Data Augmentation for Classification of Negative Pregnancy Outcomes in Imbalanced Data

TL;DR

The paper addresses the challenge of studying negative pregnancy outcomes in imbalanced data by leveraging publicly available Twitter data and an NLP pipeline to automatically identify term pregnancies with normal birth weight (positives) versus adverse outcomes (negatives). It systematically investigates data augmentation strategies, including GPT-3.5-based generation and prompt engineering, to balance the minority negative class and assess their impact on classifier performance. A rules-based layer is integrated with transformer models (notably BERT) to further boost prediction accuracy. Results show strong performance for positive outcomes (e.g., BERT Large Uncased F1 ≈ 0.96) but ongoing difficulty for negative outcomes, demonstrating the viability of social-media data for maternal health epidemiology while highlighting areas for improvement such as semantic understanding and multimodal data integration.

Abstract

Infant mortality remains a significant public health concern in the United States, with birth defects identified as a leading cause. Despite ongoing efforts to understand the causes of negative pregnancy outcomes like miscarriage, stillbirths, birth defects, and premature birth, there is still a need for more comprehensive research and strategies for intervention. This paper introduces a novel approach that uses publicly available social media data, especially from platforms like Twitter, to enhance current datasets for studying negative pregnancy outcomes through observational research. The inherent challenges in utilizing social media data, including imbalance, noise, and lack of structure, necessitate robust preprocessing techniques and data augmentation strategies. By constructing a natural language processing (NLP) pipeline, we aim to automatically identify women sharing their pregnancy experiences, categorizing them based on reported outcomes. Women reporting full gestation and normal birth weight will be classified as positive cases, while those reporting negative pregnancy outcomes will be identified as negative cases. Furthermore, this study offers potential applications in assessing the causal impact of specific interventions, treatments, or prenatal exposures on maternal and fetal health outcomes. Additionally, it provides a framework for future health studies involving pregnant cohorts and comparator groups. In a broader context, our research showcases the viability of social media data as an adjunctive resource in epidemiological investigations about pregnancy outcomes.

Figures (5)

• Figure 1: The proposed methodology
• Figure 2: Traditional Data augmentation and F1 Score trend
• Figure 3: Data augmentation of minor class and F1 Score trend
• Figure 4:
• Figure 5: Rules-Based + Normal Model vs. Conventional Model