VMAP: Vaginal Microbiome Atlas during Pregnancy.

Objectives: To enable interactive visualization of the vaginal microbiome across the pregnancy and facilitate discovery of novel insights and generation of new hypotheses. Material and Methods: Vaginal Microbiome Atlas during Pregnancy (VMAP) was created with R shiny to generate visualizations of structured vaginal microbiome data from multiple studies. Results: VMAP (http://vmapapp.org) visualizes 3880 vaginal microbiome samples of 1402 pregnant individuals from 11 studies, aggregated via open-source tool MaLiAmPi. Visualized features include diversity measures, VALENCIA community state types, and composition (phylotypes, taxonomy) that can be filtered by various categories. Discussion: This work represents one of the largest and most geographically diverse aggregations of the vaginal microbiome in pregnancy to date and serves as a user-friendly resource to further analyze vaginal microbiome data and better understand pregnancies and associated outcomes. Conclusion: VMAP can be obtained from https://github.com/msirota/vmap.git and is currently deployed as an online app for non-R users.

Surgical Necrotizing Enterocolitis and Spontaneous Intestinal Perforation Lead to Severe Growth Failure in Infants.

OBJECTIVE: We aimed to determine the incidence of growth failure in infants with necrotizing enterocolitis (NEC) or spontaneous intestinal perforation (SIP) and whether initial laparotomy versus peritoneal drainage (PD) impacted the likelihood of growth failure. SUMMARY BACKGROUND DATA: Infants with surgical NEC and SIP have high mortality, and most have neurodevelopmental impairment and poor growth. Existing literature on growth outcomes for these infants is limited. METHODS: This is a preplanned secondary study of the Necrotizing Enterocolitis Surgery Trial dataset. The primary outcome was growth failure (Z-score for weight <-2.0) at 18 to 22 months. We used logistic regression, including diagnosis and treatment, as covariates. Secondary outcomes were analyzed using the Fisher exact or Pearson χ2 test for categorical variables and the Wilcoxon rank sum test or one-way ANOVA for continuous variables. RESULTS: Among 217 survivors, 207 infants (95%) had primary outcome data. Growth failure at 18 to 22 months occurred in 24/50 (48%) of NEC infants versus 65/157 (42%) SIP (P=0.4). The mean weight-for-age Z-score at 18 to 22 months in NEC infants was -2.05±0.99 versus -1.84±1.09 SIP (P=0.2), and the predicted mean weight-for-age Z-score SIP (Beta -0.27; 95% CI: -0.53, -0.01; P=0.041). Median declines in weight-for-age Z-score between birth and 18 to 22 months were significant in all infants but most severe (>2) in NEC infants (P=0.2). CONCLUSIONS: This first ever prospective study of growth outcomes in infants with surgical NEC or SIP demonstrates that growth failure is very common, especially in infants with NEC, and persists at 18-22 months.

A Novel Stem Cell Model to Study Preeclampsia Endothelial Dysfunction.

Preeclampsia is a common pregnancy complication affecting 5% to 7% of all pregnancies worldwide annually. While the pathogenesis is not fully understood, maternal endothelium dysfunction is thought to be a central component to preeclampsia development. Studies to dissect maternal endothelial dysfunction, particularly on a patient-specific basis, are hampered by limited access to systemic primary endothelial cells (ECs). The objective of this study was to establish a replenishable, patient-specific in vitro EC model to allow robust mechanistic studies to dissect endothelial dysfunction in preeclampsia. Induced pluripotent stem cells (iPSCs) from three women with a history of normotensive pregnancies were differentiated into ECs. The established ECs were exposed to pooled sera from normotensive pregnancies, preeclamptic pregnancies, normotensive postpartum for non-pregnant comparison and controls. Endothelial functions including nitric oxide (NO) release, cell migration, tube formation and viability were evaluated. Levels of NO release were significantly lower after incubation with preeclamptic sera compared to the fetal bovine serum (FBS) control, and normotensive and non-pregnant (postpartum) sera treatments were also lower than FBS but higher than preeclamptic sera treatments. Tube formation and cell migration were also impaired with preeclamptic sera compared to FBS controls. Cell viabilities remained unaffected by any sera treatment. Consistent outcomes were obtained across all three patient-specific lines treated with the same pooled sera. Establishment of patient-derived iPSC-ECs treated with pregnancy sera serves as a novel model to explore the interplay between individual maternal endothelial health and circulating factors that lead to endothelial dysfunction in preeclampsia.

