Mitigating Algorithmic Bias in Clinical AI Systems Through Fairness-Aware Training Objectives and Equitable Model Calibration Techniques
Keywords:
Algorithmic Bias, Clinical AI, Fairness-Aware Learning, Model Calibration, Health Equity, Machine Learning in HealthcareAbstract
The integration of artificial intelligence (AI) into clinical decision-making has the potential to improve diagnostic accuracy, treatment recommendations, and patient outcomes. However, the increasing reliance on machine learning (ML) in healthcare has revealed deep-rooted algorithmic biases that may exacerbate health disparities across demographic groups. This paper explores strategies to mitigate such biases through fairness-aware training objectives and post-hoc calibration techniques. We propose a framework combining group fairness constraints during training and recalibration methods to enhance equity across ethnic, gender, and age groups. Through empirical analysis on two clinical datasets, we demonstrate improved fairness without significant trade-offs in accuracy. This work contributes to the growing field of ethical AI by highlighting scalable interventions for real-world clinical systems.
References
Obermeyer, Ziad, Brian Powers, Christine Vogeli, and Sendhil Mullainathan. "Dissecting Racial Bias in an Algorithm Used to Manage the Health of Populations." Science, vol. 366, no. 6464, 2019, pp. 447–453.
Gonepally, S., Amuda, K. K., Kumbum, P. K., Adari, V. K., & Chunduru, V. K. (2022). Teaching software engineering by means of computer game development: Challenges and opportunities using the PROMETHEE method. SOJ Materials Science & Engineering, 9(1), 1–9.
Chen, Irene Y., Peter Szolovits, and Marzyeh Ghassemi. "Can AI Help Reduce Disparities in General Medical and Mental Health Care?" AMA Journal of Ethics, vol. 22, no. 10, 2020, pp. E874–881.
Rajkomar, Alvin, Moritz Hardt, Michael D. Howell, Geoffrey Corrado, and Michael H. Chin. "Ensuring Fairness in Machine Learning to Advance Health Equity." Annals of Internal Medicine, vol. 169, no. 12, 2018, pp. 866–872.
Gonepally, S., Amuda, K. K., Kumbum, P. K., Adari, V. K., & Chunduru, V. K. (2023). Addressing supply chain administration challenges in the construction industry: A TOPSIS-based evaluation approach. Data Analytics and Artificial Intelligence, 3(1), 152–164.
Beutel, Alex, Jilin Chen, Zhe Zhao, and Ed H. Chi. "Fairness in Recommendation Ranking Through Pairwise Comparisons." Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019, pp. 2212–2220.
Wiens, Jenna, John Guttag, and Eric Horvitz. "Do No Harm: A Roadmap for Responsible Machine Learning for Health Care." Nature Medicine, vol. 27, no. 5, 2021, pp. 793–797.
Chouldechova, Alexandra. "Fair Prediction with Disparate Impact: A Study of Bias in Recidivism Prediction Instruments." Big Data, vol. 5, no. 2, 2017, pp. 153–163.
Hardt, Moritz, Eric Price, and Nati Srebro. "Equality of Opportunity in Supervised Learning." Advances in Neural Information Processing Systems, vol. 29, 2016, pp. 3315–3323.
Kumbum, P. K., Adari, V. K., Chunduru, V. K., Gonepally, S., & Amuda, K. K. (2023). Navigating digital privacy and security effects on student financial behavior, academic performance, and well-being. Data Analytics and Artificial Intelligence, 3(2), 235–246.
Kleinberg, Jon, Sendhil Mullainathan, and Manish Raghavan. "Inherent Trade-Offs in the Fair Determination of Risk Scores." Proceedings of the 8th Innovations in Theoretical Computer Science Conference, 2017, pp. 43:1–43:23.
Liu, Lydia T., H. Brendan McMahan, Zackory Erickson, and Olga Raskina. "A Delayed Impact of Fair Machine Learning." Proceedings of the 36th International Conference on Machine Learning, vol. 97, 2019, pp. 3254–3263.
Mehrabi, Ninareh, Fred Morstatter, Nripsuta Saxena, Kristina Lerman, and Aram Galstyan. "A Survey on Bias and Fairness in Machine Learning." ACM Computing Surveys, vol. 54, no. 6, 2021, pp. 1–35.
Adari, V. K., Chunduru, V. K., Gonepally, S., Amuda, K. K., & Kumbum, P. K. (2023). Ethical analysis and decision-making framework for marketing communications: A weighted product model approach. Data Analytics and Artificial Intelligence, 3(5), 44–53. https://doi.org/10.46632/daai/3/5/7
Ghassemi, Marzyeh, Luke Oakden-Rayner, and Andrew L. Beam. "The False Hope of Current Approaches to Explainable Artificial Intelligence in Health Care." The Lancet Digital Health, vol. 3, no. 11, 2021, pp. e745–e750.
Wang, Tian, Hao Zhang, and Murat Kantarcioglu. "Improving Fairness in Clinical Prediction Using Adversarial Learning." IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 5, 2022, pp. 2060–2070.
Seyyed-Kalantari, Laleh, Hao Zhang, Matthew McDermott, and Marzyeh Ghassemi. "Underdiagnosis Bias of Artificial Intelligence Algorithms in Chest Radiographs." Nature Medicine, vol. 27, 2021, pp. 2176–2182.
