Cross-ethnicity/race generalization failure of behavioral prediction from resting-state functional connectivity

Li, J.; Bzdok, Danilo; Chen, Jianzhong; Tam, Angela; Ooi, Leon Qi Rong; Holmes, Avram J.; Ge, Tian; Patil, Kaustubh R.; Jabbi, Mbemba; Eickhoff, Simon B.; Yeo, B.T. Thomas; Genon, Sarah

doi:10.1126/sciadv.abj1812

Cited by 85 publications

(89 citation statements)

References 97 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, models that are fit on a biased demographic group often do not generalize to more diverse samples(67). It is possible that sampling procedures impact the relationship between diffusion properties of the white matter and academic skills and may explain the seemingly contradictory results between the present study and past findings.…”

Section: Discussionmentioning

confidence: 99%

White matter and literacy: a dynamic system in flux

Roy

Richie-Halford

Kruper

et al. 2022

Preprint

View full text Add to dashboard Cite

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

show abstract

Section: Discussionmentioning

confidence: 99%

White matter and literacy: a dynamic system in flux

Roy

Richie-Halford

Kruper

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Diversity in the datasets becomes an increasingly important point that is being addressed by researchers to counteract bias that can be potentially harmful (Leavy, 2018 ). Nonetheless, ensuring diversity in and of itself is not enough (Li et al, 2022 ); more research is needed to understand how discrimination intersects with socioeconomic factors to keep bias from being introduced into healthcare algorithms through structural inequalities in society (Quinn et al, 2021 ). Anticipating structural bias in datasets and understanding the social implications of using AI systems before their implementation is considered best practice; some authors in the sample even propose that failing to do so should be qualified as scientific misconduct (Owens and Walker, 2020 ).…”

Section: Discussionmentioning

confidence: 99%

Ethics of AI in Radiology: A Review of Ethical and Societal Implications

Goisauf¹,

Abadía²

2022

Front. Big Data

View full text Add to dashboard Cite

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

show abstract

“…This literature is playing a crucial role in shaping policies for deployment of automated diagnostic models. Consequently, there is also a large amount of recent work on identifying such biases 19,22,25 , and developing techniques to mitigate these biases 20,36,37 . In this study, we have shown that when machine learning models are trained using well-established data preprocessing and hyper-parameter optimization techniques on data from large-scale multi-site studies for three neurological disorders, namely Alzheimer's disease, schizophrenia, and autism spectrum disorder, the predictions of these models need not be biased.…”

Section: Relationship Of This Work To Existing Literature On Identify...mentioning

confidence: 99%

Bias in Machine Learning Models Can Be Significantly Mitigated by Careful Training: Evidence from Neuroimaging Studies

Wang,

Chaudhari,

Davatzikos

2022

Preprint

View full text Add to dashboard Cite

Despite the great promise that machine learning has offered in many fields of medicine, it has also raised concerns about potential biases and poor generalization across genders, age distributions, races and ethnicities, hospitals, and data acquisition equipment and protocols. In the current study, and in the context of three brain diseases, we provide experimental data which support that when properly trained, machine learning models can generalize well across diverse conditions and do not suffer from biases. Specifically, by using multi-study magnetic resonance imaging consortia for diagnosing Alzheimer's disease, schizophrenia, and autism spectrum disorder, we find that, the accuracy of well-trained models is consistent across different subgroups pertaining to attributes such as gender, age, and racial groups, as also different clinical studies. We find that models that incorporate multi-source data from demographic, clinical, genetic factors and cognitive scores are also unbiased. These models have better predictive accuracy across subgroups than those trained only with structural measures in some cases but there are also situations when these additional features do not help.

show abstract

Cross-ethnicity/race generalization failure of behavioral prediction from resting-state functional connectivity

Cited by 85 publications

References 97 publications

White matter and literacy: a dynamic system in flux

White matter and literacy: a dynamic system in flux

Ethics of AI in Radiology: A Review of Ethical and Societal Implications

Bias in Machine Learning Models Can Be Significantly Mitigated by Careful Training: Evidence from Neuroimaging Studies

Contact Info

Product

Resources

About