Academic Journal
Accounting for racial bias and social determinants of health in a model of hypertension control.
| Τίτλος: | Accounting for racial bias and social determinants of health in a model of hypertension control. |
|---|---|
| Συγγραφείς: | Hu Y; Department of Electrical and Computer Engineering, Department of Biomedical Engineering, Division of Systems Engineering, and Faculty of Computing & Data Sciences, Boston University, 8 Saint Mary's St., Boston, MA, 02215, USA., Cordella N; Department of Medicine, Boston Medical Center and Boston University School of Medicine, Boston, MA, USA., Mishuris RG; Mass General Brigham and Harvard Medical School, Boston, MA, USA., Paschalidis IC; Department of Electrical and Computer Engineering, Department of Biomedical Engineering, Division of Systems Engineering, and Faculty of Computing & Data Sciences, Boston University, 8 Saint Mary's St., Boston, MA, 02215, USA. yannisp@bu.edu. |
| Πηγή: | BMC medical informatics and decision making [BMC Med Inform Decis Mak] 2025 Feb 03; Vol. 25 (1), pp. 53. Date of Electronic Publication: 2025 Feb 03. |
| Τύπος έκδοσης: | Journal Article |
| Γλώσσα: | English |
| Στοιχεία περιοδικού: | Publisher: BioMed Central Country of Publication: England NLM ID: 101088682 Publication Model: Electronic Cited Medium: Internet ISSN: 1472-6947 (Electronic) Linking ISSN: 14726947 NLM ISO Abbreviation: BMC Med Inform Decis Mak Subsets: MEDLINE |
| Imprint Name(s): | Original Publication: London : BioMed Central, [2001- |
| Ιατρικοί όροι (MeSH): | Hypertension*/ethnology , Hypertension*/therapy , Social Determinants of Health*/statistics & numerical data , Social Determinants of Health*/ethnology , Racism*/statistics & numerical data, Black or African American/statistics & numerical data ; Humans ; Female ; Middle Aged ; Male ; Retrospective Studies ; Aged ; Adult ; Boston ; White |
| Περίληψη: | Background: Hypertension control remains a critical problem and most of the existing literature views it from a clinical perspective, overlooking the role of sociodemographic factors. This study aims to identify patients with not well-controlled hypertension using readily available demographic and socioeconomic features and elucidate important predictive variables. Methods: In this retrospective cohort study, records from 1/1/2012 to 1/1/2020 at the Boston Medical Center were used. Patients with either a hypertension diagnosis or related records (≥ 130 mmHg systolic or ≥ 90 mmHg diastolic, n = 164,041) were selected. Models were developed to predict which patients had uncontrolled hypertension defined as systolic blood pressure (SBP) records exceeding 160 mmHg. Results: The predictive model of high SBP reached an Area Under the Receiver Operating Characteristic Curve of 74.49% ± 0.23%. Age, race, Social Determinants of Health (SDoH), mental health, and cigarette use were predictive of high SBP. Being Black or having critical social needs led to higher probability of uncontrolled SBP. To mitigate model bias and elucidate differences in predictive variables, two separate models were trained for Black and White patients. Black patients face a 4.7 INLINEMATH higher False Positive Rate (FPR) and a 0.58 INLINEMATH lower False Negative Rate (FNR) compared to White patients. Decision threshold differentiation was implemented to equalize FNR. Race-specific models revealed different sets of social variables predicting high SBP, with Black patients being affected by structural barriers (e.g., food and transportation) and White patients by personal and demographic factors (e.g., marital status). Conclusions: Models using non-clinical factors can predict which patients exhibit poorly controlled hypertension. Racial and SDoH variables are significant predictors but lead to biased predictive models. Race-specific models are not sufficient to resolve such biases and require further decision threshold tuning. A host of structural socioeconomic factors are identified to be targeted to reduce disparities in hypertension control. (© 2025. The Author(s).) |
