# The Effect of Counterfactuals on Reading Chest X-rays

arXiv: https://arxiv.org/abs/2304.00487 · HTML: https://mlsanity.com/paper/2304.00487/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 6 references that are in the map.
- First posted on arXiv 2 Apr 2023.

## Builds on (most cited first, 4 of 4)

- [Axiomatic Attribution for Deep Networks](https://mlsanity.com/paper/1703.01365/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations](https://mlsanity.com/paper/1703.03717/) (2017)
- [TorchXRayVision: A library of chest X-ray datasets and models](https://mlsanity.com/paper/2111.00595/) (2021)

## Abstract (arXiv)

This study evaluates the effect of counterfactual explanations on the interpretation of chest X-rays. We conduct a reader study with two radiologists assessing 240 chest X-ray predictions to rate their confidence that the model's prediction is correct using a 5 point scale. Half of the predictions are false positives. Each prediction is explained twice, once using traditional attribution methods and once with a counterfactual explanation. The overall results indicate that counterfactual explanations allow a radiologist to have more confidence in true positive predictions compared to traditional approaches (0.15±0.95 with p=0.01) with only a small increase in false positive predictions (0.04±1.06 with p=0.57). We observe the specific prediction tasks of Mass and Atelectasis appear to benefit the most compared to other tasks.