Skip to main content
construction release_alert
Scholars@Duke will be undergoing maintenance April 11-15. Some features may be unavailable during this time.
cancel
Journal cover image

Trans-Balance: Reducing demographic disparity for prediction models in the presence of class imbalance.

Publication ,  Journal Article
Hong, C; Liu, M; Wojdyla, DM; Hickey, J; Pencina, M; Henao, R
Published in: J Biomed Inform
January 2024

INTRODUCTION: Risk prediction, including early disease detection, prevention, and intervention, is essential to precision medicine. However, systematic bias in risk estimation caused by heterogeneity across different demographic groups can lead to inappropriate or misinformed treatment decisions. In addition, low incidence (class-imbalance) outcomes negatively impact the classification performance of many standard learning algorithms which further exacerbates the racial disparity issues. Therefore, it is crucial to improve the performance of statistical and machine learning models in underrepresented populations in the presence of heavy class imbalance. METHOD: To address demographic disparity in the presence of class imbalance, we develop a novel framework, Trans-Balance, by leveraging recent advances in imbalance learning, transfer learning, and federated learning. We consider a practical setting where data from multiple sites are stored locally under privacy constraints. RESULTS: We show that the proposed Trans-Balance framework improves upon existing approaches by explicitly accounting for heterogeneity across demographic subgroups and cohorts. We demonstrate the feasibility and validity of our methods through numerical experiments and a real application to a multi-cohort study with data from participants of four large, NIH-funded cohorts for stroke risk prediction. CONCLUSION: Our findings indicate that the Trans-Balance approach significantly improves predictive performance, especially in scenarios marked by severe class imbalance and demographic disparity. Given its versatility and effectiveness, Trans-Balance offers a valuable contribution to enhancing risk prediction in biomedical research and related fields.

Duke Scholars

Published In

J Biomed Inform

DOI

EISSN

1532-0480

Publication Date

January 2024

Volume

149

Start / End Page

104532

Location

United States

Related Subject Headings

  • Medical Informatics
  • Machine Learning
  • Humans
  • Demography
  • Cohort Studies
  • Biomedical Research
  • Biomedical Engineering
  • Algorithms
  • 4601 Applied computing
  • 4203 Health services and systems
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Hong, C., Liu, M., Wojdyla, D. M., Hickey, J., Pencina, M., & Henao, R. (2024). Trans-Balance: Reducing demographic disparity for prediction models in the presence of class imbalance. J Biomed Inform, 149, 104532. https://doi.org/10.1016/j.jbi.2023.104532
Hong, Chuan, Molei Liu, Daniel M. Wojdyla, Jimmy Hickey, Michael Pencina, and Ricardo Henao. “Trans-Balance: Reducing demographic disparity for prediction models in the presence of class imbalance.J Biomed Inform 149 (January 2024): 104532. https://doi.org/10.1016/j.jbi.2023.104532.
Hong C, Liu M, Wojdyla DM, Hickey J, Pencina M, Henao R. Trans-Balance: Reducing demographic disparity for prediction models in the presence of class imbalance. J Biomed Inform. 2024 Jan;149:104532.
Hong, Chuan, et al. “Trans-Balance: Reducing demographic disparity for prediction models in the presence of class imbalance.J Biomed Inform, vol. 149, Jan. 2024, p. 104532. Pubmed, doi:10.1016/j.jbi.2023.104532.
Hong C, Liu M, Wojdyla DM, Hickey J, Pencina M, Henao R. Trans-Balance: Reducing demographic disparity for prediction models in the presence of class imbalance. J Biomed Inform. 2024 Jan;149:104532.
Journal cover image

Published In

J Biomed Inform

DOI

EISSN

1532-0480

Publication Date

January 2024

Volume

149

Start / End Page

104532

Location

United States

Related Subject Headings

  • Medical Informatics
  • Machine Learning
  • Humans
  • Demography
  • Cohort Studies
  • Biomedical Research
  • Biomedical Engineering
  • Algorithms
  • 4601 Applied computing
  • 4203 Health services and systems