Addressing the Challenge of Biomedical Data Inequality: An Artificial Intelligence Perspective DOI Creative Commons

Yan Gao,

Teena Sharma, Yan Cui

et al.

Annual Review of Biomedical Data Science, Journal Year: 2023, Volume and Issue: 6(1), P. 153 - 171

Published: April 27, 2023

Artificial intelligence (AI) and other data-driven technologies hold great promise to transform healthcare confer the predictive power essential precision medicine. However, existing biomedical data, which are a vital resource foundation for developing medical AI models, do not reflect diversity of human population. The low representation in data has become significant health risk non-European populations, growing application opens new pathway this manifest amplify. Here we review current status inequality present conceptual framework understanding its impacts on machine learning. We also discuss recent advances algorithmic interventions mitigating disparities arising from inequality. Finally, briefly newly identified disparity quality among ethnic groups potential

Language: Английский

One Size Does Not Fit All: Methodological Considerations for Brain-Based Predictive Modeling in Psychiatry DOI Creative Commons
Elvisha Dhamala, B.T. Thomas Yeo, Avram J. Holmes

et al.

Biological Psychiatry, Journal Year: 2022, Volume and Issue: 93(8), P. 717 - 728

Published: Sept. 29, 2022

Language: Английский

Citations

61
Increasing diversity in connectomics with the Chinese Human Connectome Project DOI
Jianqiao Ge, Guoyuan Yang,

Meizhen Han

et al.

Nature Neuroscience, Journal Year: 2022, Volume and Issue: 26(1), P. 163 - 172

Published: Dec. 19, 2022

Language: Английский

Citations

57
Ethics of AI in Radiology: A Review of Ethical and Societal Implications DOI Creative Commons
Melanie Goisauf, Mónica Cano Abadía

Frontiers in Big Data, Journal Year: 2022, Volume and Issue: 5

Published: July 14, 2022

Artificial intelligence (AI) is being applied in medicine to improve healthcare and advance health equity. The application of AI-based technologies radiology expected diagnostic performance by increasing accuracy simplifying personalized decision-making. While this technology has the potential services, many ethical societal implications need be carefully considered avoid harmful consequences for individuals groups, especially most vulnerable populations. Therefore, several questions are raised, including (1) what types issues raised use AI biomedical research, (2) how these tackled radiology, case breast cancer? To answer questions, a systematic review academic literature was conducted. Searches were performed five electronic databases identify peer-reviewed articles published since 2017 on topic ethics radiology. results show that discourse mainly addressed expectations challenges associated with medical AI, particular bias black box issues, various guiding principles have been suggested ensure AI. We found remain underexplored, more attention needs paid addressing discriminatory effects injustices. conclude critical reflection identified gaps from philosophical STS perspective, underlining integrate social science perspective developments future.

Language: Английский

Citations

54
Reply to: Multivariate BWAS can be replicable with moderate sample sizes DOI Creative Commons
Brenden Tervo‐Clemmens, Scott Marek, Roselyne J. Chauvin

et al.

Nature, Journal Year: 2023, Volume and Issue: 615(7951), P. E8 - E12

Published: March 8, 2023

Language: Английский

Citations

30
The challenges and prospects of brain-based prediction of behaviour DOI
Jianxiao Wu, Jingwei Li, Simon B. Eickhoff

et al.

Nature Human Behaviour, Journal Year: 2023, Volume and Issue: 7(8), P. 1255 - 1264

Published: July 31, 2023

Language: Английский

Citations

27
In vivo whole-cortex marker of excitation-inhibition ratio indexes cortical maturation and cognitive ability in youth DOI Creative Commons
Shaoshi Zhang, Bart Larsen, Valerie J. Sydnor

et al.

