Using the PowerMom Digital Health Platform to Support Prenatal Mental Health and Maternal Health Outcomes: Observational Cohort Study
Bibliographic record
Abstract
Background: Mental health disorders such as anxiety and depression are common among individuals of childbearing age. Such disorders can affect pregnancy and postpartum well-being. This study aims to study the impact of prenatal mental health on the pregnancy journey and highlights the use of mobile health technologies such as PowerMom for symptom tracking and screening. objectives: We collected data in a decentralized digital trial using the PowerMom platform to investigate the impact of maternal mental health throughout pregnancy. The goal was to understand how anxiety and depression influence pregnancy-related symptoms, pregnancy outcomes, and postpartum well-being. Methods: Survey data were collected via PowerMom, a bilingual mobile research platform that integrates patient-reported outcomes, wearable data, and electronic health records. Participants were divided into 2 cohorts: those who reported receiving treatment for anxiety or depression during pregnancy (n=571) and those who reported not receiving treatment (n=1505). We compared self-reported symptoms, prepregnancy conditions, complications from past pregnancies, delivery outcomes, and postpartum mental health between cohorts, using the Fisher exact test and the Kruskal-Wallis test for statistical analysis. Results: Participants receiving treatment for anxiety or depression reported higher instances of physical symptoms than those untreated, with significant differences for 13 symptoms including fatigue (80.2% vs 65.4%; adjusted P<.001), nausea and vomiting (69.7% vs 52.7%; adjusted P<.001), and stomach cramping and abdominal pain (64.0% vs 50.4%; adjusted P<.001). Participants receiving treatment also had a higher prevalence of several conditions prior to pregnancy than those not receiving treatment, with significant differences noted in 4 out of 10 conditions: endometriosis (14.0% vs 8.8%; adjusted P=.007), hypertension (10.9% vs 3.9%; adjusted P<.001), eating disorder (7.7% vs 3.1%; adjusted P<.001), and heart disease (2.8% vs 0.5%; adjusted P<.001). Participants receiving treatment also reported a higher prevalence of complications in past pregnancies than those not receiving treatment, with significant differences noted in 2 out of 7 complications: high blood pressure (9.9% vs 5.8%; adjusted P=.016) and preeclampsia (9.2% vs 5.5%; adjusted P=.021). No significant differences were observed in mode of delivery, epidural use, stillbirth, and miscarriage rates between the 2 cohorts. Postpartum, treated participants reported significantly higher mental health composite scores, indicating more severe mental health symptoms. A higher percentage of treated participants were at high risk for having perinatal mood disorder (38/83, 45.8%) than untreated participants (36/196, 18.4%; P<.001). Conclusions: The PowerMom platform demonstrated its value in facilitating remote, scalable data collection for maternal mental health research. Pregnant individuals reporting treatment for anxiety or depression experienced more physical symptoms and worse postpartum mental health outcomes than untreated individuals. These findings underscore the potential for mobile health technologies to support future interventional studies aimed at improving maternal mental health outcomes during pregnancy.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".