# Two-step adversarial debiasing with partial learning -- medical image case-studies

arXiv: https://arxiv.org/abs/2111.08711 · HTML: https://mlsanity.com/paper/2111.08711/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 16 references that are in the map.
- First posted on arXiv 16 Nov 2021.

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

- [Reading Race: AI Recognises Patient's Racial Identity In Medical Images](https://mlsanity.com/paper/2107.10356/) (2021)
- [CheXclusion: Fairness gaps in deep chest X-ray classifiers](https://mlsanity.com/paper/2003.00827/) (2020)
- [Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings](https://mlsanity.com/paper/2003.11515/) (2020)
- [Ablation Studies in Artificial Neural Networks](https://mlsanity.com/paper/1901.08644/) (2019)

## Built on by (most cited first, 5 of 5)

- [Improving Fairness in AI Models on Electronic Health Records: The Case for Federated Learning Methods](https://mlsanity.com/paper/2305.11386/) (2023)
- [A Survey on Medical Document Summarization](https://mlsanity.com/paper/2212.01669/) (2022)
- [A survey of recent methods for addressing AI fairness and bias in biomedicine](https://mlsanity.com/paper/2402.08250/) (2024)
- [Open Challenges on Fairness of Artificial Intelligence in Medical Imaging Applications](https://mlsanity.com/paper/2407.16953/) (2024)
- [Fair Machine Learning in Healthcare: A Review](https://mlsanity.com/paper/2206.14397/) (2022)

## Abstract (arXiv)

The use of artificial intelligence (AI) in healthcare has become a very active research area in the last few years. While significant progress has been made in image classification tasks, only a few AI methods are actually being deployed in hospitals. A major hurdle in actively using clinical AI models currently is the trustworthiness of these models. More often than not, these complex models are black boxes in which promising results are generated. However, when scrutinized, these models begin to reveal implicit biases during the decision making, such as detecting race and having bias towards ethnic groups and subpopulations. In our ongoing study, we develop a two-step adversarial debiasing approach with partial learning that can reduce the racial disparity while preserving the performance of the targeted task. The methodology has been evaluated on two independent medical image case-studies - chest X-ray and mammograms, and showed promises in bias reduction while preserving the targeted performance.