Improving model fairness in image-based computer-aided diagnosis

Mingquan Lin (), Tianhao Li, Yifan Yang, Gregory Holste, Ying Ding, Sarah H. Tassel, Kyle Kovacs, George Shih, Zhangyang Wang, Zhiyong Lu, Fei Wang and Yifan Peng ()
Additional contact information
Mingquan Lin: Weill Cornell Medicine
Tianhao Li: The University of Texas at Austin
Yifan Yang: National Institutes of Health (NIH)
Gregory Holste: The University of Texas at Austin
Ying Ding: The University of Texas at Austin
Sarah H. Tassel: Weill Cornell Medicine
Kyle Kovacs: Weill Cornell Medicine
George Shih: Weill Cornell Medicine
Zhangyang Wang: The University of Texas at Austin
Zhiyong Lu: National Institutes of Health (NIH)
Fei Wang: Weill Cornell Medicine
Yifan Peng: Weill Cornell Medicine

Nature Communications, 2023, vol. 14, issue 1, 1-9

Abstract: Abstract Deep learning has become a popular tool for computer-aided diagnosis using medical images, sometimes matching or exceeding the performance of clinicians. However, these models can also reflect and amplify human bias, potentially resulting inaccurate missed diagnoses. Despite this concern, the problem of improving model fairness in medical image classification by deep learning has yet to be fully studied. To address this issue, we propose an algorithm that leverages the marginal pairwise equal opportunity to reduce bias in medical image classification. Our evaluations across four tasks using four independent large-scale cohorts demonstrate that our proposed algorithm not only improves fairness in individual and intersectional subgroups but also maintains overall performance. Specifically, the relative change in pairwise fairness difference between our proposed model and the baseline model was reduced by over 35%, while the relative change in AUC value was typically within 1%. By reducing the bias generated by deep learning models, our proposed approach can potentially alleviate concerns about the fairness and reliability of image-based computer-aided diagnosis.

Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-023-41974-4 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:14:y:2023:i:1:d:10.1038_s41467-023-41974-4

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-023-41974-4

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().