Uterine leiomyomas cause heavy menstrual bleeding, anemia, and pregnancy loss in millions of women worldwide. Driver mutations in the transcriptional mediator complex subunit 12 (MED12) gene in uterine myometrial cells initiate 70% of leiomyomas that grow in a progesterone-dependent manner. We showed a distinct chromatin occupancy landscape of MED12 in mutant MED12 (mut-MED12) versus WT-MED12 leiomyomas. Integration of cistromic and transcriptomics data identified tryptophan 2,3-dioxygenase (TDO2) as the top mut-MED12 target gene that was significantly upregulated in mut-MED12 leiomyomas when compared with adjacent myometrium and WT-MED12 leiomyomas. TDO2 catalyzes the conversion of tryptophan to kynurenine, an aryl hydrocarbon receptor (AHR) ligand that we confirmed to be significantly elevated in mut-MED12 leiomyomas. Treatment of primary mut-MED12 leiomyoma cells with tryptophan or kynurenine stimulated AHR nuclear translocation, increased proliferation, inhibited apoptosis, and induced AHR-target gene expression, whereas blocking the TDO2/kynurenine/AHR pathway by siRNA or pharmacological treatment abolished these effects. Progesterone receptors regulated the expression of AHR and its target genes. In vivo, TDO2 expression positively correlated with the expression of genes crucial for leiomyoma growth. In summary, activation of the TDO2/kynurenine/AHR pathway selectively in mut-MED12 leiomyomas promoted tumor growth and may inform the future development of targeted treatments and precision medicine.

Perinatal depression is one of the most common medical complications during pregnancy and postpartum period, affecting 10% to 20% of pregnant individuals, with higher rates among Black and Latina women who are also less likely to be diagnosed and treated. Machine learning (ML) models based on electronic medical records (EMRs) have effectively predicted postpartum depression in middle-class White women but have rarely included sufficient proportions of racial/ethnic minorities, which has contributed to biases in ML models. Our goal is to determine whether ML models could predict depression in early pregnancy in racial/ethnic minority women by leveraging EMR data. We extracted EMRs from a large U.S. urban hospital serving mostly low-income Black and Hispanic women (n = 5875). Depressive symptom severity was assessed using the Patient Health Questionnaire-9 self-report questionnaire. We investigated multiple ML classifiers using Shapley additive explanations for model interpretation and determined prediction bias with 4 metrics: disparate impact, equal opportunity difference, and equalized odds (standard deviations of true positives and false positives). Although the best-performing ML model's (elastic net) performance was low (area under the receiver operating characteristic curve = 0.61), we identified known perinatal depression risk factors such as unplanned pregnancy and being single and underexplored factors such as self-reported pain, lower prenatal vitamin intake, asthma, carrying a male fetus, and lower platelet levels. Despite the sample comprising mostly low-income minority women (54% Black, 27% Latina), the model performed worse for these communities (area under the receiver operating characteristic curve: 57% Black, 59% Latina women vs. 64% White women). EMR-based ML models could moderately predict early pregnancy depression but exhibited biased performance against low-income minority women.

INTRODUCTION: Diet and decreased gut microbiome diversity has been associated with acute pancreatitis (AP) risk. However, differences in dietary intake, gut microbiome, and their impact on microbial end metabolites have not been studied in AP. We aimed to determine differences in (i) dietary intake (ii) gut microbiome diversity and sulfidogenic bacterial abundance, and (iii) serum short-chain fatty acid (SCFA) and hydrogen sulfide (H₂S) concentrations in AP and control subjects. METHODS: This case-control study recruited 54 AP and 46 control subjects during hospitalization. Clinical and diet data and stool and blood samples were collected. 16S rDNA sequencing was used to determine gut microbiome alpha diversity and composition. Serum SCFA and H₂S levels were measured. Machine learning (ML) model was used to identify microbial targets associated with AP. RESULTS: AP patients had a decreased intake of vitamin D₃, whole grains, fish, and beneficial eicosapentaenoic, docosapentaenoic, and docosahexaenoic acids. AP patients also had lower gut microbiome diversity (P = 0.021) and a higher abundance of sulfidogenic bacteria including Veillonella sp. and Haemophilus sp., which were associated with AP risk. Serum acetate and H₂S concentrations were significantly higher in the AP group (P < 0.001 and P = 0.043, respectively). ML model had 96% predictive ability to distinguish AP patients from controls. DISCUSSION: AP patients have decreased beneficial nutrient intake and gut microbiome diversity. An increased abundance of H₂S-producing genera in the AP and SCFA-producing genera in the control group and predictive ability of ML model to distinguish AP patients indicates that diet, gut microbiota, and their end metabolites play a key role in AP.

