Woebot for Postpartum Mood and Anxiety: A Randomized Controlled Trial Evaluating Feasibility, Acceptability, and Preliminary Efficacy of a Mobile CBT Intervention (Preprint)
Bibliographic record
Abstract
BACKGROUND Postpartum psychological distress, ranging from transient mood and anxiety disturbances to full-syndrome postpartum depression (PPD), is prevalent. Many postpartum individuals lack access to evidence-based interventions due to stigma and insufficient provider availability. The treatment gap is particularly pronounced among historically marginalized groups, including Black, Hispanic/Latina, and low-income mothers, who face higher PPD prevalence and systemic barriers to care. Digital health interventions offer scalable, accessible, and culturally informed emotional support to address these disparities. OBJECTIVE To evaluate the feasibility, acceptability, and preliminary efficacy of a smartphone application-delivered intervention for managing stress, anxiety, and mood in a diverse postpartum population. METHODS This randomized controlled trial recruited participants from the PowerMom study, a digital platform for maternal health research. Eligible individuals (≥16 years, <3 months postpartum) were randomized to Woebot for Postpartum Mood and Anxiety (W-PPMA) or a waitlist control condition. W-PPMA, an investigational digital mental health intervention, features a relational agent delivering cognitive behavioral therapy (CBT)-based psychoeducation via text-based conversations. Primary outcomes included feasibility, acceptability, and satisfaction at 8-week end-of-intervention (EOI). The secondary outcome was change in self-reported depressive symptoms (PHQ-8) at 8-week EOI among participants with elevated baseline symptoms. Exploratory outcomes included anxiety (GAD-7), perinatal depression (EPDS), stress (PSS), mother-infant bond (MIB), and therapeutic alliance (WAI-SR), assessed at baseline, mid-treatment (4 weeks), EOI, and follow-ups at 12 and 16 weeks. The study followed CONSORT guidelines and received IRB approval. RESULTS Participants (N=267; W-PPMA=144, Waitlist=123) represented diverse sociodemographic, mental health, and pregnancy backgrounds. W-PPMA users engaged with the app a median (Q1, Q3) of 9.0 (5.0, 23.8) days over 4.0 (2.0, 7.0) active weeks and reported high feasibility, acceptance, and satisfaction (URPI-F= 31 (28, 34), URPI-A= 30 (28, 34), CSQ-8= 26 (24, 29)). The secondary outcome indicated a small but favorable effect of W-PPMA on depressive symptoms (Cohen’s d=-0.16). Exploratory analyses showed positive trends in perceived stress (PSS) and perinatal depression (EPDS) at EOI. Therapeutic alliance (WAI-SR) was highest among Black participants and those from socioeconomically disadvantaged neighborhoods (ADI ≥75) at Baseline, and at EOI, among those with military healthcare insurance and socioeconomically disadvantaged neighborhoods (ADI ≥75). Satisfaction (CSQ-8) was highest among those with a high school or GED education, highlighting accessibility. CONCLUSIONS Among a diverse postpartum cohort, W-PPMA demonstrated feasibility, acceptability, and modest preliminary efficacy in reducing depressive symptoms. Exploratory findings suggest broader benefits for stress and mood management. High engagement and satisfaction highlight W-PPMA’s potential as a scalable, accessible, and culturally informed digital mental health tool. These findings underscore its potential to bridge gaps in postpartum mental health care, particularly for marginalized populations. Further research is warranted. CLINICALTRIAL Clinicaltrials.gov NCT05662605
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.003 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.014 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".