Summary of Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis Using Slice Discovery Methods, by Vincent Olesen et al.
Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods
by Vincent Olesen, Nina Weng, Aasa Feragen, Eike Petersen
First submitted to arxiv on: 17 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Computers and Society (cs.CY)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary Machine learning models have achieved high overall accuracy in medical image analysis, but performance disparities on specific patient groups hinder their clinical utility, safety, and fairness. To address these issues, we leverage Slice Discovery Methods (SDMs) to identify interpretable underperforming subsets of data and formulate hypotheses regarding the cause of observed performance disparities. We introduce a novel SDM and apply it in a case study on the classification of pneumothorax and atelectasis from chest x-rays. Our study demonstrates the effectiveness of SDMs in hypothesis formulation and yields an explanation of previously observed but unexplained performance disparities between male and female patients in widely used chest X-ray datasets and models. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Machine learning models are good at recognizing medical images, but they can be biased against certain groups of people. This is a problem because it means the models might not work as well for some patients as they do for others. The researchers in this paper came up with a way to figure out why these biases happen and how to fix them. They used something called Slice Discovery Methods (SDMs) to look at medical images and find patterns that explain why the models are biased. They tested their method on chest x-rays and found that it worked well. The results showed that the models were learning shortcuts, which means they were relying on easy-to-spot features instead of really understanding what was going on in the images. |
Keywords
» Artificial intelligence » Classification » Machine learning