Importance: Perinatal depression (PND) affects 10-20% of pregnant women, with significant racial disparities in prevalence, screening, and treatment. Neighborhood-level factors significantly influence PND risk, particularly among women of color, but current machine learning models using electronic medical records (EMRs) rarely incorporate neighborhood characteristics. Objective: To determine whether integrating neighborhood-level information with EMRs improves fairness in PND prediction while identifying key neighborhood factors influencing model bias across racial/ethnic groups. Design, Setting, and Participants: Study of 6,137 pregnant women who received care at a large urban academic hospital from 2010-2019, comprising 58% Non-Hispanic Black (NHB), 10% Non-Hispanic White (NHW), and 28% Hispanic (H) individuals, with depression status determined by PHQ-9 scores. Exposures: 125 neighborhood-level factors from Chicago Health Atlas merged with 61 EMR features based on residential location. Main Outcomes and Measures: Model performance (ROCAUC, PRAUC) and fairness metrics (disparate impact, equal opportunity difference, equalized odds). Feature importance analyzed using Shapley values and the impact of each neighborhood factor on model bias were evaluated. Results Models integrating neighborhood-level measures showed moderate predictive performance (ROCAUC: NHB 55%, NHW 57%, H 58%) while significantly improving fairness metrics compared to EMR-only models (p<0.05). Factors, such as suicide mortality rate and neighborhood safety rate, helped reduce bias. NHB women showed stronger correlations between PND risk factors and neighborhood variables compared to other groups. Most neighborhood factors had differential impacts across racial/ethnic groups, increasing bias for NHB women while reducing it for Hispanic women. Conclusions and Relevance: Incorporating neighborhood-level information enhances fairness in PND prediction while maintaining predictive capability. The differential impact of neighborhood factors across racial/ethnic groups highlights the importance of considering neighborhood context in clinical risk assessment to reduce disparities in prenatal depression care.

Chronic exposure to structural violence and environmental hazards may disrupt stress regulation, trigger inflammation, and impair iron metabolism in women. Iron deficiency has been associated with depression, but the combined impact of environmental stressors and anemia on maternal mental health remains understudied. We analyzed associations between 28 neighborhood-level environmental stressors, hemoglobin levels, and depressive symptoms (measured by the Patient Health Questionnaire-9) during early pregnancy, using retrospective data from 1964 pregnant patients (2015–2019) at an urban health center in Chicago. Demographic and residential data were linked to environmental indicators from the Chicago Health Atlas. Factor analysis reduced the environmental variables, and multivariable regression models examined associations with PHQ-9 scores at first pregnancy encounter. Participants were predominantly non-Hispanic Black (56%) and Hispanic (27%), with 13% anemic and 16% screening positive for depressive symptoms. Poverty, non-Hispanic Black race, single status, public or no insurance, and unemployment were associated with higher depressive symptoms. Among anemic individuals, neighborhood crime was significantly associated with depressive symptoms, while hemoglobin levels and gestational age were not. These findings highlight how environmental and social inequities contribute to maternal mental health disparities and support the need for integrated, equity-focused prenatal care interventions.