Fairness Analysis in AI Algorithms in Healthcare: A Study on Post-Processing Approaches

• Vitor Galioti Martini UNIFESP
• Lilian Berton UNIFESP

DOI: https://doi.org/10.5753/eniac.2024.244467

Resumo

Equity in Artificial Intelligence (AI) algorithms applied to healthcare is an ever-evolving field of study with significant implications for the quality and fairness of healthcare. This work focuses on applying data analysis to investigate biases in a healthcare dataset and examining how different post-processing techniques, which are less utilized and discussed in the literature compared to pre-processing techniques, can be employed to address these biases. We analyzed the Stroke Prediction dataset, and bias was identified and analyzed along with its correlation with the data. Subsequently, post-processing techniques were applied to reduce these biases, and the effectiveness of these techniques was analyzed. It was found that while all adopted post-processing techniques reduced biases, this came at the cost of a decrease in classification accuracy and precision. Among them, the EqOddsPostprocessing technique from the AIF360 library demonstrated the least impact on model accuracy and precision.

Palavras-chave: Fairness, Machine Learning, Post-processing, Healthcare, AVC

Referências

Bellamy, R. K., Dey, K., Hind, M., Hoffman, S. C., Houde, S., Kannan, K., Lohia, P., Martino, J., Mehta, S., Mojsilovic, A., et al. (2018). Ai fairness 360: An extensible toolkit for detecting, understanding, and mitigating unwanted algorithmic bias. arXiv preprint arXiv:1810.01943.

Broder, R. S. and Berton, L. (2021). Performance analysis of machine learning algorithms trained on biased data. In Anais do XVIII Encontro Nacional de Inteligência Artificial e Computacional, pages 548–558. SBC.

Castelnovo, A., Crupi, R., Greco, G., Regoli, D., Penco, I. G., and Cosentini, A. C. (2022). A clarification of the nuances in the fairness metrics landscape. Scientific Reports, 12(1):4209.

Chen, R. J., Chen, T. Y., Lipkova, J., Wang, J. J., Williamson, D. F., Lu, M. Y., Sahai, S., and Mahmood, F. (2021). Algorithm fairness in ai for medicine and healthcare. arXiv preprint arXiv:2110.00603.

Dueñas, H. R., Seah, C., Johnson, J. S., and Huckins, L. M. (2020). Implicit bias of encoded variables: frameworks for addressing structured bias in ehr–gwas data. Human Molecular Genetics, 29(R1):R33–R41.

Esteva, A., Robicquet, A., Ramsundar, B., Kuleshov, V., DePristo, M., Chou, K., Cui, C., Corrado, G., Thrun, S., and Dean, J. (2019). A guide to deep learning in healthcare. Nature medicine, 25(1):24–29.

Gianfrancesco, M. A., Tamang, S., Yazdany, J., and Schmajuk, G. (2018). Potential biases in machine learning algorithms using electronic health record data. JAMA internal medicine, 178(11):1544–1547.

Jiang, F., Jiang, Y., Zhi, H., Dong, Y., Li, H., Ma, S., Wang, Y., Dong, Q., Shen, H., and Wang, Y. (2017). Artificial intelligence in healthcare: past, present and future. Stroke and vascular neurology, 2(4).

Li, F., Wu, P., Ong, H. H., Peterson, J. F., Wei, W.-Q., and Zhao, J. (2023). Evaluating and mitigating bias in machine learning models for cardiovascular disease prediction. Journal of Biomedical Informatics, 138:104294.

Lisabeth, L. D., Brown, D. L., Hughes, R., Majersik, J. J., and Morgenstern, L. B. (2009). Acute stroke symptoms: comparing women and men. Stroke, 40(6):2031–2036.

Liu, T., Siegel, E., and Shen, D. (2022). Deep learning and medical image analysis for covid-19 diagnosis and prediction. Annual Review of Biomedical Engineering, 24:179–201.

Mehta, R., Shui, C., and Arbel, T. (2023). Evaluating the fairness of deep learning uncertainty estimates in medical image analysis. arXiv preprint arXiv:2303.03242.

Miller, R. J., Singh, A., Otaki, Y., Tamarappoo, B. K., Kavanagh, P., Parekh, T., Hu, L.-H., Gransar, H., Sharir, T., Einstein, A. J., et al. (2023). Mitigating bias in deep learning for diagnosis of coronary artery disease from myocardial perfusion spect images. European journal of nuclear medicine and molecular imaging, 50(2):387–397.

Mohammed, R., Rawashdeh, J., and Abdullah, M. (2020). Machine learning with over-sampling and undersampling techniques: overview study and experimental results. In 2020 11th international conference on information and communication systems (ICICS), pages 243–248. IEEE.

Noseworthy, P. A., Attia, Z. I., Brewer, L. C., Hayes, S. N., Yao, X., Kapa, S., Friedman, P. A., and Lopez-Jimenez, F. (2020). Assessing and mitigating bias in medical artificial intelligence: the effects of race and ethnicity on a deep learning model for ecg analysis. Circulation: Arrhythmia and Electrophysiology, 13(3):e007988.

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.

Pivovarov, R., Albers, D. J., Sepulveda, J. L., and Elhadad, N. (2014). Identifying and mitigating biases in ehr laboratory tests. Journal of biomedical informatics, 51:24–34.

Rabonato, R. T. and Berton, L. (2024). A systematic review of fairness in machine learning. AI and Ethics, pages 1–12.

Straw, I. and Callison-Burch, C. (2020). Artificial intelligence in mental health and the biases of language based models. PloS one, 15(12):e0240376.

Su, C., Yu, G., Wang, J., Yan, Z., and Cui, L. (2022). A review of causality-based fairness machine learning.

Wissel, B. D., Greiner, H. M., Glauser, T. A., Mangano, F. T., Santel, D., Pestian, J. P., Szczesniak, R. D., and Dexheimer, J. W. (2019). Investigation of bias in an epilepsy machine learning algorithm trained on physician notes. Epilepsia, 60(9):e93–e98.