Association of pregnancy complications and postpartum maternal leukocyte telomeres in two diverse cohorts: a nested case-control study.

BACKGROUND: Biologic strain such as oxidative stress has been associated with short leukocyte telomere length (LTL), as well as with preeclampsia and spontaneous preterm birth, yet little is known about their relationships with each other. We investigated associations of postpartum maternal LTL with preeclampsia and spontaneous preterm birth. METHODS: This pilot nested case control study included independent cohorts of pregnant people with singleton gestations from two academic institutions: Cohort 1 (hereafter referred to as Suburban) were enrolled prior to 20 weeks' gestation between 2012 and 2018; and Cohort 2 (hereafter referred to as Urban) were enrolled at delivery between 2000 and 2012. Spontaneous preterm birth or preeclampsia were the selected pregnancy complications and served as cases. Cases were compared with controls from each study cohort of uncomplicated term births. Blood was collected between postpartum day 1 and up to 6 months postpartum and samples were frozen, then simultaneously thawed for analysis. Postpartum LTL was the primary outcome, measured using quantitative polymerase chain reaction (PCR) and compared using linear multivariable regression models adjusting for maternal age. Secondary analyses were done stratified by mode of delivery and self-reported level of stress during pregnancy. RESULTS: 156 people were included; 66 from the Suburban Cohort and 90 from the Urban Cohort. The Suburban Cohort was predominantly White, Hispanic, higher income and the Urban Cohort was predominantly Black, Haitian, and lower income. We found a trend towards shorter LTLs among people with preeclampsia in the Urban Cohort (6517 versus 6913 bp, p = 0.07), but not in the Suburban Cohort. There were no significant differences in LTLs among people with spontaneous preterm birth compared to term controls in the Suburban Cohort (6044 versus 6144 bp, p = 0.64) or in the Urban Cohort (6717 versus 6913, p = 0.37). No differences were noted by mode of delivery. When stratifying by stress levels in the Urban Cohort, preeclampsia was associated with shorter postpartum LTLs in people with moderate stress levels (p = 0.02). CONCLUSION: Our exploratory results compare postpartum maternal LTLs between cases with preeclampsia or spontaneous preterm birth and controls in two distinct cohorts. These pilot data contribute to emerging literature on LTLs in pregnancy.

Mode of delivery predicts postpartum maternal leukocyte telomere length.

BACKGROUND: Recent studies have suggested that pregnancy accelerates biologic aging, yet little is known about how biomarkers of aging are affected by events during the peripartum period. Given that immune shifts are known to occur following surgery, we explored the relation between mode of delivery and postpartum maternal leukocyte telomere length (LTL), a marker of biologic aging. STUDY DESIGN: Postpartum maternal blood samples were obtained from a prospective cohort of term, singleton livebirths without hypertensive disorders or peripartum infections between 2012 and 2018. The primary outcome was postpartum LTLs from one blood sample drawn between postpartum week 1 and up to 6 months postpartum, measured from thawed frozen peripheral blood mononuclear cells using quantitative PCR in basepairs (bp). Multivariable linear regression models compared LTLs between vaginal versus cesarean births, adjusting for age, body mass index, and nulliparity as potential confounders. Analyses were conducted in two mutually exclusive groups: those with LTL measured postpartum week 1 and those measured up to 6 months postpartum. Secondarily, we compared multiomics by mode of delivery using machine-learning methods to evaluate whether other biologic changes occurred following cesarean. These included transcriptomics, metabolomics, microbiomics, immunomics, and proteomics (serum and plasma). RESULTS: Of 67 included people, 50 (74.6 %) had vaginal and 17 (25.4 %) had cesarean births. LTLs were significantly shorter after cesarean in postpartum week 1 (5755.2 bp cesarean versus 6267.8 bp vaginal, p = 0.01) as well as in the later draws (5586.6 versus 5945.6 bp, p = 0.04). After adjusting for confounders, these differences persisted in both week 1 (adjusted beta -496.1, 95 % confidence interval [CI] -891.1, -101.1, p = 0.01) and beyond (adjusted beta -396.8; 95 % CI -727.2, -66.4. p = 0.02). Among the 15 participants who also had complete postpartum multiomics data available, there were predictive signatures of vaginal versus cesarean births in transcriptomics (cell-free [cf]RNA), metabolomics, microbiomics, and proteomics that did not persist after false discovery correction. CONCLUSION: Maternal LTLs in postpartum week 1 were nearly 500 bp shorter following cesarean. This difference persisted several weeks postpartum, even though other markers of inflammation had normalized. Mode of delivery should be considered in any analyses of postpartum LTLs and further investigation into this phenomenon is warranted.

