Implicit Framing in Obstetric Counseling Notes: A Grounded LLM Pipeline on a VBAC-Eligible Cohort

2026-04-24

AI Summary

This study addresses the implicit framing effects in obstetric counseling, where clinicians’ language regarding vaginal birth after cesarean (VBAC) versus repeat cesarean section (RCS) may influence patient decisions, yet large-scale, confounder-controlled textual analyses are lacking. The authors constructed a rigorously matched cohort of VBAC-eligible patients, free of medical contraindications, and innovatively integrated structured clinical data with large language model (LLM)-based extraction of verbatim evidence and zero-shot framing classification to systematically analyze linguistic patterns in counseling transcripts. Results demonstrate that RCS discussions significantly favored risk-oriented language, with statistically significant differences in framing distributions between VBAC and RCS consultations. This work presents the first interpretable, large-scale analysis of linguistic framing in obstetric decision-making, highlighting the potential of LLMs to enhance clinical decision support.

Technology Category

Natural Language Processing: Language Grounding & Multi-modal NLPComputer Vision: Language and VisionData Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval

Application Category

User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendationResponsible Web: Consent frameworks and practices on the webWeb Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Clinical framing -- the linguistic manner in which clinical information is presented -- can influence patient understanding and decision-making, with important implications for healthcare outcomes. Obstetrics is a high-stakes domain in which physicians counsel patients on delivery mode choices such as vaginal birth after cesarean (VBAC) and repeat cesarean section (RCS), yet counseling language remains underexplored in large-scale clinical text analysis. In this work, we analyze physician counseling language in 2,024 obstetric history and physical narratives for a rigorously defined cohort of patients for whom both VBAC and RCS were clinically viable options. To control for confounding due to medical contraindications, we first construct a VBAC-eligible cohort using structured clinical data supplemented by a large language model (LLM)-based extraction pipeline constrained to grounded, verbatim evidence from free-text narratives. We then apply a zero-shot LLM framework to categorize counseling segments into predefined framing categories capturing how physicians linguistically present delivery options. Our analysis reveals a significant difference in counseling framing distributions between VBAC and RCS notes; risk-focused language accounts for a substantially larger share of counseling segments in RCS documentation than in VBAC, with category-level differences confirmed by statistical testing, highlighting the value of controlled LLM-based framing analysis in obstetric care.

Problem

• clinical framing
• obstetric counseling
• VBAC
• language bias
• healthcare communication

Innovation

• grounded LLM pipeline
• implicit framing
• VBAC-eligible cohort
• zero-shot LLM
• clinical language analysis