Proceedings of the National Academy of Sciences, Journal Year: 2024, Volume and Issue: 121(23)

Published: May 30, 2024

A balanced excitation-inhibition ratio (E/I ratio) is critical for healthy brain function. Normative development of cortex-wide E/I remains unknown. Here, we noninvasively estimate a putative marker whole-cortex by fitting large-scale biophysically plausible circuit model to resting-state functional MRI (fMRI) data. We first confirm that our generates realistic dynamics in the Human Connectome Project. Next, show estimated sensitive gamma-aminobutyric acid (GABA) agonist benzodiazepine alprazolam during fMRI. Alprazolam-induced changes are spatially consistent with positron emission tomography measurement receptor density. then investigate relationship between and neurodevelopment. find declines heterogeneously across cerebral cortex youth, greatest reduction occurring sensorimotor systems relative association systems. Importantly, among children same chronological age, lower (especially cortex) linked better cognitive performance. This result replicated North American (8.2 23.0 y old) Asian (7.2 7.9 cohorts, suggesting more mature indexes improved cognition normative development. Overall, findings open door studying how disrupted trajectories may lead dysfunction psychopathology emerges youth.

Language: Английский

Citations

15
Functional brain networks are associated with both sex and gender in children DOI Creative Commons
Elvisha Dhamala,

Dani S. Bassett,

B.T. Thomas Yeo

et al.

Science Advances, Journal Year: 2024, Volume and Issue: 10(28)

Published: July 12, 2024

Sex and gender are associated with human behavior throughout the life span across health disease, but whether they similar or distinct neural phenotypes is unknown. Here, we demonstrate that, in children, sex uniquely reflected intrinsic functional connectivity of brain. Somatomotor, visual, control, limbic networks preferentially sex, while network correlates more distributed cortex. These results suggest that irreducible to one another not only society also biology.

Language: Английский

Citations

15
White matter and literacy: A dynamic system in flux DOI Creative Commons
Ethan Roy, Adam Richie-Halford, John Kruper

et al.

Developmental Cognitive Neuroscience, Journal Year: 2024, Volume and Issue: 65, P. 101341 - 101341

Published: Jan. 6, 2024

Cross-sectional studies have linked differences in white matter tissue properties to reading skills. However, past reported a range of, sometimes conflicting, results. Some suggest that act as individual-level traits predictive of skill, whereas others skill and develop function an individual's educational experience. In the present study, we tested two hypotheses: a) diffusion reflect stable brain characteristics relate individual ability or b) is dynamic system, with learning over time. To answer these questions, examined relationship between five-year longitudinal dataset series large-scale, single-observation, cross-sectional datasets (N=14,249 total participants). We find gains correspond changes matter. datasets, no evidence for hypothesis predict skill. These findings highlight link processes learning.

Language: Английский

Citations

12
A survey of recent methods for addressing AI fairness and bias in biomedicine DOI Creative Commons
Yifan Yang, Mingquan Lin, Han Zhao

et al.

Journal of Biomedical Informatics, Journal Year: 2024, Volume and Issue: 154, P. 104646 - 104646

Published: April 25, 2024

Artificial intelligence (AI) systems have the potential to revolutionize clinical practices, including improving diagnostic accuracy and surgical decision-making, while also reducing costs manpower. However, it is important recognize that these may perpetuate social inequities or demonstrate biases, such as those based on race gender. Such biases can occur before, during, after development of AI models, making critical understand address enable accurate reliable application models in settings. To mitigate bias concerns during model development, we surveyed recent publications different debiasing methods fields biomedical natural language processing (NLP) computer vision (CV). Then discussed methods, data perturbation adversarial learning, been applied domain bias.

Language: Английский

Citations

11
The power of many brains: Catalyzing neuropsychiatric discovery through open neuroimaging data and large-scale collaboration DOI Creative Commons
Bin Lü, Xiao Chen, F. Xavier Castellanos

et al.

Science Bulletin, Journal Year: 2024, Volume and Issue: 69(10), P. 1536 - 1555

Published: March 6, 2024

Recent advances in open neuroimaging data are enhancing our comprehension of neuropsychiatric disorders. By pooling images from various cohorts, statistical power has increased, enabling the detection subtle abnormalities and robust associations, fostering new research methods. Global collaborations imaging have furthered knowledge neurobiological foundations brain disorders aided imaging-based prediction for more targeted treatment. Large-scale magnetic resonance initiatives driving innovation analytics supporting generalizable psychiatric studies. We also emphasize significant role big understanding neural mechanisms early identification precise treatment However, challenges such as harmonization across different sites, privacy protection, effective sharing must be addressed. With proper governance science practices, we conclude with a projection how large-scale resources could revolutionize diagnosis, selection, outcome prediction, contributing to optimal health.

Language: Английский

Citations

11