Solving the Puzzle of Preterm Birth.

Solving the puzzle of preterm birth has been challenging and will require novel integrative solutions as preterm birth likely arises from many etiologies. It has been demonstrated that many sociodemographic and psychological determinants of preterm birth relate to its complex biology. It is this understanding that has enabled the development of a novel preventative strategy, which integrates the omics profile (genome, epigenome, transcriptome, proteome, metabolome, microbiome) with sociodemographic, environmental, and psychological determinants of individual pregnant people to solve the puzzle of preterm birth.

Predicting Preterm Birth Using Proteomics.

The complexity of preterm birth (PTB), both spontaneous and medically indicated, and its various etiologies and associated risk factors pose a significant challenge for developing tools to accurately predict risk. This review focuses on the discovery of proteomics signatures that might be useful for predicting spontaneous PTB or preeclampsia, which often results in PTB. We describe methods for proteomics analyses, proteomics biomarker candidates that have so far been identified, obstacles for discovering biomarkers that are sufficiently accurate for clinical use, and the derivation of composite signatures including clinical parameters to increase predictive power.

Outcome of Pregnancy Oral Glucose Tolerance Test and Preterm Birth.

BACKGROUND: Gestational diabetes is associated with adverse outcomes such as preterm birth (<37 weeks). However, there is no international consensus on screening criteria or diagnostic levels for gestational diabetes, and it is unknown whether body mass index (BMI) or obesity modifies the relation between glucose level and preterm birth. METHODS: We studied a pregnancy cohort restricted to two Danish regions from the linked Danish Medical Birth Register to study associations between glucose measurements from the 2-hour postload 75-g oral glucose tolerance test (one-step approach) and preterm birth from 2004 to 2018. In Denmark, gestational diabetes screening is a targeted strategy for mothers with identified risk factors. We used Poisson regression to estimate rate ratios (RR) of preterm birth with z-standardized glucose measurements. We assessed effect measure modification by stratifying analyses and testing for heterogeneity. RESULTS: Among 11,337 pregnancies (6.2% delivered preterm), we observed an adjusted preterm birth RR of 1.2 (95% confidence interval [CI] = 1.1, 1.3) for a one-standard deviation glucose increase of 1.4 mmol/l from the mean of 6.7 mmol/l. There was evidence for effect measure modification by obesity, for example, adjusted RR for nonobese (BMI, <30): 1.2 (95% CI = 1.1, 1.3) versus obese (BMI, ≥30): 1.3 (95% CI = 1.2-1.5), P = 0.05 for heterogeneity. CONCLUSION: Among mothers screened for gestational diabetes, increased glucose levels, even those below the diagnostic level for gestational diabetes in Denmark, were associated with increased preterm birth risk. Obesity (BMI, ≥30) may be an effect measure modifier, not just a confounder, of the relation between blood glucose and preterm birth risk.

Is it time for a precision health approach to the management of newborn hyperbilirubinemia?

Newborn hyperbilirubinemia during the first two weeks of life is one of most common problems requiring management decisions by a pediatrician. However, high bilirubin levels in the circulation have been associated with neurologic injury under a variety of conditions encountered in the newborn infant, such as hemolysis. The risk for developing dangerous hyperbilirubinemia is multifactorial and is determined by a complex set of factors related to a newborn infant's genetic capacities as well as intra- and extrauterine exposures. To this end, a precision health approach based on the integration of prenatal genetic and postnatal diagnostic measures might improve the management of neonatal hyperbilirubinemia.

Vascular health years after a hypertensive disorder of pregnancy: The EPOCH study.

BACKGROUND: Preeclampsia is associated with a two-fold increase in a woman's lifetime risk of developing atherosclerotic cardiovascular disease (ASCVD), but the reasons for this association are uncertain. The objective of this study was to examine the associations between vascular health and a hypertensive disorder of pregnancy among women ≥ 2 years postpartum. METHODS: Pre-menopausal women with a history of either a hypertensive disorder of pregnancy (cases: preeclampsia or gestational hypertension) or a normotensive pregnancy (controls) were enrolled. Participants were assessed for standard ASCVD risk factors and underwent vascular testing, including measurements of blood pressure, endothelial function, and carotid artery ultrasound. The primary outcomes were blood pressure, ASCVD risk, reactive hyperemia index measured by EndoPAT and carotid intima-medial thickness. The secondary outcomes were augmentation index normalized to 75 beats per minute and pulse wave amplitude measured by EndoPAT, and carotid elastic modulus and carotid beta-stiffness measured by carotid ultrasound. RESULTS: Participants had a mean age of 40.7 years and were 5.7 years since their last pregnancy. In bivariate analyses, cases (N = 68) were more likely than controls (N = 71) to have hypertension (18% vs 4%, P = .034), higher calculated ASCVD risk (0.6 vs 0.4, P = .02), higher blood pressures (systolic: 118.5 vs 111.6 mm Hg, P = .0004; diastolic: 75.2 vs 69.8 mm Hg, P = .0004), and higher augmentation index values (7.7 vs 2.3, P = .03). They did not, however, differ significantly in carotid intima-media thickness (0.5 vs 0.5, P = .29) or reactive hyperemia index (2.1 vs 2.1, P = .93), nor in pulse wave amplitude (416 vs 326, P = .11), carotid elastic modulus (445 vs 426, P = .36), or carotid beta stiffness (2.8 vs 2.8, P = .86). CONCLUSION: Women with a prior hypertensive disorder of pregnancy had higher ASCVD risk and blood pressures several years postpartum, but did not have more endothelial dysfunction or subclinical atherosclerosis.

Identifying therapeutic candidates for endometriosis through a transcriptomics-based drug repositioning approach.

Existing medical treatments for endometriosis-related pain are often ineffective, underscoring the need for new therapeutic strategies. In this study, we applied a computational drug repurposing pipeline to stratified and unstratified disease signatures based on endometrial gene expression data to identify potential therapeutics from existing drugs, based on expression reversal. Of 3,131 unique genes differentially expressed by at least one of six endometriosis signatures, only 308 (9.8%) were in common; however, 221 out of 299 drugs identified, (73.9%) were shared. We selected fenoprofen, an uncommonly prescribed NSAID that was the top therapeutic candidate for further investigation. When testing fenoprofen in an established rat model of endometriosis, fenoprofen successfully alleviated endometriosis-associated vaginal hyperalgesia, a surrogate marker for endometriosis-related pain. These findings validate fenoprofen as a therapeutic that could be utilized more frequently for endometriosis and suggest the utility of the aforementioned computational drug repurposing approach for endometriosis.

Integrating evidence and causal mapping of factors that influence medication decision-making by pregnant women at risk of hypertensive disorder: protocol for a scoping review.

INTRODUCTION: In 2018, the American College of Obstetricians and Gynecologists recommended low-dose aspirin to prevent the onset of pre-eclampsia among women who were at high risk. Factors influencing women's acceptance of this recommendation span multiple sectors and levels. Understanding how these factors interact will help stakeholders design effective population-level intervention strategies. Our study aims to identify and map relationships among factors influencing the medication decisions of pregnant women at risk of hypertensive disorders. METHODS AND ANALYSIS: Preferred Reporting Items for Systematic Reviews and Meta-Analyses for Scoping Reviews (PRISMA-ScR) guidelines will be followed for this review. A research librarian developed a comprehensive search strategy to retrieve published and unpublished English studies after 1 January 1980, involving factors that influence pregnant women's uptake and adherence to medication for gestational hypertensive disorders. This literature includes perceptions, patterns, acceptance, refusal, tendencies, probability and service utilisation. We will search PubMed, Embase, Web of Science and CINAHL. Reference lists of the selected papers will be searched manually to identify more relevant studies. A two-stage independent screening, consisting of title and abstract screening, followed by full-text screening, will be conducted by two independent reviewers to identify eligible articles. Extracted data will be recorded in a customised variable extraction form and input into a Microsoft Access database. The PRISMA-ScR will be used to guide the presentation of the results, which will be presented in a table and causal map to demonstrate the relationships between extracted variables and medication uptake and adherence. A conceptual simulation model will be formulated to validate the logic of the relationships between variables and identify knowledge gaps. Lastly, experts and stakeholders will be invited to critique and comment on the results. ETHICS AND DISSEMINATION: This study does not require ethical approval. The full review results will be presented at a relevant conference and submitted to a peer-reviewed scientific journal for publication.

Large-scale proteomics in the first trimester of pregnancy predict psychopathology and temperament in preschool children: an exploratory study.

BACKGROUND: Understanding the prenatal origins of children's psychopathology is a fundamental goal in developmental and clinical science. Recent research suggests that inflammation during pregnancy can trigger a cascade of fetal programming changes that contribute to vulnerability for the emergence of psychopathology. Most studies, however, have focused on a handful of proinflammatory cytokines and have not explored a range of prenatal biological pathways that may be involved in increasing postnatal risk for emotional and behavioral difficulties. METHODS: Using extreme gradient boosted machine learning models, we explored large-scale proteomics, considering over 1,000 proteins from first trimester blood samples, to predict behavior in early childhood. Mothers reported on their 3- to 5-year-old children's (N = 89, 51% female) temperament (Child Behavior Questionnaire) and psychopathology (Child Behavior Checklist). RESULTS: We found that machine learning models of prenatal proteomics predict 5%-10% of the variance in children's sadness, perceptual sensitivity, attention problems, and emotional reactivity. Enrichment analyses identified immune function, nervous system development, and cell signaling pathways as being particularly important in predicting children's outcomes. CONCLUSIONS: Our findings, though exploratory, suggest processes in early pregnancy that are related to functioning in early childhood. Predictive features included far more proteins than have been considered in prior work. Specifically, proteins implicated in inflammation, in the development of the central nervous system, and in key cell-signaling pathways were enriched in relation to child temperament and psychopathology measures.

Discovery of sparse, reliable omic biomarkers with Stabl.

Adoption of high-content omic technologies in clinical studies, coupled with computational methods, has yielded an abundance of candidate biomarkers. However, translating such findings into bona fide clinical biomarkers remains challenging. To facilitate this process, we introduce Stabl, a general machine learning method that identifies a sparse, reliable set of biomarkers by integrating noise injection and a data-driven signal-to-noise threshold into multivariable predictive modeling. Evaluation of Stabl on synthetic datasets and five independent clinical studies demonstrates improved biomarker sparsity and reliability compared to commonly used sparsity-promoting regularization methods while maintaining predictive performance; it distills datasets containing 1,400-35,000 features down to 4-34 candidate biomarkers. Stabl extends to multi-omic integration tasks, enabling biological interpretation of complex predictive models, as it hones in on a shortlist of proteomic, metabolomic and cytometric events predicting labor onset, microbial biomarkers of pre-term birth and a pre-operative immune signature of post-surgical infections. Stabl is available at https://github.com/gregbellan/Stabl .

Integrative analysis of noncoding mutations identifies the druggable genome in preterm birth.

Preterm birth affects ~10% of pregnancies in the US. Despite familial associations, identifying at-risk genetic loci has been challenging. We built deep learning and graphical models to score mutational effects at base resolution via integrating the pregnant myometrial epigenome and large-scale patient genomes with spontaneous preterm birth (sPTB) from European and African American cohorts. We uncovered previously unidentified sPTB genes that are involved in myometrial muscle relaxation and inflammatory responses and that are regulated by the progesterone receptor near labor onset. We studied genomic variants in these genes in our recruited pregnant women administered progestin prophylaxis. We observed that mutation burden in these genes was predictive of responses to progestin treatment for preterm birth. To advance therapeutic development, we screened ~4000 compounds, identified candidate molecules that affect our identified genes, and experimentally validated their therapeutic effects on regulating labor. Together, our integrative approach revealed the druggable genome in preterm birth and provided a generalizable framework for studying complex diseases.

Microbiome preterm birth DREAM challenge: Crowdsourcing machine learning approaches to advance preterm birth research.

Every year, 11% of infants are born preterm with significant health consequences, with the vaginal microbiome a risk factor for preterm birth. We crowdsource models to predict (1) preterm birth (PTB; <37 weeks) or (2) early preterm birth (ePTB; <32 weeks) from 9 vaginal microbiome studies representing 3,578 samples from 1,268 pregnant individuals, aggregated from public raw data via phylogenetic harmonization. The predictive models are validated on two independent unpublished datasets representing 331 samples from 148 pregnant individuals. The top-performing models (among 148 and 121 submissions from 318 teams) achieve area under the receiver operator characteristic (AUROC) curve scores of 0.69 and 0.87 predicting PTB and ePTB, respectively. Alpha diversity, VALENCIA community state types, and composition are important features in the top-performing models, most of which are tree-based methods. This work is a model for translation of microbiome data into clinically relevant predictive models and to better understand preterm birth.

The placental vasculature is affected by changes in gene expression and glycogen-rich cells in a diet-induced obesity mouse model.

Maternal obesity is a risk factor for pregnancy complications. Obesity caused by a high-fat diet (HFD) may alter maternal glucose/glycogen metabolism. Here, our objective was to investigate whether the placental vasculature is altered via changes in gene expression and glycogen-rich cells using a preclinical mouse model of diet-induced obesity. We subjected female FVB/N mice to one of three feeding regimens: regular chow (RC) given at preconception and during pregnancy (Control); RC given at preconception and then a HFD during pregnancy (HFD-P); or HFD initiated 4 weeks preconception and during pregnancy (HFD-PreCP). Daily food consumption and weekly maternal weights were recorded. Maternal blood glucose levels were measured at preconception and 4 gestational epochs (E6.5-E9.5, E10.5-E12.5, E13.5-E15.5, E16.5-E19.5). At E8.5-E16.5, total RNA in placentas were isolated for gene expression analyses. Placentas were also collected for HE and periodic acid Schiff's (PAS) staining and glycogen content assays. Dams in the HFD-P and HFD-PreCP groups gained significantly more weight than controls. Pre- and antenatal glucose levels were also significantly higher (15%-30%) in HFD-PreCP dams. Expression of several placental genes were also altered in HFD dams compared with controls. Consumption of the HFD also led to phenotypic and morphologic changes in glycogen trophoblasts (GlyTs) and uterine natural killer (uNK) cells. Alterations in vascularity were also observed in the labyrinth of HFD-PreCP placentas, which correlated with decreased placental efficiency. Overall, we observed that a HFD induces gestational obesity in mice, alters expression of placental genes, affects glucose homeostasis, and alters glycogen-positive GlyTs and uNK cells. All these changes may lead to impaired placental vascular development, and thus heighten the risk for pregnancy complications.

Deep representation learning identifies associations between physical activity and sleep patterns during pregnancy and prematurity.

Preterm birth (PTB) is the leading cause of infant mortality globally. Research has focused on developing predictive models for PTB without prioritizing cost-effective interventions. Physical activity and sleep present unique opportunities for interventions in low- and middle-income populations (LMICs). However, objective measurement of physical activity and sleep remains challenging and self-reported metrics suffer from low-resolution and accuracy. In this study, we use physical activity data collected using a wearable device comprising over 181,944 h of data across N = 1083 patients. Using a new state-of-the art deep learning time-series classification architecture, we develop a 'clock' of healthy dynamics during pregnancy by using gestational age (GA) as a surrogate for progression of pregnancy. We also develop novel interpretability algorithms that integrate unsupervised clustering, model error analysis, feature attribution, and automated actigraphy analysis, allowing for model interpretation with respect to sleep, activity, and clinical variables. Our model performs significantly better than 7 other machine learning and AI methods for modeling the progression of pregnancy. We found that deviations from a normal 'clock' of physical activity and sleep changes during pregnancy are strongly associated with pregnancy outcomes. When our model underestimates GA, there are 0.52 fewer preterm births than expected (P = 1.01e - 67, permutation test) and when our model overestimates GA, there are 1.44 times (P = 2.82e - 39, permutation test) more preterm births than expected. Model error is negatively correlated with interdaily stability (P = 0.043, Spearman's), indicating that our model assigns a more advanced GA when an individual's daily rhythms are less precise. Supporting this, our model attributes higher importance to sleep periods in predicting higher-than-actual GA, relative to lower-than-actual GA (P = 1.01e - 21, Mann-Whitney U). Combining prediction and interpretability allows us to signal when activity behaviors alter the likelihood of preterm birth and advocates for the development of clinical decision support through passive monitoring and exercise habit and sleep recommendations, which can be easily implemented in LMICs.