Maternal Vulnerability Indicators Derived from Free-Text Clinical Documentation in Adolescent Pregnancy.

Background and

Objectives

Adolescent pregnancy is associated with biological, behavioral, and healthcare-related vulnerabilities that are incompletely captured by structured datasets. This study aimed to characterize selected maternal vulnerability indicators derived from narrative clinical documentation and to examine their exploratory associations with documented prenatal care deficiency and neonatal outcomes. Materials and

Methods

We conducted a retrospective cohort study including 759 singleton adolescent pregnancies managed at a Romanian secondary obstetric center between 2020 and 2024. Narrative clinical observations were reviewed to extract maternal vulnerability indicators, including smoking, anemia, infection, hypertensive disorders, obesity, Rh incompatibility, and documented prenatal care deficiency. Associations between extracted variables, documented prenatal care deficiency, and neonatal outcomes were evaluated using contingency analyses, Kendall's tau-b correlations, and multivariable logistic regression models.

Results

Among pregnancies with available narrative observations, documented prenatal care deficiency was identified in 612/692 (88.4%), maternal anemia in 207/692 (29.9%), and smoking during pregnancy in 186/692 (26.9%). Validation performance differed across categories, with a sensitivity of 57.1% (95% CI 18.4-90.1%) for hypertensive disorders and wide confidence intervals for rare categories. Correlations between extracted variables were weak, indicating limited clustering of maternal risk factors. Hypertensive disorders (aOR 0.31, 95% CI 0.10-0.95, p = 0.038) and maternal obesity (aOR 0.39, 95% CI 0.16-0.98, p = 0.044) were associated with lower odds of documented prenatal care deficiency. Significant neonatal associations were observed primarily for low birth weight. Hypertensive disorders were independently associated with increased odds of low birth weight (aOR 3.56, 95% CI 1.33-9.54, p = 0.011), whereas documented maternal anemia was associated with lower observed odds of LBW (aOR 0.45, 95% CI 0.24-0.82, p = 0.009). No significant associations were identified for preterm birth or Apgar score < 7 at 5 min.

Conclusions

Narrative clinical documentation allowed the identification of heterogeneous maternal vulnerability indicators that showed weak interrelationships and selective associations with prenatal surveillance patterns and low birth weight. These exploratory findings should be interpreted in the context of healthcare engagement and documentation practices.