TY - JOUR
T1 - The Risk of Coding Racism into Pediatric Sepsis Care
T2 - The Necessity of Antiracism in Machine Learning
AU - Sveen, William
AU - Dewan, Maya
AU - Dexheimer, Judith W.
N1 - Publisher Copyright:
© 2022 Elsevier Inc.
PY - 2022/8
Y1 - 2022/8
N2 - Machine learning holds the possibility of improving racial health inequalities by compensating for human bias and structural racism. However, unanticipated racial biases may enter during model design, training, or implementation and perpetuate or worsen racial inequalities if ignored. Pre-existing racial health inequalities could be codified into medical care by machine learning without clinicians being aware. To illustrate the importance of a commitment to antiracism at all stages of machine learning, we examine machine learning in predicting severe sepsis in Black children, focusing on the impacts of structural racism that may be perpetuated by machine learning and difficult to discover. To move toward antiracist machine learning, we recommend partnering with ethicists and experts in model development, enrolling representative samples for training, including socioeconomic inputs with proximate causal associations to racial inequalities, reporting outcomes by race, and committing to equitable models that narrow inequality gaps or at least have equal benefit.
AB - Machine learning holds the possibility of improving racial health inequalities by compensating for human bias and structural racism. However, unanticipated racial biases may enter during model design, training, or implementation and perpetuate or worsen racial inequalities if ignored. Pre-existing racial health inequalities could be codified into medical care by machine learning without clinicians being aware. To illustrate the importance of a commitment to antiracism at all stages of machine learning, we examine machine learning in predicting severe sepsis in Black children, focusing on the impacts of structural racism that may be perpetuated by machine learning and difficult to discover. To move toward antiracist machine learning, we recommend partnering with ethicists and experts in model development, enrolling representative samples for training, including socioeconomic inputs with proximate causal associations to racial inequalities, reporting outcomes by race, and committing to equitable models that narrow inequality gaps or at least have equal benefit.
UR - http://www.scopus.com/inward/record.url?scp=85132443544&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85132443544&partnerID=8YFLogxK
U2 - 10.1016/j.jpeds.2022.04.024
DO - 10.1016/j.jpeds.2022.04.024
M3 - Article
C2 - 35469891
AN - SCOPUS:85132443544
SN - 0022-3476
VL - 247
SP - 129
EP - 132
JO - Journal of Pediatrics
JF - Journal of Pediatrics
ER -