Mobile Health Adoption in High-Risk Pregnancies Using Cluster Analysis of Biopsychosocial Outcomes: Observational Longitudinal Cohort Study
Bibliographic record
Abstract
Background: The use of mobile technologies during high-risk pregnancy, placing patients at the center of care, affords them self-management and easier access to health information. Objective: This study aims to understand the health perception of pregnant women at the beginning of high-risk antenatal care, the usability of a mobile health app-the Health Assistant-and to compare maternal-fetal outcomes between users and nonusers of the app. Methods: This is an observational longitudinal cohort study that looked into clusters of high-risk pregnant women admitted to antenatal care at the maternity unit of a public university hospital in southern Brazil between April 2022 and November 2023. Pregnant women who did not have a compatible smartphone to download the app or who did not have internet access were excluded from the study. According to systematic randomization, one patient was allocated to the app group and the other to the control group. They all answered an inclusion questionnaire (Q1), and those in the app group were instructed to use the Health Assistant app to prepare for their first antenatal appointment, which would take place in a few weeks' time, when they would answer the Brazilian version of the Mobile App Usability Questionnaire. After childbirth, maternal-fetal outcomes were assessed. Student 2-tailed t test, Mann-Whitney test, Fisher exact test, and the chi-square test were used for statistical analysis. A hierarchical cluster analysis was performed using the Ward method and the Euclidean squared distance measure. Results: The sample contained 111 pregnant women, of whom 55 (49.5%) were allocated to the app group and 56 (50.5%) to the control group. Of the 55 pregnant women who used the app, 21 (38.2%) demonstrated adherence, with an average Mobile App Usability Questionnaire score of 6.2 (SD 1.0). Clustering included 110 pregnant women, and the dendrogram resulted in three clusters, which show several significant differences in terms of family income, medical history, medication adherence, and lifestyle habits. Cluster 2 had the lowest adherence to the app (P=.08) and attended significantly fewer antenatal appointments (6.9 appointments) as compared with Clusters 1 (10.3) and 3 (9.1; P=.006). Cesarean section was more frequent in Cluster 3 (n=41, 95.3%) as compared with Clusters 1 (n=12, 27.9%) and 2 (n=5, 20.8%), P<.001. Conclusions: Cluster analysis, revealing different profiles of pregnant women, allowed us to identify groups that would benefit from personalized approaches and digital interventions to improve self-awareness and gestational outcomes. The Health Assistant app showed good usability in this context.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| 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 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".