Targeting Machine Learning and Artificial Intelligence Algorithms in Health Care to Reduce Bias and Improve Population Health

The US health care system is complex and mired in rising costs, an aging population, a declining workforce, administrative inefficiency, access issues, and suboptimal health outcomes that collectively propagate health inequities.^1-4 It ranks last among industrialized nations for maternal and avoidable mortality.⁵ Over a decade ago, value-based health care merged the medical and population health models and entrenched the social determinants of health in health care delivery by linking it to reimbursement in the public and private health sectors. The overall goal of achieving an efficient, lower-cost path to achieving health equity and improving population health would in part be realized through a deeper understanding of the intersectionality of the biomedical model of health, social contexts, social position, and systematic differences in health and health outcomes.^6-8 However, incentivized Centers for Medicare and Medicaid Services care delivery models to deliver value-based care amplified the problem because, in part, of 60% penetrance of value-based care, physician adoption of only 49%, and questionable improvement in patient outcomes for high-resource service lines.^9, 10 With nearly a $4 trillion annual expenditure on US health care, artificial intelligence is being embraced as the solution to mitigate these problems.¹¹ However, technology in and of itself is unlikely to resolve health care challenges because of inherent gaps, deficiencies, and exclusionary cycles within the system itself and the need for integration through biopsychosocial lenses of public and population health and medicine.^12-14

References

1. Schneider EC, Shah A, Doty MM, Tikkanen R, Fields K, Williams RD II.Mirror, mirror 2021: reflecting poorly: health care in the U.S. compared toother high-income countries. The Commonwealth Fund. August 4, 2021.Accessed August 1, 2024. https://commonwealthfund.org/publications/fund-reports/2021/aug/mirror-mirror-2021-reflecting-poorly
2. Glassman JK. Health care providers are raking in profits by exploiting pro-grams meant for the poor. The Hill. July 18, 2023. Accessed August 5,2024.https://thehill.com/opinion/healthcare/4101826-health-care-providers-are-raking-in-profits-by-exploiting-programs-meant-for-the-poor/
3. Dall T, Reynolds R, Chakrabarti R, Ruttinger C, Zarek P, Parker O; Global-Data. The Complexities of Physician Supply and Demand: Projections from 2021 to 2036. Association of American Medical Colleges; 2024.
4. Gooch K. 6 predictions for the future healthcare workforce. Becker’s Hospital Review. December 17, 2021. Accessed April 19, 2024.https://beckershospitalreview.com/workforce/6-predictions-for-the-future-healthcare-workforce.html?oly_enc_id=9174C2123745F8T
5. NHE fact sheet. Centers for Medicare and Medicaid Services. UpdatedJune 16, 2024. Accessed July 31, 2024. https://www.cms.gov/data-research/statistics-trends-and-reports/national-health-expenditure-data/nhe-fact-sheet
6. Olstad DL, McIntyre L. Reconceptualizing precision public health. BMJ Open.2019;9(9):e030279.
7. Marmot MG, Smith GD, Stansfeld S, et al. Health inequalities among British civil servants: the Whitehall II study. Lancet. 1991;337(8754):1387-1393.
8. Commission on Social Determinants of Health. Closing the gap in a generation: health equity through action on the social determinants of health.World Health Organization. August 27, 2008. Accessed July 31, 2024. https://www.who.int/publications/i/item/WHO-IER-CSDH-08.1
9. Rubin R. How value-based Medicare payments exacerbate health care disparities. JAMA. 2018;319(10):968-970.
10. Damberg CL, Elliott MN. Opportunities to address health disparities in performance-based accountability and payment programs. JAMA HealthForum. 2021;2(6):e211143.
11. Hsu HE, Wang R, Broadwell C, et al. Association between federal value-based incentive programs and health care-associated infection rates in safety-net and non–safety-net hospitals. JAMA Netw Open. 2020;3(7):e209700.
12. NHE fact sheet. Centers for Medicare and Medicaid Services. UpdatedJune 12, 2024. Accessed December 7, 2023. https://cms.gov/data-research/statistics-trends-and-reports/national-health-expenditure-data/nhe-fact-sheet
13. Bracic A, Callier SL, Price WN II. Exclusion cycles: reinforcing disparities in medicine. Science. 2022;377(6611):1158-1160.
14. King DW, Hurd TC. Hajek RA, Jones LA. Using a biopsychosocial approach to address health disparities—one person’s vision. J Cancer Educ. 2009;24(Suppl2):S26-S32