RadFusion: Benchmarking Performance and Fairness for Multimodal Pulmonary Embolism Detection from CT and EHR release_qcdzdqrhkvbf3c2mkvlb7hgf24

by Yuyin Zhou, Shih-Cheng Huang, Jason Alan Fries, Alaa Youssef, Timothy J. Amrhein, Marcello Chang, Imon Banerjee, Daniel Rubin, Lei Xing, Nigam Shah, Matthew P. Lungren

Released as a article .

2021  

Abstract

Despite the routine use of electronic health record (EHR) data by radiologists to contextualize clinical history and inform image interpretation, the majority of deep learning architectures for medical imaging are unimodal, i.e., they only learn features from pixel-level information. Recent research revealing how race can be recovered from pixel data alone highlights the potential for serious biases in models which fail to account for demographics and other key patient attributes. Yet the lack of imaging datasets which capture clinical context, inclusive of demographics and longitudinal medical history, has left multimodal medical imaging underexplored. To better assess these challenges, we present RadFusion, a multimodal, benchmark dataset of 1794 patients with corresponding EHR data and high-resolution computed tomography (CT) scans labeled for pulmonary embolism. We evaluate several representative multimodal fusion models and benchmark their fairness properties across protected subgroups, e.g., gender, race/ethnicity, age. Our results suggest that integrating imaging and EHR data can improve classification performance and robustness without introducing large disparities in the true positive rate between population groups.
In text/plain format

Archived Files and Locations

application/pdf  713.6 kB
file_4bd7wak5lvgfjptchqslmkt2o4
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2021-11-23
Version   v1
Language   en ?
arXiv  2111.11665v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: ecd54a5f-f17a-4e93-9baf-26caa0f97586
API URL: JSON