Skin-SOAP: A Weakly Supervised Framework for Generating Structured SOAP Notes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kamal, Sadia, Oates, Tim, Wan, Joy
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915433321332736
author Kamal, Sadia
Oates, Tim
Wan, Joy
author_facet Kamal, Sadia
Oates, Tim
Wan, Joy
contents Skin carcinoma is the most prevalent form of cancer globally, accounting for over $8 billion in annual healthcare expenditures. Early diagnosis, accurate and timely treatment are critical to improving patient survival rates. In clinical settings, physicians document patient visits using detailed SOAP (Subjective, Objective, Assessment, and Plan) notes. However, manually generating these notes is labor-intensive and contributes to clinician burnout. In this work, we propose skin-SOAP, a weakly supervised multimodal framework to generate clinically structured SOAP notes from limited inputs, including lesion images and sparse clinical text. Our approach reduces reliance on manual annotations, enabling scalable, clinically grounded documentation while alleviating clinician burden and reducing the need for large annotated data. Our method achieves performance comparable to GPT-4o, Claude, and DeepSeek Janus Pro across key clinical relevance metrics. To evaluate this clinical relevance, we introduce two novel metrics MedConceptEval and Clinical Coherence Score (CCS) which assess semantic alignment with expert medical concepts and input features, respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2508_05019
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Skin-SOAP: A Weakly Supervised Framework for Generating Structured SOAP Notes
Kamal, Sadia
Oates, Tim
Wan, Joy
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
Skin carcinoma is the most prevalent form of cancer globally, accounting for over $8 billion in annual healthcare expenditures. Early diagnosis, accurate and timely treatment are critical to improving patient survival rates. In clinical settings, physicians document patient visits using detailed SOAP (Subjective, Objective, Assessment, and Plan) notes. However, manually generating these notes is labor-intensive and contributes to clinician burnout. In this work, we propose skin-SOAP, a weakly supervised multimodal framework to generate clinically structured SOAP notes from limited inputs, including lesion images and sparse clinical text. Our approach reduces reliance on manual annotations, enabling scalable, clinically grounded documentation while alleviating clinician burden and reducing the need for large annotated data. Our method achieves performance comparable to GPT-4o, Claude, and DeepSeek Janus Pro across key clinical relevance metrics. To evaluate this clinical relevance, we introduce two novel metrics MedConceptEval and Clinical Coherence Score (CCS) which assess semantic alignment with expert medical concepts and input features, respectively.
title Skin-SOAP: A Weakly Supervised Framework for Generating Structured SOAP Notes
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2508.05019