A SCOPING REVIEW OF MACHINE LEARNING STUDIES ON DEMENTIA RISK FOR ETHNORACIAL MINORITIES
2024

Machine Learning Studies on Dementia Risk for Ethnoracial Minorities

Sample size: 14 publication Evidence: low

Author Information

Author(s): Hong Michin, Ji Soo-Yeon, Kim Seon, Kim Kyeongmo

Primary Institution: Indiana University Indianapolis

Hypothesis

The study aims to review dementia risk for ethnoracial minorities using machine learning methods.

Conclusion

Machine learning studies have made limited progress in understanding dementia risk among ethnoracial minorities.

Supporting Evidence

  • The review included 14 studies published since 2020.
  • Most studies found a lower risk of dementia among non-Hispanic Whites compared to other groups.
  • Various machine learning techniques were employed, including neural networks and random forests.
  • The studies often lacked adequate representation of ethnoracial minorities.

Takeaway

This study looked at how well machine learning helps understand dementia risk for different racial groups, and it found that there's still a lot we don't know.

Methodology

The study reviewed 599 articles, narrowed down to 14 that met inclusion criteria, and analyzed them for key themes.

Potential Biases

The studies primarily treated race as a predictor without adequately representing minority groups.

Limitations

Most studies lacked minority samples, which may contribute to the existing racial gap in dementia research.

Participant Demographics

The studies included non-Hispanic Whites, Hispanics, and Non-Hispanic Blacks.

Digital Object Identifier (DOI)

10.1093/geroni/igae098.3305

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication