USING SUPERVISED MACHINE LEARNING METHODS TO IDENTIFY INDIVIDUALS AT RISK OF DEMENTIA
2024

Using Machine Learning to Identify Dementia Risk

Sample size: 2235 publication Evidence: moderate

Author Information

Author(s): Ayushi Divecha, Sarah Bannon, Kristen Dams-O’Connor

Primary Institution: Icahn School of Medicine at Mount Sinai

Hypothesis

Can machine learning models effectively identify individuals at risk of developing dementia?

Conclusion

The study aims to use machine learning to predict dementia risk in cognitively normal individuals.

Supporting Evidence

  • The study uses data from five large NIH-funded studies of aging.
  • 2235 individuals were included in the analysis with a mean follow-up of 8.6 years.
  • Random forest models will be used to predict dementia risk.

Takeaway

Researchers are using computers to help find people who might get dementia in the future, so they can get help early.

Methodology

The study uses clinical and cognitive data from large NIH-funded studies and applies random forest models to predict dementia risk.

Limitations

Cognitive function was assessed using different measures across cohorts, which may affect comparisons.

Participant Demographics

Participants were cognitively normal individuals from three NIH-funded cohorts.

Digital Object Identifier (DOI)

10.1093/geroni/igae098.1382

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication