Fairness in Low Birthweight Predictive Models: Implications of Excluding Race/Ethnicity. - National Genomics Data Center (CNCB-NGDC)

Advanced Search

Fairness in Low Birthweight Predictive Models: Implications of Excluding Race/Ethnicity.

Clare C Brown, Michael Thomsen, Benjamin C Amick, J Mick Tilford, Keneshia Bryant-Moore, Horacio Gomez-Acevedo

Author Information

Clare C Brown: Department of Health Policy and Management, Fay W Boozman College of Public Health, University of Arkansas for Medical Sciences, 4301 W Markham St Slot #820-12, Little Rock, AR, 72205, USA. ccbrown@uams.edu. ORCID
Michael Thomsen: Department of Health Policy and Management, Fay W Boozman College of Public Health, University of Arkansas for Medical Sciences, 4301 W Markham St Slot #820-12, Little Rock, AR, 72205, USA.
Benjamin C Amick: Department of Epidemiology, Fay W Boozman College of Public Health, University of Arkansas for Medical Sciences, Little Rock, AR, USA.
J Mick Tilford: Department of Health Policy and Management, Fay W Boozman College of Public Health, University of Arkansas for Medical Sciences, 4301 W Markham St Slot #820-12, Little Rock, AR, 72205, USA.
Keneshia Bryant-Moore: Department of Health Behavior and Health Education, Fay W Boozman College of Public Health, University of Arkansas for Medical Sciences, Little Rock, AR, USA.
Horacio Gomez-Acevedo: Department of Biomedical Informatics, College of Medicine, University of Arkansas for Medical Sciences, Little Rock, AR, USA. ORCID

PMID: 39881067 DOI: 10.1007/s40615-025-02296-x

CONTEXT: To evaluate algorithmic fairness in low birthweight predictive models.
STUDY DESIGN: This study analyzed insurance claims (n = 9,990,990; 2013-2021) linked with birth certificates (n = 173,035; 2014-2021) from the Arkansas All Payers Claims Database (APCD).
METHODS: Low birthweight (< 2500 g) predictive models included four approaches (logistic, elastic net, linear discriminate analysis, and gradient boosting machines [GMB]) with and without racial/ethnic information. Model performance was assessed overall, among Hispanic individuals, and among non-Hispanic White, Black, Native Hawaiian/Other Pacific Islander, and Asian individuals using multiple measures of predictive performance (i.e., AUC [area under the receiver operating characteristic curve] scores, calibration, sensitivity, and specificity).
RESULTS: AUC scores were lower (underperformed) for Black and Asian individuals relative to White individuals. In the strongest performing model (i.e., GMB), the AUC scores for Black (0.718 [95% CI: 0.705-0.732]) and Asian (0.655 [95% CI: 0.582-0.728]) populations were lower than the AUC for White individuals (0.764 [95% CI: 0.754-0.775 ]). Model performance measured using AUC was comparable in models that included and excluded race/ethnicity; however, sensitivity (i.e., the percent of records correctly predicted as "low birthweight" among those who actually had low birthweight) was lower and calibration was weaker, suggesting underprediction for Black individuals when race/ethnicity were excluded.
CONCLUSIONS: This study found that racially blind models resulted in underprediction and reduced algorithmic performance, measured using sensitivity and calibration, for Black populations. Such under prediction could unfairly decrease resource allocation needed to reduce perinatal health inequities. Population health management programs should carefully consider algorithmic fairness in predictive models and associated resource allocation decisions.

Equity Algorithmic fairness Low birthweight

Shachar C, Gerke S. Prevention of bias and discrimination in clinical practice algorithms. JAMA. 2023;329(4):283–4. [PMID: 36602791]
Gianfrancesco MA, Tamang S, Yazdany J, Schmajuk G. Potential biases in machine learning algorithms using electronic health record data. JAMA Intern Med. 2018;178(11):1544–7. [PMID: 30128552]
Bonner TJ, Ayyanar P, Milam AJ, Blocker Renaldo C. Understanding the complexities of equity within the emergence and utilization of AI in academic medical centers. Am J Manag Care. 2024:30(6 Spec No.):SP425–SP427
Nong P, Raj M, Platt J. Integrating predictive models into care: facilitating informed decision-making and communicating equity issues. AJMC. 2022;28(1):18–24.
Murphy A, Bowen K, Naqa IME, Yoga B, Green BL. 2024 Bridging health disparities in the data-driven world of artificial intelligence: a narrative review. J Racial Ethn Health Disparities. 1–13 https://doi.org/10.1007/s40615-024-02057-2
Cary MP Jr, Zink A, Wei S, et al. Mitigating racial and ethnic bias and advancing health equity in clinical algorithms: a scoping review: scoping review examines racial and ethnic bias in clinical algorithms. Health Aff. 2023;42(10):1359–68. [DOI: 10.1377/hlthaff.2023.00553]
Siddique SM, Tipton K, Leas B, et al. The impact of health care algorithms on racial and ethnic disparities: a systematic review. Ann Intern Med. 2024;177(4):484–96. [PMID: 38467001]
Haider SA, Borna S, Gomez-Cabello CA, Pressman SM, Haider CR, Forte AJ. 2024 The algorithmic divide: a systematic review on AI-driven racial disparities in healthcare. J Racial Ethn Health Disparities. 1–30. https://doi.org/10.1007/s40615-024-02237-0
Hussain SA, Bresnahan M, Zhuang J. 2024 The bias algorithm: how AI in healthcare exacerbates ethnic and racial disparities–a scoping review. Ethn Health. 1–18. https://doi.org/10.1080/13557858.2024.2422848
Vyas DA, Eisenstein LG, Jones DS. Hidden in plain sight—reconsidering the use of race correction in clinical algorithms. N Engl J Med. 2020;383(9):874–82. [PMID: 32853499]
Khor S, Haupt EC, Hahn EE, Lyons LJL, Shankaran V, Bansal A. Racial and ethnic bias in risk prediction models for colorectal cancer recurrence when race and ethnicity are omitted as predictors. JAMA Netw Open. 2023;6(6):e2318495. [PMID: 37318804]
Chohlas-Wood A, Coots M, Goel S, Nyarko J. Designing equitable algorithms. Nat Comput Sci. 2023;3(7):601–10. [PMID: 38177749]
Patterson JK, Thorsten VR, Eggleston B, et al. Building a predictive model of low birth weight in low-and middle-income countries: a prospective cohort study. BMC Pregnancy Childbirth. 2023;23:600. [PMID: 37608358]
Martin JA, Hamilton BE, Osterman MJ, Driscoll AK. Division of Vital Statistics Births: final data for 2019. Natl Vital Stat Rep. 2021;70(2):1–50. [PMID: 35157571]
Schempf AH, Branum AM, Lukacs SL, Schoendorf KC. The contribution of preterm birth to the black–white infant mortality gap, 1990 and 2000. Am J Public Health. 2007;97(7):1255–60. [PMID: 17538050]
Choi KH, Martinson ML. The relationship between low birthweight and childhood health: disparities by race, ethnicity, and national origin. Ann Epidemiol. 2018;28(10):704–9.
Ng JH, Ye F, Ward LM, Haffer SC, Scholle SH. Data on race, ethnicity, and language largely incomplete for managed care plan members. Health Aff. 2017;36(3):548–52. [DOI: 10.1377/hlthaff.2016.1044]
State Health Access Data Assistance Center. Race/ethnicity data in CMS Medicaid (T-MSIS) Analytic Files updated December 2021—features 2019 data. Published August 2020. Updated January 2022. Accessed Jan 8 2025 at https://www.shadac.org/news/raceethnicity-data-cms-medicaid-t-msis-analytic-files-updated-december-2021-%E2%80%93-features-2019
McCradden MD, Joshi S, Mazwi M, Anderson JA. Ethical limitations of algorithmic fairness solutions in health care machine learning. Lancet Digit Health. 2020;2(5):e221–3. [PMID: 33328054]
Baker DW, Hasnain-Wynia R, Kandula NR, Thompson JA, Brown ER. Attitudes toward health care providers collecting information about patients’ race ethnicity and language. Med Care. 2007;45(11):1034–42. [PMID: 18049343]
Hasnain‐Wynia R, Baker DW. Obtaining data on patient race, ethnicity, and primary language in health care organizations: current challenges and proposed solutions. Health Serv Res. 2006;41(4p1):1501–18.
Smedley BD, Stith AY, Nelson AR, Institute of Medicine, Board on Health Sciences Policy, Committee on understanding and eliminating racial and ethnic disparities in health care. Unequal treatment: Confronting racial and ethnic disparities in health care. Washington DC: National Academies Press: 2003
Arkansas Center for Health Improvement. Arkansas all-payer claims database (APCD). Web site. Accessed Jan 8 2025 at https://www.arkansasapcd.net/Home/
Elixhauser A, Steiner C, Harris DR, Coffey RM. Comorbidity measures for use with administrative data. Med Care. 1998;36(1):8–27. [PMID: 9431328]
Rezaeiahari M, Brown CC, Ali MM, Datta J, Tilford JM. Understanding racial disparities in severe maternal morbidity using Bayesian network analysis. PLoS ONE. 2021;16(10):e0259258. [PMID: 34705872]
