EndoExtract: Co-Designing Structured Text Extraction from Endometriosis Ultrasound Reports

TL;DR

EndoExtract is a system that uses large language models to extract structured information from unstructured endometriosis ultrasound reports, improving workflow efficiency and reducing manual effort.

Contribution

This paper introduces EndoExtract, a novel LLM-powered system designed specifically for structured data extraction from medical reports, with a user-centered interface for clinical review.

Findings

Supports shift from manual data entry to supervisory validation

Highlights source evidence within PDFs for verification

Addresses workflow pain points identified through user research

Abstract

Endometriosis ultrasound reports are often unstructured free-text documents that require manual abstraction for downstream tasks such as analytics, machine learning model training, and clinical auditing. We present \textbf{EndoExtract}, an on-premise LLM-powered system that extracts structured data from these reports and surfaces interpretive fields for human review. Through contextual inquiry with research assistants, we identified key workflow pain points: asymmetric trust between numerical and interpretive fields, repetitive manual highlighting, fatigue from sustained comparison, and terminology inconsistency across radiologists. These findings informed an interface that surfaces only interpretive fields for mandatory review, automatically highlights source evidence within PDFs, and separates batch extraction from human-paced verification. A formative workshop revealed that \textbf{EndoExtract} supports a shift from field-by-field data entry to supervisory validation, though participants noted risks of over-skimming and challenges in managing missing data.