Incorporating Data From Text Messages and Email Into Psychotherapy: Randomized Controlled Trial.

Background: As digital communication becomes central to daily life, psychotherapy increasingly has access to patients' electronic media data. Although digital phenotyping has been widely studied, less is known about whether incorporating personal communication data, such as text messages, improves clinical outcomes in psychotherapy. Objective: This study aimed to determine whether integrating personalized text message data into psychotherapy improves depression, anxiety, health-related quality of life, and therapeutic alliance and to examine whether increased access to collateral information influences clinical decision-making. Methods: The Electronic Media and its Impact on Psychotherapy (EMAP) study was a randomized controlled trial conducted in adult and geriatric outpatient and partial hospitalization settings at an academic psychiatric hospital. Participants receiving psychotherapy for primary depression or anxiety (n=101) were randomized to electronic media-enhanced therapy (EME; n=52) or treatment as usual (TAU; n=49). In EME, research staff reviewed participants' text messages prior to sessions using personalized mood-related key terms and presented aggregated findings on a Health Insurance Portability and Accountability Act (HIPAA)-compliant clinician dashboard. TAU participants received standard care without message review. Outcomes included change scores for the Patient Health Questionnaire-9 (PHQ-9), the Generalized Anxiety Disorder-7 (GAD-7), the 36-item Short Form Health Survey (SF-36), and the Working Alliance Inventory-Short Revised (WAI-SR). Linear regression and nonparametric tests compared groups. Moderation analyses assessed whether the frequency of information access influenced treatment changes. Results: No statistically significant between-group differences were observed in anxiety or working alliance. Among participants with SF-36 follow-up data (n=65), EME participants demonstrated greater improvement in the pain subscale. Greater frequency of information access was associated with increased treatment-related changes in the EME group. Access to additional collateral information was associated with more clinical actions but not with improved distal outcomes. Conclusions: Integrating personalized text message data into short-term psychotherapy did not significantly improve depression or anxiety, and it neither improved nor worsened therapeutic alliance. However, access to greater amounts of collateral information, including electronic media, influenced clinical decision-making, suggesting nuanced and context-dependent effects.