Smartphone keyboard dynamics predict affect in suicidal ideation.

Area of Science:

• Digital health
• Computational psychiatry
• Mental health assessment

Background:

• Digital phenotyping enables unobtrusive, real-time mental health monitoring.
• Integrating diverse data modalities with varying sampling rates presents significant challenges.
• Existing methods struggle with high-dimensional data and temporal synchronization.

Purpose of the Study:

• To develop an integrated pipeline for fusing digital phenotyping data modalities.
• To address challenges of high dimensionality and differing sampling frequencies in multimodal data.
• To investigate the relationship between digital behavioral data and mental health symptoms.

Main Methods:

• Developed a pipeline transforming data to a common time unit.
• Applied temporal independent component analysis (ICA) to high-dimensional self-report data.
• Utilized linear mixed-effects models to fuse self-report and keyboard dynamics data.

Main Results:

• ICA on self-report data identified components related to well-being, anhedonia, irritability, and social dysfunction.
• Reduced phone movement during typing correlated with increased anhedonia (β = -0.12, p = 0.00030).
• The pipeline successfully integrated daily self-report and BiAffect keyboard dynamics.

Conclusions:

• The proposed pipeline effectively integrates multimodal digital phenotyping data.
• This approach facilitates deeper understanding of mental health conditions through behavioral patterns.
• The method is broadly applicable to dense, longitudinal digital phenotyping datasets.