Literature DB >> 35396996

Assessing socioeconomic bias in machine learning algorithms in health care: a case study of the HOUSES index.

Young J Juhn1,2, Euijung Ryu3, Chung-Il Wi1,2, Katherine S King3, Momin Malik4, Santiago Romero-Brufau5, Chunhua Weng6, Sunghwan Sohn7, Richard R Sharp8, John D Halamka4,9.   

Abstract

OBJECTIVE: Artificial intelligence (AI) models may propagate harmful biases in performance and hence negatively affect the underserved. We aimed to assess the degree to which data quality of electronic health records (EHRs) affected by inequities related to low socioeconomic status (SES), results in differential performance of AI models across SES.
MATERIALS AND METHODS: This study utilized existing machine learning models for predicting asthma exacerbation in children with asthma. We compared balanced error rate (BER) against different SES levels measured by HOUsing-based SocioEconomic Status measure (HOUSES) index. As a possible mechanism for differential performance, we also compared incompleteness of EHR information relevant to asthma care by SES.
RESULTS: Asthmatic children with lower SES had larger BER than those with higher SES (eg, ratio = 1.35 for HOUSES Q1 vs Q2-Q4) and had a higher proportion of missing information relevant to asthma care (eg, 41% vs 24% for missing asthma severity and 12% vs 9.8% for undiagnosed asthma despite meeting asthma criteria). DISCUSSION: Our study suggests that lower SES is associated with worse predictive model performance. It also highlights the potential role of incomplete EHR data in this differential performance and suggests a way to mitigate this bias.
CONCLUSION: The HOUSES index allows AI researchers to assess bias in predictive model performance by SES. Although our case study was based on a small sample size and a single-site study, the study results highlight a potential strategy for identifying bias by using an innovative SES measure.
© The Author(s) 2022. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.

Entities:  

Keywords:  HOUSES; algorithmic bias; artificial intelligence; electronic health records; social determinants of health

Mesh:

Year:  2022        PMID: 35396996      PMCID: PMC9196683          DOI: 10.1093/jamia/ocac052

Source DB:  PubMed          Journal:  J Am Med Inform Assoc        ISSN: 1067-5027            Impact factor:   7.942


  63 in total

1.  Primary care physicians who treat blacks and whites.

Authors:  Peter B Bach; Hoangmai H Pham; Deborah Schrag; Ramsey C Tate; J Lee Hargraves
Journal:  N Engl J Med       Date:  2004-08-05       Impact factor: 91.245

2.  Ensuring Fairness in Machine Learning to Advance Health Equity.

Authors:  Alvin Rajkomar; Michaela Hardt; Michael D Howell; Greg Corrado; Marshall H Chin
Journal:  Ann Intern Med       Date:  2018-12-04       Impact factor: 25.391

3.  Invited commentary: Using area-based socioeconomic measures--think conceptually, act cautiously.

Authors:  Arline T Geronimus
Journal:  Am J Epidemiol       Date:  2006-09-12       Impact factor: 4.897

4.  Development and initial testing of a new socioeconomic status measure based on housing data.

Authors:  Young J Juhn; Timothy J Beebe; Dawn M Finnie; Jeff Sloan; Philip H Wheeler; Barbara Yawn; Arthur R Williams
Journal:  J Urban Health       Date:  2011-10       Impact factor: 3.671

5.  Pursuing minimally disruptive medicine: disruption from illness and health care-related demands is correlated with patient capacity.

Authors:  Kasey R Boehmer; Nathan D Shippee; Timothy J Beebe; Victor M Montori
Journal:  J Clin Epidemiol       Date:  2016-01-11       Impact factor: 6.437

6.  The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database.

Authors:  Stan Benjamens; Pranavsingh Dhunnoo; Bertalan Meskó
Journal:  NPJ Digit Med       Date:  2020-09-11

7.  Comparison of individual-level versus area-level socioeconomic measures in assessing health outcomes of children in Olmsted County, Minnesota.

Authors:  Maria R Pardo-Crespo; Nirmala Priya Narla; Arthur R Williams; Timothy J Beebe; Jeff Sloan; Barbara P Yawn; Philip H Wheeler; Young J Juhn
Journal:  J Epidemiol Community Health       Date:  2013-01-15       Impact factor: 3.710

8.  Artificial intelligence-enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial.

Authors:  Xiaoxi Yao; David R Rushlow; Jonathan W Inselman; Rozalina G McCoy; Thomas D Thacher; Emma M Behnken; Matthew E Bernard; Steven L Rosas; Abdulla Akfaly; Artika Misra; Paul E Molling; Joseph S Krien; Randy M Foss; Barbara A Barry; Konstantinos C Siontis; Suraj Kapa; Patricia A Pellikka; Francisco Lopez-Jimenez; Zachi I Attia; Nilay D Shah; Paul A Friedman; Peter A Noseworthy
Journal:  Nat Med       Date:  2021-05-06       Impact factor: 53.440

9.  Association between an individual housing-based socioeconomic index and inconsistent self-reporting of health conditions: a prospective cohort study in the Mayo Clinic Biobank.

Authors:  Euijung Ryu; Janet E Olson; Young J Juhn; Matthew A Hathcock; Chung-Il Wi; James R Cerhan; Kathleen J Yost; Paul Y Takahashi
Journal:  BMJ Open       Date:  2018-05-14       Impact factor: 2.692

10.  Artificial intelligence-assisted clinical decision support for childhood asthma management: A randomized clinical trial.

Authors:  Hee Yun Seol; Pragya Shrestha; Joy Fladager Muth; Chung-Il Wi; Sunghwan Sohn; Euijung Ryu; Miguel Park; Kathy Ihrke; Sungrim Moon; Katherine King; Philip Wheeler; Bijan Borah; James Moriarty; Jordan Rosedahl; Hongfang Liu; Deborah B McWilliams; Young J Juhn
Journal:  PLoS One       Date:  2021-08-02       Impact factor: 3.240

View more
  1 in total

1.  Consideration of bias in data sources and digital services to advance health equity.

Authors:  Suzanne Bakken
Journal:  J Am Med Inform Assoc       Date:  2022-06-14       Impact factor: 7.942

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.