Gender Disparity Mitigation in Multitask Neural Network Regression Models Applied to Parkinson’s Disease

• Bruno Pires M. Silva UNIFESP
• Lilian Berton UNIFESP
• Luiz Leduino de Salles Neto UNIFESP

DOI: https://doi.org/10.5753/sbcas.2025.6995

Abstract

Fairness in predictive models is crucial, especially in sensitive contexts such as healthcare, where disparities can result in severe consequences. This work proposes a solution to mitigate such disparities in regression problems. The approach employs a modified multitask neural network, in which modifications are made to the loss function to reduce the disparity in errors between genders. The model was applied to a dataset of patients with Parkinson’s disease to predict a score on disease progression. Preliminary results show the ability to predict gender and satisfactory performance in the regression task.

References

Barocas, S., Hardt, M., and Narayanan, A. (2018). Fairness and machine learning. fairmlbook. org, 2019.

Cozman, F. G. and Kaufman, D. (2022). Viés no aprendizado de máquina em sistemas de inteligência artificial: a diversidade de origens e os caminhos de mitigação. Revista USP, (135):195–210.

Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016). Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. jama, 316(22):2402–2410.

Gursoy, F. and Kakadiaris, I. A. (2022). Error parity fairness: Testing for group fairness in regression tasks. arXiv preprint arXiv:2208.08279.

Obermeyer, Z., Powers, B., Vogeli, C., and Mullainathan, S. (2019). Dissecting racial bias in an algorithm used to manage the health of populations. Science, 366(6464):447–453.

Pessach, D. and Shmueli, E. (2022). A review on fairness in machine learning. ACM Computing Surveys (CSUR), 55(3):1–44.

Pfohl, S. R., Foryciarz, A., and Shah, N. H. (2021). An empirical characterization of fair machine learning for clinical risk prediction. Journal of biomedical informatics, 113:103621.

Sun, Q., Akman, A., and Schuller, B. W. (2025). Explainable artificial intelligence for medical applications: A review. ACM Trans. Comput. Healthcare, 6(2).

Tsanas, A. and Little, M. (2009). Parkinsons Telemonitoring. UCI Machine Learning Repository. DOI: 10.24432/C5ZS3N.

Yu, K. and Luo, X. (2024). Intelligent diagnosis and progression analysis of alzheimer’s disease using machine learning. In Proceedings of the 2024 5th International Symposium on Artificial Intelligence for Medicine Science, pages 66–72.

Zemel, R., Wu, Y., Swersky, K., Pitassi, T., and Dwork, C. (2013). Learning fair representations. In International conference on machine learning, pages 325–333. PMLR.

Zhang, B. H., Lemoine, B., and Mitchell, M. (2018). Mitigating unwanted biases with adversarial learning. In Proceedings of the 2018 AAAI/ACM Conference on AI, Ethics, and Society, pages 335–340.