Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| 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 |