Saved in:
Bibliographic Details
Main Authors: Li, Haiyi, Zhao, Yiyang, Li, Yutong, Deslandes, Alison, Avery, Jodie, Leonardi, Mathew, Hull, Mary Louise, Chen, Hsiang-Ting
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.18154
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917274282098688
author Li, Haiyi
Zhao, Yiyang
Li, Yutong
Deslandes, Alison
Avery, Jodie
Leonardi, Mathew
Hull, Mary Louise
Chen, Hsiang-Ting
author_facet Li, Haiyi
Zhao, Yiyang
Li, Yutong
Deslandes, Alison
Avery, Jodie
Leonardi, Mathew
Hull, Mary Louise
Chen, Hsiang-Ting
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_18154
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EndoExtract: Co-Designing Structured Text Extraction from Endometriosis Ultrasound Reports
Li, Haiyi
Zhao, Yiyang
Li, Yutong
Deslandes, Alison
Avery, Jodie
Leonardi, Mathew
Hull, Mary Louise
Chen, Hsiang-Ting
Human-Computer Interaction
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.
title EndoExtract: Co-Designing Structured Text Extraction from Endometriosis Ultrasound Reports
topic Human-Computer Interaction
url https://arxiv.org/abs/2601.18154