Emily S. Miller

Background: Preterm birth is associated with an increased rate of serious maternal complication compared with those who deliver at term. However, data are limited on risk factors for maternal morbidity and mortality specifically in the setting of preterm birth. Improved understanding of risk factors for morbidity in patients with preterm birth can help optimize interventions to best support patients experiencing preterm birth. Objective: To assess associations between obstetric factors and maternal morbidities and mortality among patients who gave birth less than 35 weeks’ gestation. Study design: This is a secondary analysis of a multicenter registry of gravidas carrying singletons or twins who gave birth at 16 0/7 to 34 6/7 weeks’ gestation January through August 2019. The primary outcome was a maternal morbidity and mortality composite (blood transfusion, postpartum hemorrhage, maternal sepsis, stroke, thromboembolism, intensive care unit admission, or death) during the delivery hospitalization. Factors were compared between those with and without the composite outcome to identify statistically significant variables. Those factors were then used to create a parsimonious multivariable logistic regression model with adjusted odds ratio (aOR) and 95% confidence intervals (CIs) using a backward strategy. We estimated area under the curve to quantify the predictive ability of these factors for the primary outcome. Results: The analysis was based on 6660 patients, of whom 15.1% experienced the primary composite outcome. Factors associated with increased odds of the outcome included increasing maternal age, use of assisted reproductive technology, twin gestation, preeclampsia, placental abruption and cesarean delivery—aOR ranged from 1.02 [1.01–1.04] for maternal age (continuous) to 2.55 [2.08–3.14] for abruption. In contrast, nulliparity, gestational diabetes, preterm prelabor rupture of membranes (PPROM), and later birth gestational age were associated with decreased odds of the primary outcome—aOR ranging from 0.96 [0.95–0.98] for gestational age (continuous) to 0.54 [0.44–0.66] for PPROM. The model with these factors had low to moderate predictive ability (AUC 0.68 [0.66–0.69]). Conclusion: Among individuals who experienced preterm birth before 35 weeks, multiple factors were associated with maternal morbidity and mortality. The factors together modestly discriminate maternal morbidity or mortality.

Participants in qualitative interviews designed to optimize the adaptation of a maternal postpartum depression intervention into a novel smartphone app noted that the app could be more useful if were delivered simultaneously to both parents; this calls for additional research on the feasibility and effectiveness of digital dyadic or stand-alone partner interventions to prevent postpartum depression.

A bstract: Postpartum depression (PPD) affects 10–15% of individuals annually, yet early identification and treatment remains challenging. We introduce ClinPreAI, a novel agentic AI system that autonomously designs, implements, and evaluates machine learning solutions for PPD risk prediction using multimodal electronic health record data. We analyzed data from 4,161 pregnant individuals hospitalized prior to delivery for medical or obstetrical complications at Texas Children’s Hospital (2012–2025), extracting 27 structured clinical variables and social worker notes. The primary outcome was Edinburgh Postnatal Depression Scale (EPDS) score ≥10 (31.0% prevalence) within 6 months after delivery, indicating clinically significant depressive symptoms. ClinPreAI operates through five specialized modules that iteratively refine predictive models through autonomous experimentation. ClinPreAI demonstrated strong performance across modalities. On structured data, it achieved F1: 0.68 ± 0.03, outperforming traditional AutoML (F1: 0.64 ± 0.02) and commercial solutions (AWS Canvas F1: 0.54–0.55). On multimodal data, ClinPreAI achieved F1: 0.65 ± 0.04, matching custom LLM-XGBoost (F1: 0.65 ± 0.01) and outperforming zero-shot models (Claude Opus F1: 0.51–0.52). This represents the first application of agentic AI to perinatal mental health prediction. Our results demonstrate that autonomous AI agents can democratize sophisticated predictive modeling in clinical settings, which is particularly valuable where domain experts lack ML training. By automating experimentation and debugging, agentic systems lower barriers to developing robust clinical prediction tools while maintaining interpretability.

