Machine Learning for Exam Triage
Xinyu Guan, Jessica Lee, Peter Wu, Yue Wu
TL;DR
This paper enhances CheXNet by incorporating non-image features, resulting in improved AUROC scores for exam triage tasks, demonstrating the benefit of multi-modal data integration.
Contribution
The study introduces a method that combines image and non-image features to improve diagnostic performance over existing models.
Findings
Improved AUROC scores compared to CheXNet
Effective integration of non-image features
Enhanced model performance in exam triage
Abstract
In this project, we extend the state-of-the-art CheXNet (Rajpurkar et al. [2017]) by making use of the additional non-image features in the dataset. Our model produced better AUROC scores than the original CheXNet.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsCOVID-19 diagnosis using AI · Artificial Intelligence in Healthcare and Education · Clinical Reasoning and Diagnostic Skills
MethodsConcatenated Skip Connection · *Communicated@Fast*How Do I Communicate to Expedia? · Dense Connections · Average Pooling · Batch Normalization · Kaiming Initialization · 1x1 Convolution · Dense Block · Global Average Pooling · Dropout