Toward a Mobile Platform for Real-world Digital Measurement of Depression: User-Centered Design, Data Quality, and Behavioral and Clinical Modeling.

BACKGROUND: Although effective mental health treatments exist, the ability to match individuals to optimal treatments is poor, and timely assessment of response is difficult. One reason for these challenges is the lack of objective measurement of psychiatric symptoms. Sensors and active tasks recorded by smartphones provide a low-burden, low-cost, and scalable way to capture real-world data from patients that could augment clinical decision-making and move the field of mental health closer to measurement-based care. OBJECTIVE: This study tests the feasibility of a fully remote study on individuals with self-reported depression using an Android-based smartphone app to collect subjective and objective measures associated with depression severity. The goals of this pilot study are to develop an engaging user interface for high task adherence through user-centered design; test the quality of collected data from passive sensors; start building clinically relevant behavioral measures (features) from passive sensors and active inputs; and preliminarily explore connections between these features and depression severity. METHODS: A total of 600 participants were asked to download the study app to join this fully remote, observational 12-week study. The app passively collected 20 sensor data streams (eg, ambient audio level, location, and inertial measurement units), and participants were asked to complete daily survey tasks, weekly voice diaries, and the clinically validated Patient Health Questionnaire (PHQ-9) self-survey. Pairwise correlations between derived behavioral features (eg, weekly minutes spent at home) and PHQ-9 were computed. Using these behavioral features, we also constructed an elastic net penalized multivariate logistic regression model predicting depressed versus nondepressed PHQ-9 scores (ie, dichotomized PHQ-9). RESULTS: A total of 415 individuals logged into the app. Over the course of the 12-week study, these participants completed 83.35% (4151/4980) of the PHQ-9s. Applying data sufficiency rules for minimally necessary daily and weekly data resulted in 3779 participant-weeks of data across 384 participants. Using a subset of 34 behavioral features, we found that 11 features showed a significant (P<.001 Benjamini-Hochberg adjusted) Spearman correlation with weekly PHQ-9, including voice diary-derived word sentiment and ambient audio levels. Restricting the data to those cases in which all 34 behavioral features were present, we had available 1013 participant-weeks from 186 participants. The logistic regression model predicting depression status resulted in a 10-fold cross-validated mean area under the curve of 0.656 (SD 0.079). CONCLUSIONS: This study finds a strong proof of concept for the use of a smartphone-based assessment of depression outcomes. Behavioral features derived from passive sensors and active tasks show promising correlations with a validated clinical measure of depression (PHQ-9). Future work is needed to increase scale that may permit the construction of more complex (eg, nonlinear) predictive models and better handle data missingness.

Affective ERP processing in a visual oddball task: arousal, valence, and gender.

OBJECTIVE: To assess affective event-related brain potentials (ERPs) using visual pictures that were highly distinct on arousal level/valence category ratings and a response task. METHODS: Images from the International Affective Pictures System (IAPS) were selected to obtain distinct affective arousal (low, high) and valence (negative, positive) rating levels. The pictures were used as target stimuli in an oddball paradigm, with a visual pattern as the standard stimulus. Participants were instructed to press a button whenever a picture occurred and to ignore the standard. Task performance and response time did not differ across conditions. RESULTS: High-arousal compared to low-arousal stimuli produced larger amplitudes for the N2, P3, early slow wave, and late slow wave components. Valence amplitude effects were weak overall and originated primarily from the later waveform components and interactions with electrode position. Gender differences were negligible. CONCLUSION: The findings suggest that arousal level is the primary determinant of affective oddball processing, and valence minimally influences ERP amplitude. SIGNIFICANCE: Affective processing engages selective attentional mechanisms that are primarily sensitive to the arousal properties of emotional stimuli. The application and nature of task demands are important considerations for interpreting these effects.

Affective visual event-related potentials: arousal, valence, and repetition effects for normal and distorted pictures.

Event-related potentials (ERPs) were used to assess arousal (low, high), valence (negative, positive), and stimulus repetition effects for normal and distorted images from the International Affective Pictures System (IAPS). Distorted stimuli were constructed by dividing each image into small squares and rearranging the segments randomly to produce a "scrambled" picture. Event-related potentials (ERPs) were elicited by presenting the normal and scrambled images as target stimuli, with a repeated visual pattern used as the standard stimulus. Participants (N=32) were instructed to press a button to the targets and ignore the standard. Stimulus repetition effects were assessed by presenting each stimulus twice in the normal and scrambled condition. High-arousal stimuli yielded larger late positive components for both the normal and scrambled pictures. No overall valence effects were obtained, but arousal and valence influenced component amplitudes for middle-latency ERPs from the scrambled stimuli. For the normal pictures, stimulus repetition was associated with increased component amplitudes for all potentials and decreased RTs of all affective categories. For the scrambled pictures, no repetition changes were obtained. The findings suggest that stimulus arousal level contributes more than valence to affective ERP measures for normal as well as perceptually distorted pictures. Stimulus repetition engages memory for previous normal picture items but is not influenced by affective category. Theoretical implications are discussed.