ML-Driven Clinical Insights for Health Equity
Keywords:
Predictive Healthcare Analytics,Machine Learning in Healthcare,Big Clinical Data,Electronic Health Records (EHR),Health Equity Analytics,AI for Equitable Care,Clinical Risk Prediction Models,Population Health Management,Healthcare Data Mining,Bias Mitigation in Healthcare AI,Social Determinants of Health (SDOH),Precision Medicine Analytics,Clinical Decision Support Systems (CDSS),Real-World Evidence (RWE),Explainable AI (XAI) in Healthcare.Abstract
Healthcare predictive analytics draws on advanced machine learning techniques to identify the risks, needs, and likely outcomes of patients in large clinical populations. Such predictive models can enable timely preventive and therapeutic interventions tailored to the individual patient and leapfrog disparate health services towards more equitable delivery. Enabling healthcare predictive analytics involves addressing a number of underlying requirements. First, predictive analytics call for large, representative clinical datasets that capture the information required for prediction, including data on the eventual outcome and associated risk factors. The most common sources of such data are electronic health records, routine administrative datasets, medical imaging, genomic, transcriptomic, and other omics data; such data sources can be prospectively integrated and linked across the life course of a patient to support prediction with longitudinal models. Second, predictive analytics are effective for addressing prediction tasks for which sufficient data are available. Such prediction tasks are usually framed as supervised machine learning problems, in which a model is learned from a training dataset, subsequently evaluated on a held-out test set, and finally deployed in the clinic. Unsupervised and semi-supervised approaches can also support predictive healthcare analytics by discovering subgroups of patients that are at elevated risk of an undesirable outcome. Third, prediction is usually only the first step; time-series or sequential models can leverage the results of prediction to support healthcare decision making, guiding timely allocation of resources to discrete cohorts of patients with specific needs.
References
1. Balagopalan, A., Baldini, I., Celi, L. A., Gichoya, J., McCoy, L. G., Naumann, T., Shalit, U., van der Schaar, M., & Wagstaff, K. L. (2024). Machine learning for healthcare that matters: Reorienting from technical novelty to equitable impact. PLOS Digital Health, 3(4), e0000474.
2. Schaekermann, M., Spitz, T., Pyles, M., Cole-Lewis, H., Wulczyn, E., Pfohl, S. R., Martin, D., Jaroensri, R., Keeling, G., Liu, Y., Lester, J., Hughes, C., Strachan, P., Tan, F., Bui, P., Mermel, C. H., Peng, L. H., Matias, Y., Corrado, G. S., ... Chen, P.-H. C. (2024). Health equity assessment of machine learning performance (HEAL): A framework and dermatology AI model case study. EClinicalMedicine, 70, 102479.
3. Roy, S., Morrell, S., Zhao, L., & Homayouni, R. (2024). Large-scale identification of social and behavioral determinants of health from clinical notes: Comparison of latent semantic indexing and generative pretrained transformer models. BMC Medical Informatics and Decision Making, 24, 296.
4. Fadiel, A., Eichenbaum, K. D., Abbasi, M., Lee, N. K., Odunsi, K., et al. (2024). Utilizing geospatial artificial intelligence to map cancer disparities across health regions. Scientific Reports, 14, 7693.
5. Gao, Y., & Cui, Y. (2024). Optimizing clinico-genomic disease prediction across ancestries: A machine learning strategy with Pareto improvement. Genome Medicine, 16, 76.
6. Yang, Y., Zhang, H., Gichoya, J. W., Katabi, D., & Ghassemi, M. (2024). The limits of fair medical imaging AI in real-world generalization. Nature Medicine, 30(10), 2838–2848.
7. Yang, J., Clifton, L., Dung, N. T., Phong, N. T., Yen, L. M., Thy, D. B. X., Soltan, A. A. S., Thwaites, L., & Clifton, D. A. (2024). Mitigating machine learning bias between high-income and low–middle-income countries for enhanced model fairness and generalizability. Scientific Reports, 14, 13318.
8. Jun, I., Ser, S. E., Cohen, S. A., Xu, J., Lucero, R. J., Bian, J., & Prosperi, M. (2024). Quantifying health outcome disparity in invasive methicillin-resistant Staphylococcus aureus infection using fairness algorithms on real-world data. Pacific Symposium on Biocomputing, 29, 419–432.
9. Gao, J., Chou, B., McCaw, Z. R., Thurston, H., Varghese, P., Hong, C., & Gronsbell, J. (2024). What is fair? Defining fairness in machine learning for health. arXiv Preprint arXiv:2406.09307.
10. Raza, S., Shaban-Nejad, A., Dolatabadi, E., & Mamiya, H. (2024). Exploring bias and prediction metrics to characterise the fairness of machine learning for equity-centered public health decision-making: A narrative review. arXiv Preprint arXiv:2408.13295.
11. Zink, A., Luan, H., & Chen, I. Y. (2024). Access to care improves EHR reliability and clinical risk prediction model performance. arXiv Preprint arXiv:2412.07712.
12. Gichoya, J. W., Banerjee, I., Bhimireddy, A. R., Burns, J. L., Celi, L. A., Chen, L. C., Correa, R., Dullerud, N., Ghassemi, M., Huang, S.-C., et al. (2024). AI recognition of patient race in medical imaging: Implications for health equity and fairness. Nature Medicine, 30(1), 45–54.
13. Seyyed-Kalantari, L., Zhang, H., McDermott, M. B. A., Chen, I. Y., & Ghassemi, M. (2024). Underdiagnosis bias of artificial intelligence algorithms applied to healthcare settings. NPJ Digital Medicine, 7(1), 1–10.
14. Chen, I. Y., Pierson, E., Rose, S., Joshi, S., Ferryman, K., & Ghassemi, M. (2024). Ethical machine learning in healthcare. Annual Review of Biomedical Data Science, 7, 123–148.
15. McCradden, M. D., Joshi, S., Mazwi, M., & Anderson, J. A. (2024). Toward equitable deployment of machine learning in clinical care. The Lancet Digital Health, 6(4), e241–e250.
16. Wiens, J., Saria, S., Sendak, M., Ghassemi, M., Liu, V. X., Doshi-Velez, F., Jung, K., Heller, K., Kale, D., Saeed, M., & Ossorio, P. N. (2024). Do no harm: A roadmap for responsible machine learning in healthcare. Nature Medicine, 30(2), 356–364.
17. Rajkomar, A., Hardt, M., Howell, M. D., Corrado, G., & Chin, M. H. (2024). Ensuring fairness in machine learning to advance health equity. New England Journal of Medicine AI, 1(2), AI2300187.
18. Obermeyer, Z., Powers, B., Vogeli, C., & Mullainathan, S. (2024). Dissecting racial bias in health algorithms and pathways to equitable machine learning. Health Affairs, 43(5), 711–720.
19. Agniel, D., Kohane, I. S., & Weber, G. M. (2024). Biases in electronic health record data for machine learning and implications for health equity. JAMIA Open, 7(1), ooae012.
20. Sendak, M. P., D’Arcy, J., Kashyap, S., Gao, M., Nichols, M., Corey, K., & Ratliff, W. (2024). A path toward health equity through trustworthy clinical machine learning systems. NPJ Digital Medicine, 7(1), 84.