| Competing Interests: | Declarations. Ethics approval and consent to participate: The study adhered to the Helsinki Declaration and was approved by the Boston University Medical Campus (IRB #H-32061) and Boston University Institutional Review Boards. Since it analyzed de-identified records, it was classified as non-human subject research. Informed consent has been waived. The Boston University team has signed a Data Use Agreement (DUA) with the Boston Medical Center to access the data. Consent for publication: Not applicable. Competing interests: The authors declare no competing interests. |
| References: | J Am Med Inform Assoc. 2017 Jan;24(1):162-171. (PMID: 27497800) Circulation. 2005 Mar 15;111(10):1233-41. (PMID: 15769763) Circulation. 2017 Nov 21;136(21):e393-e423. (PMID: 29061565) JAMA. 2003 Jul 9;290(2):199-206. (PMID: 12851274) J Mach Learn Res. 2018 Jan;19(1):517-564. (PMID: 34421397) Int J Med Inform. 2022 Jul;163:104762. (PMID: 35429722) Am J Hypertens. 2004 Oct;17(10):963-70. (PMID: 15485761) Med Care. 2019 Jun;57 Suppl 6 Suppl 2:S133-S139. (PMID: 31095052) Soc Sci Med. 2007 Nov;65(9):1853-66. (PMID: 17640788) BMC Health Serv Res. 2020 Mar 16;20(1):216. (PMID: 32178663) Blood Press. 2011 Aug;20(4):196-203. (PMID: 21299436) BMC Med Inform Decis Mak. 2023 Mar 1;23(1):44. (PMID: 36859187) Ann Intern Med. 2008 Jan 15;148(2):102-10. (PMID: 18195335) Ann Fam Med. 2010 Jul-Aug;8(4):348-53. (PMID: 20644190) Hypertension. 2013 Feb;61(2):319-26. (PMID: 23232644) Curr Pharm Des. 2010;16(23):2518-25. (PMID: 20550499) JAMA. 1999 Nov 10;282(18):1737-44. (PMID: 10568646) J Hypertens. 2015 Feb;33(2):221-9. (PMID: 25479029) Hypertension. 2010 Jun;55(6):1339-45. (PMID: 20439822) JAMA. 2003 May 21;289(19):2560-72. (PMID: 12748199) J Comput Graph Stat. 2024;33(1):192-207. (PMID: 39184344) Circ Heart Fail. 2022 Nov;15(11):e009473. (PMID: 36378761) Epidemiology. 2008 Jul;19(4):590-8. (PMID: 18480733) Hypertension. 2010 Apr;55(4):1058-62. (PMID: 20157053) J Am Coll Cardiol. 2018 May 15;71(19):e127-e248. (PMID: 29146535) Int J Med Inform. 2020 Jul;139:104122. (PMID: 32339929) Hypertension. 1990 Aug;16(2):170-9. (PMID: 2379950) Arch Intern Med. 2005 Oct 10;165(18):2098-104. (PMID: 16216999) Circulation. 2016 Aug 9;134(6):441-50. (PMID: 27502908) Int J Equity Health. 2016 Nov 17;15(1):146. (PMID: 27852274) Am J Med. 2009 May;122(5):464-71. (PMID: 19375556) |
| Grant Information: | R01 GM135930 United States GM NIGMS NIH HHS; N00014-19-1-2571 Office of Naval Research; IIS-1914792 National Science Foundation; R01 GM135930 United States NH NIH HHS; UL54 TR004130 Boston University Clinical and Translational Science Award (CTSA) |
| Contributed Indexing: | Keywords: Hypertension; Machine learning; Racial bias; Social determinants of health |
| Entry Date(s): | Date Created: 20250203 Date Completed: 20250505 Latest Revision: 20260706 |
| Update Code: | 20260706 |
| PubMed Central ID: | PMC11792567 |
| DOI: | 10.1186/s12911-025-02873-4 |
| PMID: | 39901187 |
| Βάση Δεδομένων: | MEDLINE |
| ISSN: | 1472-6947 |
|---|---|
| DOI: | 10.1186/s12911-025-02873-4 |