Digital Detection of Dementia (D CUBED) Trials
2024

Digital Detection of Dementia Trials

Sample size: 5960 publication Evidence: moderate

Author Information

Author(s): Boustani Malaz, Fowler Nicole

Primary Institution: Indiana University

Hypothesis

Can electronic health record data and machine learning algorithms effectively detect dementia?

Conclusion

The study found that using a Passive Digital Marker and Quick Dementia Rating Scale can accurately diagnose dementia in primary care settings.

Supporting Evidence

  • The Passive Digital Marker achieved 80% accuracy in dementia detection.
  • The Quick Dementia Rating Scale had 85% accuracy for dementia diagnosis.
  • The trials recruited diverse primary care practices across different settings.

Takeaway

Researchers used computer data to help doctors find out if older people have dementia, and it worked really well.

Methodology

The study involved pragmatic cluster-randomized controlled trials comparing usual care with the PDM and QDRS in primary care clinics.

Limitations

The study may have limitations related to the non-interruptive nature of the Best Practice Alert used in the first year.

Participant Demographics

The trial included 5960 older patients with a mean age of 71.9 years, 61% female, and 51% African American.

Digital Object Identifier (DOI)

10.1093/geroni/igae098.1928

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication