Samantha N. Piekos

The placenta is essential for pregnancy, and its dysfunction can harm both mother and fetus. To better understand placental physiology and its disruption in disease, we employ a multiomics approach (transcriptomics, metabolomics, and proteomics) combined with clinical data and histopathology from 321 placentas across conditions: severe fetal growth restriction (FGR), FGR with hypertension (FGR + HDP), severe preeclampsia (PE), and spontaneous preterm delivery (PTD). Cellular deconvolution reveals FGR + HDP placentas have more extravillous trophoblasts than controls (p < 0.0001). After adjusting for fetal sex and gestational age, we build condition-specific interomics networks and detect communities (a.k.a. subnetworks). In a control community, miR-365a-3p is the most connected node, whereas in FGR + HDP placentas, it is hypoxia-induced miR-210-3p. From this community, we identify a signature containing mRNAs implicated in placental dysfunction (e.g. FLT1, FSTL3, HTRA4, LEP, and PHYHIP), which distinguishes FGR + HDP placentas from those with other conditions, illustrating the power of interomics in understanding obstetric syndromes.

Background: Social determinants of health (SDoH) such as housing insecurity are known to be intricately linked to patients’ health status. More efficient methods for abstracting structured data on SDoH can help accelerate the inclusion of exposome variables in biomedical research and support health care systems in identifying patients who could benefit from proactive outreach. Large language models (LLMs) developed from Generative Pre-trained Transformers (GPTs) have shown potential for performing complex abstraction tasks on unstructured clinical notes. Objective: Here, we assess the performance of GPTs on identifying temporal aspects of housing insecurity and compare results between both original and deidentified notes. Methods: We compared the ability of GPT-3.5 and GPT-4 to identify instances of both current and past housing instability, as well as general housing status, from 25,217 notes from 795 pregnant women. Results were compared with manual abstraction, a named entity recognition model, and regular expressions. Results: Compared with GPT-3.5 and the named entity recognition model, GPT-4 had the highest performance and had a much higher recall (0.924) than human abstractors (0.702) in identifying patients experiencing current or past housing instability, although precision was lower (0.850) compared with human abstractors (0.971). GPT-4’s precision improved slightly (0.936 original, 0.939 deidentified) on deidentified versions of the same notes, while recall dropped (0.781 original, 0.704 deidentified). Conclusions: This work demonstrates that while manual abstraction is likely to yield slightly more accurate results overall, LLMs can provide a scalable, cost-effective solution with the advantage of greater recall. This could support semiautomated abstraction, but given the potential risk for harm, human review would be essential before using results for any patient engagement or care decisions. Furthermore, recall was lower when notes were deidentified prior to LLM abstraction.

The placenta is essential for a healthy pregnancy, and placental pathology can endanger both maternal and fetal health. Placental function is affected by dynamic, complex, and interconnected molecular, cellular, and environmental events; therefore, we need a systems biology approach to study disease in normal physiological placenta function. We use placental multiomics (short and bulk transcriptomics, untargeted metabolomics, and targeted proteomics) paired with clinical data and placental histopathology reports from 321 placentas across multiple obstetric conditions: fetal growth restriction (FGR), FGR with pregnancy-related hypertension (FGR+HDP), preeclampsia (PE), and spontaneous preterm delivery (PTD). We first performed cellular deconvolution to estimate cell type numbers from bulk transcriptomes: FGR+HDP placentas were the most different from control placentas driven by a higher estimated number of extravillous trophoblast (p<0.0001). Next, we evaluated the impact of fetal sex and gestational age on analyte levels, adjusting for these confounders. We then generated obstetric condition-specific correlation networks and identified communities of related analytes associated with physiology and disease. We demonstrated how network connectivity and its disruption in disease can be used to identify signatures unique to a clinical outcome. We examined a community defined in control placentas for which the most connected node was miR-365a-3p in contrast to the corresponding community in FGR+HDP placentas for which the most connected node was hypoxia-induced miR-210-3p. From this community, we identified a signature containing mRNA transcripts implicated in placental dysfunction (e.g. FLT1, FSTL3, HTRA4, LEP, and PHYHIP). This signature distinguishes between FGR+HDP placentas and placentas of differing clinical outcomes in high-dimensional space. These findings illustrate the power of systems biology-driven interomics network analysis in a single tissue type, laying the groundwork for future multi-tissue studies.

BACKGROUND Social determinants of health (SDoH) such as housing insecurity are known to be intricately linked to patients’ health status. More efficient methods for abstracting structured data on SDoH can help accelerate the inclusion of exposome variables in biomedical research and support health care systems in identifying patients who could benefit from proactive outreach. Large language models (LLMs) developed from Generative Pre-trained Transformers (GPTs) have shown potential for performing complex abstraction tasks on unstructured clinical notes. OBJECTIVE Here, we assess the performance of GPTs on identifying temporal aspects of housing insecurity and compare results between both original and deidentified notes. METHODS We compared the ability of GPT-3.5 and GPT-4 to identify instances of both current and past housing instability, as well as general housing status, from 25,217 notes from 795 pregnant women. Results were compared with manual abstraction, a named entity recognition model, and regular expressions. RESULTS Compared with GPT-3.5 and the named entity recognition model, GPT-4 had the highest performance and had a much higher recall (0.924) than human abstractors (0.702) in identifying patients experiencing current or past housing instability, although precision was lower (0.850) compared with human abstractors (0.971). GPT-4’s precision improved slightly (0.936 original, 0.939 deidentified) on deidentified versions of the same notes, while recall dropped (0.781 original, 0.704 deidentified). CONCLUSIONS This work demonstrates that while manual abstraction is likely to yield slightly more accurate results overall, LLMs can provide a scalable, cost-effective solution with the advantage of greater recall. This could support semiautomated abstraction, but given the potential risk for harm, human review would be essential before using results for any patient engagement or care decisions. Furthermore, recall was lower when notes were deidentified prior to LLM abstraction.

Social Determinants of Health (SDoH) are an important part of the exposome and are known to have a large impact on variation in health outcomes. In particular, housing stability is known to be intricately linked to a patient’s health status, and pregnant women experiencing housing instability (HI) are known to have worse health outcomes. Most SDoH information is stored in electronic health records (EHRs) as free text (unstructured) clinical notes, which traditionally required natural language processing (NLP) for automatic identification of relevant text or keywords. A patient’s housing status can be ambiguous or subjective, and can change from note to note or within the same note, making it difficult to use existing NLP solutions. New developments in NLP allow researchers to prompt LLMs to perform complex, subjective annotation tasks that require reasoning that previously could only be attempted by human annotators. For example, large language models (LLMs) such as GPT (Generative Pre-trained Transformer) enable researchers to analyze complex, unstructured data using simple prompts. We used a secure platform within a large healthcare system to compare the ability of GPT-3.5 and GPT-4 to identify instances of both current and past housing instability, as well as general housing status, from 25,217 notes from 795 pregnant women. Results from these LLMs were compared with results from manual annotation, a named entity recognition (NER) model, and regular expressions (RegEx). We developed a chain-of-thought prompt requiring evidence and justification for each note from the LLMs, to help maximize the chances of finding relevant text related to HI while minimizing hallucinations and false positives. Compared with GPT-3.5 and the NER model, GPT-4 had the highest performance and had a much higher recall (0.924) than human annotators (0.702) in identifying patients experiencing current or past housing instability, although precision was lower (0.850) compared with human annotators (0.971). In most cases, the evidence output by GPT-4 was similar or identical to that of human annotators, and there was no evidence of hallucinations in any of the outputs from GPT-4. Most cases where the annotators and GPT-4 differed were ambiguous or subjective, such as “living in an apartment with too many people”. We also looked at GPT-4 performance on de-identified versions of the same notes and found that precision improved slightly (0.936 original, 0.939 de-identified), while recall dropped (0.781 original, 0.704 de-identified). This work demonstrates that, while manual annotation is likely to yield slightly more accurate results overall, LLMs, when compared with manual annotation, provide a scalable, cost-effective solution with the advantage of greater recall. At the same time, further evaluation is needed to address the risk of missed cases and bias in the initial selection of housing-related notes. Additionally, while it was possible to reduce confabulation, signs of unusual justifications remained. Given these factors, together with changes in both LLMs and charting over time, this approach is not yet appropriate for use as a fully-automated process. However, these results demonstrate the potential for using LLMs for computer-assisted annotation with human review, reducing cost and increasing recall. More efficient methods for obtaining structured SDoH data can help accelerate inclusion of exposome variables in biomedical research, and support healthcare systems in identifying patients who could benefit from proactive outreach.

Objective: We applied propensity score matching method at scale on patient records to confirm signals of known drug effects on preterm birth and detect previously unidentified potential drug effects. Materials and Methods: This was a retrospective study on women who had continuity of care at Providence St. Joseph Health (PSJH) both before and after pregnancy and delivered live births between 2013/01/01 and 2022/12/31 (n=365,075). Our exposures of interest were all outpatient medications prescribed during pregnancy. We limited our analyses to medication that met the minimal sample size (n=600). The primary outcome of interest was preterm birth. Secondary outcomes of interest were small for gestational age and low birth weight. We used propensity score matching at scale to evaluate the risk of these adverse pregnancy outcomes associated with drug exposure after adjusting for demographics, pregnancy characteristics, and comorbidities. Results: The total medication prescription rate increased from 58.5% to 75.3% ( P <0.0001) from 2013 to 2022. The prevalence rate of preterm birth was 7.7%. 175 out of 1329 prenatally prescribed outpatient medications met the minimum sample size. We identified 58 medications statistically significantly associated with the risk of preterm birth (P≤0.1; decreased: 12, increased: 46). Discussion: We narrowed down from 1329 medications to 58 medications that showed statistically significant association with the risk of preterm birth even after addressing numerous covariates through propensity score matching. Conclusion: This data-driven approach demonstrated that multiple testable hypotheses in pregnancy pharmacology can be prioritized at scale, laying the foundation for application in other pregnancy outcomes.

There is uncertainty around the safety of SSRIs for treating depression during pregnancy. Nevertheless, the use of SSRIs has been gradually increasing, especially during the COVID-19 pandemic period. We aimed to (1) characterize maternal depression rate and use of SSRIs in a recent 10-year period, (2) address confounding by indication, as well as socioeconomic and environmental factors, and (3) evaluate associations of the timing of SSRI exposure in pregnancy with risk for preterm birth (PTB), low birthweight (LBW), and small for gestational age (SGA) infants among women with depression before pregnancy. We conducted propensity score-adjusted regression to calculate odds ratios (ORs) of PTB, LBW, and SGA. We accounted for maternal/pregnancy characteristics, comorbidity, depression severity, time of delivery, social vulnerability, and rural residence. There were 50.3% and 40.3% increases in the prevalence rate of prenatal depression and prenatal SSRI prescription rate during the pandemic. We identified women with depression ≤180 days before pregnancy (n = 8406). Women with no SSRI order during pregnancy (n = 3760) constituted the unexposed group. The late SSRI exposure group consisted of women with an SSRI order after the first trimester (n = 3759). The early-only SSRI exposure group consisted of women with SSRI orders only in the first trimester (n = 887). The late SSRI exposure group had an increased risk of PTB of OR = 1.5 ([1.2,1.8]) and LBW of OR = 1.5 ([1.2,2.0]), relative to the unexposed group. Associations between late SSRI exposure and risk of PTB/LBW were similar among a subsample of patients who delivered during the pandemic. These findings suggest an association between PTB/LBW and SSRI exposure is dependent on exposure timing during pregnancy. Small for gestational age is not associated with SSRI exposure.

Background Immune-mediated inflammatory diseases (IMIDs) are likely to complicate maternal health. However, literature data on patients with IMIDs undergoing pregnancy is scarce and often overlooks the impact of comorbidities. Methods We investigated 12 selected IMIDs: psoriasis, inflammatory bowel disease, rheumatoid arthritis, spondyloarthritis, multiple sclerosis, systemic lupus erythematosus, psoriatic arthritis, antiphospholipid syndrome, Sjögren’s syndrome, vasculitis, sarcoidosis, systemic sclerosis. We characterized patients with IMIDs prior to pregnancy (IMIDs group) based on pregnancy/maternal characteristics, comorbidities, and pre-pregnancy/prenatal immunomodulatory medications (IMMs) prescription patterns. We 1:1 propensity score matched the IMIDs cohort with people who had no IMID diagnoses prior to pregnancy (non-IMIDs cohort). Outcome measures were preterm birth (PTB), low birth weight (LBW), small for gestational age (SGA), and cesarean section. Findings The prevalence rate of pregnancy occurring with people with a previous IMID diagnosis has doubled in the past ten years. We identified 5,784 patients with IMIDs. 17% of the IMIDs group had at least one prenatal IMM prescription. Depending on the type of IMM, from 48% to 70% of the patients taking IMMs before pregnancy continued them throughout pregnancy. Patients with IMIDs had similar but slightly increased risks of PTB (Relative risk (RR)=1·1[1·0, 1·3]), LBW (RR=1·2 [1·0,1·4]), SGA (RR=1·1 [1·0,1·2]), and cesarean section (RR=1·1 [1·1,1·2]) compared to a matched cohort of people without IMIDs. Out of the 12 selected IMIDs, three for PTB, one for LBW, two for SGA, and six for cesarean section had results supporting increased risk. Interpretation The association between IMIDs and the increased risk of adverse pregnancy outcomes depend on both the nature of the IMID and the presence of comorbidities. Funding NIH

Background: Both COVID-19 and pregnancy are associated with hypercoagulability. Due to the increased risk for thrombosis, the United States National Institute of Health’s recommendation for prophylactic anticoagulant use for pregnant patients has expanded from patients hospitalized for severe COVID-19 manifestation to all patients hospitalized for the manifestation of COVID-19 (no guideline: before December 26, 2020; first update: December 27, 2022; second update: February 24, 2022-present). However, no study has evaluated this recommendation. Objective: The objective of this study was to characterize prophylactic anticoagulant use among hospitalized pregnant people with COVID-19 from March 20, 2020, to October 19, 2022. Methods: This was a retrospective cohort study in large US health care systems across 7 states. The cohort of interest was pregnant patients who were hospitalized with COVID-19, without previous coagulopathy or contraindication to anticoagulants (n=2767). The treatment group consisted of patients prescribed prophylactic dose anticoagulation between 2 days before and 14 days after COVID-19 treatment onset (n=191). The control group was patients with no anticoagulant exposure between 14 days before and 60 days after COVID-19 treatment onset (n=2534). We ascertained the use of prophylactic anticoagulants with attention to the updates in guidelines and emerging SARS-CoV-2 variants. We propensity score matched the treatment and control group 1:1 on the most important features contributing to the prophylactic anticoagulant administration status classification. Outcome measures included coagulopathy, bleeding, COVID-19–related complications, and maternal-fetal health outcomes. Additionally, the inpatient anticoagulant administration rate was validated in a nationwide population from Truveta, a collective of 700 hospitals across the United States. Results: The overall administration rate of prophylactic anticoagulants was 7% (191/2725). It was lowest after the second guideline update (no guideline: 27/262, 10%; first update: 145/1663, 8.72%; second update: 19/811, 2.3%; P<.001) and during the omicron-dominant period (Wild type: 45/549, 8.2%; Alpha: 18/129, 14%; Delta: 81/507, 16%; and Omicron: 47/1551, 3%; P<.001). Models developed on retrospective data showed that the variable most associated with the administration of inpatient prophylactic anticoagulant was comorbidities prior to SARS-CoV-2 infection. The patients who were administered prophylactic anticoagulant were also more likely to receive supplementary oxygen (57/191, 30% vs 9/188, 5%; P<.001). There was no statistical difference in a new diagnosis of coagulopathy, bleeding, or maternal-fetal health outcomes between those who received treatment and the matched control group. Conclusions: Most hospitalized pregnant patients with COVID-19 did not receive prophylactic anticoagulants across health care systems as recommended by guidelines. Guideline-recommended treatment was administered more frequently to patients with greater COVID-19 illness severity. Given the low rate of administration and differences between treated and untreated cohorts, efficacy could not be assessed.

Purpose There is uncertainty around the safety of SSRIs for treating depression during pregnancy. We aimed 1) to address confounding by indication, as well as socioeconomic and environmental factors associated with depression and 2) evaluate associations of timing of SSRI exposure in pregnancy with the risk of preterm birth and related outcomes (small for gestational age and low birthweight) among women with depression before pregnancy. Methods We conducted propensity score-adjusted regression to calculate odds ratios (OR) of preterm birth, small for gestational age, and low birth weight. We accounted for maternal/pregnancy characteristics, pre-pregnancy comorbidity/depression severity, social vulnerability, rural health disparity, and pre-natal depression severity. We additionally conducted a drug-specific analysis and assessed the impact of other classes of antidepressants within our cohort of interest. Results Among women with a history of depression, we identified women with indication of depression ≤ 180 days before pregnancy (n=6,408). Women with no SSRI order during pregnancy (n=3,122) constituted the unexposed group (no SSRI exposure group). The late SSRI exposure group consisted of women with an SSRI order after the first trimester (n=2,596). The early-only SSRI exposure group consisted of women with SSRI orders only in the first trimester (n=691). Late SSRI exposure group had an increased risk of preterm birth of OR=1.7 ([1.3,2.2], pConclusions These findings suggest associations between preterm birth/low birthweight and SSRI exposure is dependent on exposure timing during pregnancy. Small for gestational age is not associated with SSRI exposure.