Disentangling Socioeconomic Status and Race in Infant Brain, Birth Weight, and Gestational Age at Birth: A Neural Network Analysis

Sarullo, Kathryn; Barch, Deanna M.; Smyser, Christopher D.; Rogers, Cynthia; Warner, Barbara; Miller, John P.; England, Sarah K.; Luby, Joan L.; Swamidass, S. Joshua

doi:10.1016/j.bpsgos.2023.05.001

Cited by 4 publications

(1 citation statement)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, lower income may prevent a child from participating in extracurricular activities that then impact other aspects of their life. Recent evidence further suggests that racerelated stressors can have effects prenatally and resultant effects on infant development may be non-linear 39 . In the present study, parts of the insular and orbital sulci showed percentages of the total effect mediated by individual and neighborhood factors over 100% (i.e., ab path greater than the total effect) suggesting there are likely interactions (i.e., non-linear associations) among the variables related to race-related differences in neurobiology.…”

Section: Discussionmentioning

confidence: 99%

Population-level normative models reveal race- and socioeconomic-related variability in cortical thickness of threat neurocircuitry

Harnett,

Fani,

Rowland

et al. 2024

Commun Biol

View full text Add to dashboard Cite

The inequitable distribution of economic resources and exposure to adversity between racial groups contributes to mental health disparities within the United States. Consideration of the potential neurodevelopmental consequences, however, has been limited particularly for neurocircuitry known to regulate the emotional response to threat. Characterizing the consequences of inequity on threat neurocircuitry is critical for robust and generalizable neurobiological models of psychiatric illness. Here we use data from the Adolescent Brain and Cognitive Development Study 4.0 release to investigate the contributions of individual and neighborhood-level economic resources and exposure to discrimination. We investigate the potential appearance of race-related differences using both standard methods and through population-level normative modeling. We show that, in a sample of white and Black adolescents, racial inequities in socioeconomic factors largely contribute to the appearance of race-related differences in cortical thickness of threat neurocircuitry. The race-related differences are preserved through the use of population-level models and such models also preserve associations between cortical thickness and specific socioeconomic factors. The present findings highlight that such socioeconomic inequities largely underlie race-related differences in brain morphology. The present findings provide important new insight for the generation of generalizable neurobiological models of psychiatric illness.

show abstract

Section: Discussionmentioning

confidence: 99%

Population-level normative models reveal race- and socioeconomic-related variability in cortical thickness of threat neurocircuitry

Harnett,

Fani,

Rowland

et al. 2024

Commun Biol

View full text Add to dashboard Cite

show abstract

Socioeconomic Disparities in Hypothalamic-Pituitary-Adrenal Axis Regulation and Prefrontal Cortical Structure

Merz,

Myers,

Hansen

et al. 2024

Biological Psychiatry Global Open Science

View full text Add to dashboard Cite

Understanding and mitigating the impact of race with adversarial autoencoders

Sarullo,

Swamidass

2024

Commun Med

View full text Add to dashboard Cite

Background Artificial intelligence carries the risk of exacerbating some of our most challenging societal problems, but it also has the potential of mitigating and addressing these problems. The confounding effects of race on machine learning is an ongoing subject of research. This study aims to mitigate the impact of race on data-derived models, using an adversarial variational autoencoder (AVAE). In this study, race is a self-reported feature. Race is often excluded as an input variable, however, due to the high correlation between race and several other variables, race is still implicitly encoded in the data. Methods We propose building a model that (1) learns a low dimensionality latent spaces, (2) employs an adversarial training procedure that ensure its latent space does not encode race, and (3) contains necessary information for reconstructing the data. We train the autoencoder to ensure the latent space does not indirectly encode race. Results In this study, AVAE successfully removes information about race from the latent space (AUC ROC = 0.5). In contrast, latent spaces constructed using other approaches still allow the reconstruction of race with high fidelity. The AVAE’s latent space does not encode race but conveys important information required to reconstruct the dataset. Furthermore, the AVAE’s latent space does not predict variables related to race ( R 2 = 0.003), while a model that includes race does ( R 2 = 0.08). Conclusions Though we constructed a race-independent latent space, any variable could be similarly controlled. We expect AVAEs are one of many approaches that will be required to effectively manage and understand bias in ML.

show abstract

Disentangling Socioeconomic Status and Race in Infant Brain, Birth Weight, and Gestational Age at Birth: A Neural Network Analysis

Cited by 4 publications

References 53 publications

Population-level normative models reveal race- and socioeconomic-related variability in cortical thickness of threat neurocircuitry

Population-level normative models reveal race- and socioeconomic-related variability in cortical thickness of threat neurocircuitry

Socioeconomic Disparities in Hypothalamic-Pituitary-Adrenal Axis Regulation and Prefrontal Cortical Structure

Understanding and mitigating the impact of race with adversarial autoencoders

Contact Info

Product

Resources

About