Background: The postpartum period represents a critical period for both birthing and nonbirthing parents due to mental health concerns and new caregiving demands. Collaborative care models aim to address these needs, but postpartum care remains fragmented, lacking continuity and holistic support. Baby2Home (B2H) is a digital intervention rooted in the collaborative care model, specifically designed to support parents through their transition into parenthood by addressing their physical, emotional, and psychosocial needs. This intervention seeks to close the gaps left by traditional care models by providing continuous, organized, and accessible support throughout the postpartum period. In our qualitative study of the B2H intervention, we reference the parallel journeys framework and use it as a part of our analysis to evaluate whether mobile health (mHealth) technology addresses the holistic needs (postpartum and psychosocial) of new parents. Objective: We aimed to assess how the B2H app supports the holistic needs of new parents and addresses care gaps identified in traditional postpartum services. Methods: We conducted semistructured interviews with 20 birthing and nonbirthing parents selected through purposive sampling based on their app use. Data were analyzed using the postpartum parallel journeys framework and inductive coding. Results: Our findings demonstrate the comprehensive impact of the B2H intervention in addressing both the physical and psychosocial needs of new parents. B2H supported postpartum care by helping parents navigate uncertainties, enhancing health care provider–parent communication, promoting self-care, and increasing parental self-efficacy. Psychosocial support included symptom identification, timely care manager assessments, coordinated treatment, and transition resources. The app also addressed care gaps by promoting inclusivity for nonbirthing parents, bridging screening and treatment, supporting real-time treatment navigation, and ensuring continuity of care. Conclusions: We demonstrate that the use of mHealth technology such as the B2H app can effectively support the multifaceted needs of new parents during their postpartum care period. By applying the parallel journeys framework, the research also identifies gaps in care that are addressed by the B2H app, presenting unique opportunities for future development and research.

UNSTRUCTURED Participants in qualitative interviews designed to optimize the adaptation of a maternal postpartum depression intervention into a novel smartphone app noted that the app could be more useful if were delivered simultaneously to both parents; this calls for additional research on the feasibility and effectiveness of digital dyadic or stand-alone partner interventions to prevent postpartum depression.

Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: The postpartum period represents a critical period for both birthing and nonbirthing parents due to mental health concerns and new caregiving demands. Collaborative care models aim to address these needs, but postpartum care remains fragmented, lacking continuity and holistic support. Baby2Home (B2H) is a digital intervention rooted in the collaborative care model, specifically designed to support parents through their transition into parenthood by addressing their physical, emotional, and psychosocial needs. This intervention seeks to close the gaps left by traditional care models by providing continuous, organized, and accessible support throughout the postpartum period. In our qualitative study of the B2H intervention, we reference the parallel journeys framework and use it as a part of our analysis to evaluate whether mobile health (mHealth) technology addresses the holistic needs (postpartum and psychosocial) of new parents. Objective: We aimed to assess how the B2H app supports the holistic needs of new parents and addresses care gaps identified in traditional postpartum services. Methods: We conducted semistructured interviews with 20 birthing and nonbirthing parents selected through purposive sampling based on their app use. Data were analyzed using the postpartum parallel journeys framework and inductive coding. Results: Our findings demonstrate the comprehensive impact of the B2H intervention in addressing both the physical and psychosocial needs of new parents. B2H supported postpartum care by helping parents navigate uncertainties, enhancing health care provider–parent communication, promoting self-care, and increasing parental self-efficacy. Psychosocial support included symptom identification, timely care manager assessments, coordinated treatment, and transition resources. The app also addressed care gaps by promoting inclusivity for nonbirthing parents, bridging screening and treatment, supporting real-time treatment navigation, and ensuring continuity of care. Conclusions: We demonstrate that the use of mHealth technology such as the B2H app can effectively support the multifaceted needs of new parents during their postpartum care period. By applying the parallel journeys framework, the research also identifies gaps in care that are addressed by the B2H app, presenting unique opportunities for future development and research.