What question did this study set out to answer?

The study aims to assess the diagnostic accuracy of a machine learning model for classifying dementia stages using neuropsychological tests.

Dementia screening with the Rivermead Behavioural Memory Test: A machine learning analysis

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial evaluates machine learning classification for dementia in individuals, suggesting effective screening tests.

The study aims to assess the diagnostic accuracy of a machine learning model for classifying dementia stages using neuropsychological tests.
Retrospective cross-sectional single-center study analyzing 590 participants with suspected dementia.
Participants included 74 healthy controls, 190 with mild cognitive impairment, and 326 with dementia.
Machine learning model analyzed scores from multiple neuropsychological tests including RBMT and assessed performance via area under the ROC curve.
The machine learning model achieved an area under the ROC curve (AUC) of 0.898.
RBMT was the most significant contributor to classification accuracy, outperforming MMSE and MoCA-J.
In borderline cases of MMSE/MoCA-J, RBMT improved classification for distinguishing healthy from MCI and MCI from dementia.

Fujiwara et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark