memory impairment score.

Figure 4

ROC curves of classifiers based on logistic regression using different digital technology features.

Figure 5

ROC curves of classifiers based on linear model-predicted MADRS using different digital technology features.