Bias Detection in Clinically Machine Learning Models

References

[1] A. Rajkomar, J. Dean, and I. Kohane, “Machine learning in medicine,” New England Journal of Medicine, vol. 380, no. 14, pp. 1347–1358, 2019.

[2] Z. Obermeyer, B. Powers, C. Vogeli, and S. Mullainathan, “Dipping racial bias in an algorithm is used to manage population health,” Science, vol. 366, no. 6464, pp. 447–453, 2019.

[3] I. Y. Chen, F. D. Johansson, and D. Sontag, “Why is my classifier discriminatory?” In progress in nerve information processing systems (NeurIPS), pp. 3543–3554, 2018.

[4] F. Kamiran and T. Calders, “Data preprocessing technology for classification without discrimination, “Knowledge and information system,, vol. 33, no. 1, pp. 1–33, 2012.

[5] M. B. Zafar, I. Valera, M. G. Rodriguez, and K. P. Gummadi, “Fairness constraints: Mechanisms for fair classification,” in Proc. 20th Int. Conf. Artificial Intelligence and Statistics (AISTATS), pp. 962– 970, 2017.

[6] M. Hardt, E. Price, and N. Srebro, “Equality of opportunity in supervised learning,” in Advances in Neural Information Processing Systems (NeurIPS), pp. 3315–3323, 2016.

[7] F. Chen, C. Liu, and W. Lin, “Unmasking bias in artificial intelligence: A systematic review of EHR- based bias detection and mitigation,” Journal of Medical Systems, vol. 48, no. 3, pp. 112–126, 2024.

[8] J. L. Cross, R. Mehta, and A. Singh, “Bias in medical artificial intelligence: Implications for clinical decision-making and fairness,” BMC Medical Ethics, vol. 25, no. 1, pp. 1–15, 2024.

[9] Y. Huang, T. Zhang, and P. Li, “A Scoping view of fair machine learning techniques when applied to healthcare data,” Frontiers in Artificial Intelligence, vol. 7, no. 122, pp. 1–18, 2024.

[10] R. Poulain, P. O’Connor, and J. Han, “Improving fairness in AI models on electronic health records: The case for federated learning methods,” arXiv preprint arXiv:2305.11386, 2023.

[11] M. W. Sjoding, R. P. Dickson, T. J. Iwashyna, S. E. Gay, and T. S. Valley, “Racial bias in pulse oximetry measurement,” New England Journal of Medicine, vol. 383, no. 25, pp. 2477–2478, 2020.

[12] J. Yang, A. Kumar, and F. Li, “An algorithmic bias training framework for mitigating adversarial in healthcare prediction models,” npj Digital Medicine, vol. 6, no. 41, pp. 1–12, 2023.

[13] M. B. Zafar, I. Valera, M. G. Rodriguez, and K. P. Gummadi, “Fairness constraints: Mechanisms for fair classification,” in Proc. 20th Int. Conf. Artificial Intelligence and Statistics (AISTATS), vol. 54,pp. 962–970, 2017.

[14] Independent Review on Equity in Medical Devices, “Bias in pulse oximetry and clinical algorithms,” UK Health Department Report, 2024.

[15] D. Ueda, Y. Chen, H. Kosaka, and T. Ichikawa, “Fairness of artificial intelligence in healthcare: A review and future directions,” Radiology: Artificial Intelligence, vol. 5, no. 1, pp. 1–14, 2023.

[16] J. Cross, H. Yuan, and M. Schuchard, “Bias in medical AI: Implications for clinical decision- making,” NPJ Digital Medicine, vol. 7, no. 66, pp. 1–11, 2024.

[17] S. Siddique, M. Khurram, and F. Jamil, “Survey on machine learning biases and mitigation techniques,” Digital, vol. 4, no. 1, pp. 101–120, 2024.

[18] A. Mehrabi, F. Morstatter, N. Saxena, K. Lerman, and A. Galstyan, “A Machine learning of bias and fairness,” ACM Computing Surveys, vol. 54, no. 6, pp. 1–35, 2021.

[19] J. Yang, R. Xie, A. Malhotra, and J. Park, “An Mitigating adversarial framework for algorithmic biases in clinical machine learning,” NPJ Digital Medicine, vol. 6, no. 22, pp. 1–12, 2023.

[20] M. P. Cary Jr., C. Wang, and R. F. Brown, “Mitigating racial and ethnic bias and advancing equity in health care AI,” Health Affairs, vol. 42, no. 3, pp. 329–338, 2023.

[21] D. Ueda et al., “Fairness in intelligence in healthcare : review and future directions,”

[22] J. Yang et al., “An Mitigating adversarial framework for algorithmic biases in clinical machine learning,” NPJ Digital Medicine, 2023. Nature

[23] U.S. Drug and Food Administration, “Performance Evaluation of Pulse Oximeters (Executive summary/draft),” Feb 2024. Food and Drug Administration

[24] W. Ahmed, “Racial Biases Associated With Pulse Oximetry,” American Journal of Respiratory and Critical Care Medicine (review), 2024. PubMed Central

[25] J. Carey, “Fairness in AI for healthcare,” ScienceDirect / review, 2024. ScienceDirect

[26] Z. Obermeyer et al., “Dissecting racial bias of this algorithm used to manage the health of populations,” Science, 2019. Science

[27] J. Yang et al., “An mitigating algorithmic biases in clinical machine learning of the algorithmic biases,” npj Digital Medicine, 2023. Nature

[28] FDA, “Executive Summary: Performance Evaluation of Pulse Oximeters,” Feb 2024 (draft/summary). Food and Drug Administration

[29] D. Ueda et al., “Fairness in healthcare: review and future directions,” Radiology: AI / PubMed, 2024. PubMed

[30] J. Cross et al., “Bias in medical AI: Implications for clinical decision-making,” NPJ Digital Medicine, 2024. PubMed Central

[31] N. Sourlos et al., “Recommendations for the creation of benchmark datasets for fairness research,” 2024. PubMed Central

@article{1710955,
      author = {Manju V A, Harish T A},
      title = {Bias Detection in Clinically Machine Learning Models},
      journal = {Iconic Research And Engineering Journals},
      year = {2025},
      volume = {9},
      number = {3},
      pages = {1692-1697},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1710955.pdf},
      abstract = {The integration of machine learning (ML) into healthcare has enabled significant advances in diagnosis, prognosis, and treatment planning. However, predictive models often inherit biases from imbalanced datasets and structural inequities, leading to unfair outcomes across demographic groups. This project presents a Healthcare Bias Detection Tool, developed in Python with a Tkinter-based interface, to evaluate both the performance and fairness of clinical ML models. The tool supports algorithms such as Support Vector Machines (SVM) and K-Nearest Neighbors (KNN), while enabling users to load datasets, preprocess data, and configure sensitive attributes and target variables. Beyond traditional metrics like accuracy, precision, recall, and F1-score, the system incorporates fairness indicators including disparate impact ratio and statistical parity difference. Visualizations such as confusion matrices, subgroup accuracy comparisons, and prediction distributions enhance interpretability. The tool also generates structured reports covering performance, bias findings, and recommended mitigation strategies, thus fostering accountability and ethical AI adoption in healthcare. By combining model validation with fairness evaluation, the framework contributes to responsible deployment of machine learning in clinical decision-making.},
      keywords = {Machine learning, bias detection, fairness metrics, healthcare AI, clinical decision support, support vector machine (SVM), K-nearest neighbors (KNN), disparate impact, statistical parity difference, ethical AI, model evaluation, transparency in AI.},
      month = {September},
  }