Mhyre JM, Bateman BT, Leffert LR. Influence of patient comorbidities on the risk of near-miss maternal morbidity or mortality. J Am Soc Anesthesiologists. 2011;115(5):963–72.
Leonard SA, Kennedy CJ, Carmichael SL, Lyell DJ, Main EK. An expanded obstetric comorbidity scoring system for predicting severe maternal morbidity. Obstet Gynecol. 2020;136(3):440–9. [PMID: 32769656]
Reid LD, Creanga AA. Severe maternal morbidity and related hospital quality measures in Maryland. J Perinatol. 2018;38(8):997–1008. [PMID: 29593355]
Hing AK, Chantarat T, Fashaw-Walters S, Hunt SL, Hardeman RR. Instruments for racial health equity: a scoping review of structural racism measurement, 2019–2021. Epidemiol Rev. 2024;46(1):1–26. [PMID: 38412307]
Chantarat T, Van Riper DC, Hardeman RR. The intricacy of structural racism measurement: a pilot development of a latent-class multidimensional measure. EClinicalMedicine. 2021;40:101092. [PMID: 34746713]
Ren Y, Wu D, Tong Y, López-DeFede A, Gareau S. Issue of data imbalance on low birthweight baby outcomes prediction and associated risk factors identification: establishment of benchmarking key machine learning models with data rebalancing strategies. J Med Internet Res. 2023;25:e44081. [PMID: 37256674]
Khan W, Zaki N, Masud MM, et al. Infant birth weight estimation and low birth weight classification in united Arab emirates using machine learning algorithms. Sci Rep. 2022;12(1):12110. [PMID: 35840605]
Gervasi SS, Chen IY, Smith-McLallen A, et al. The potential for bias in machine learning and opportunities for health insurers to address it: article examines the potential for bias in machine learning and opportunities for health insurers to address it. Health Aff. 2022;41(2):212–8. [DOI: 10.1377/hlthaff.2021.01287]
Hurd TC, Payton FC, Hood DB. Targeting machine learning and artificial intelligence algorithms in health care to reduce bias and improve population health. Milbank Q. 2024;102(3):577–604. [PMID: 39116187]
Buckley A, Sestito S, Ogundipe T, et al. Racial and ethnic disparities among women undergoing a trial of labor after cesarean delivery: performance of the VBAC calculator with and without patients’ race/ethnicity. Reprod Sci. 2022;29(7):2030–8. [PMID: 35534768]
Park Y, Hu J, Singh M, et al. Comparison of methods to reduce bias from clinical prediction models of postpartum depression. JAMA Netw Open. 2021;4(4):e213909. [PMID: 33856478]
Yoo RM, Dash D, Lu JH, et al. Investigating real-world consequences of biases in commonly used clinical calculators. AJMC. 2023;29(1):e1–7.
Bekele WT. Machine learning algorithms for predicting low birth weight in ethiopia. BMC Med Inform Decis Mak. 2022;22:232. [PMID: 36064400]
Ranjbar A, Montazeri F, Farashah MV, Mehrnoush V, Darsareh F, Roozbeh N. Machine learning-based approach for predicting low birth weight. BMC Pregnancy Childbirth. 2023;23(1):803. [PMID: 37985975]
Obermeyer Z, Powers B, Vogeli C, Mullainathan S. Dissecting racial bias in an algorithm used to manage the health of populations. Science. 2019;366(6464):447–53. [PMID: 31649194]
Braveman P. The Black-White disparity in preterm birth: Race or racism? Milbank Q. 2023;101(Suppl 1):356–78. [PMID: 37096619]
Chin MH, Afsar-Manesh N, Bierman AS, et al. Guiding principles to address the impact of algorithm bias on racial and ethnic disparities in health and health care. JAMA Netw Open. 2023;6(12):e2345050. [PMID: 38100101]
Hasnain R, Fujiura GT, Capua JE, Bui TTT, Khan S. Disaggregating the Asian “other”: Heterogeneity and methodological issues in research on Asian Americans with disabilities. Societies. 2020;10(3):58. [DOI: 10.3390/soc10030058]
Roohan PJ, Josberger RE, Acar J, Dabir P, Feder HM, Gagliano PJ. Validation of birth certificate data in new york state. J Community Health. 2003;28(5):335–46. [PMID: 14535599]
Northam S, Knapp TR. The reliability and validity of birth certificates. J Obstet Gynecol Neonatal Nurs. 2006;35(1):3–12. [PMID: 16466348]
Alhusen JL, Bower KM, Epstein E, Sharps P. Racial discrimination and adverse birth outcomes: an integrative review. J Midwifery Womens Health. 2016;61(6):707–20. [PMID: 27737504]
Leifheit KM, Schwartz GL, Pollack CE, et al. Severe housing insecurity during pregnancy: association with adverse birth and infant outcomes. Int J Environ Res Public Health. 2020;17(22):8659. [PMID: 33233450]
Gete DG, Waller M, Mishra GD. Effects of maternal diets on preterm birth and low birth weight: a systematic review. Br J Nutr. 2020;123(4):446–61. [PMID: 31711550]
Wilcox AJ. On the importance—and the unimportance—of birthweight. Int J Epidemiol. 2001;30(6):1233–41. [PMID: 11821313]
Ratwani RM, Sutton K, Galarraga JE. Addressing AI algorithmic bias in health care. JAMA. 2024;332(13):1051–2. [PMID: 39230911]

R01 DK125641/NIDDK NIH HHS
1R01DK125641/NIDDK NIH HHS
U54 TR001629/NCATS NIH HHS
R01 MH133857/NIMH NIH HHS
U54TR001629/NCATS NIH HHS
1K01MD018072/NIMHD NIH HHS
R01MH133857/NIMH NIH HHS
K01 MD018072/NIMHD NIH HHS

Journal Article