Publication
ICDH 2022
Conference paper

Automated Analysis of Drawing Process for Detecting Prodromal and Clinical Dementia

Abstract

Early diagnosis of dementia, particularly in the prodromal stage (i.e., mild cognitive impairment, or MCI), has become a research and clinical priority, but remains challenging. Automated analysis of the drawing process has been studied as a promising means for screening prodromal and clinical dementia, providing multifaceted information encompassing characteristics in pen trajectory and posture, writing pressure, and pauses between strokes that would reflect cognitive and motor impairments related to dementia. Here, we examined the feasibility of using features characterizing the drawing process not only for detecting prodromal and clinical dementia and but also for predicting the severity of cognitive impairments assessed by Mini-Mental State Examination (MMSE) as well as the severity of neuropathological changes assessed by medial temporal lobe atrophy. To this end, we collected drawing data with a digitizing tablet and pen from 145 older adults consisting of three clinical diagnostic groups of cognitively normal (CN), MCI, and dementia. The nested cross-validation results showed that the combination of drawing features could classify the clinical diagnostic groups of CN, MCI, and dementia with AUC of 0.909 and 75.1% accuracy (CN vs. MCI: 82.4% accuracy; CN vs. dementia: 92.2% accuracy; MCI vs. dementia: 80.3% accuracy); and could predict MMSE scores with an R2 of 0.491 and severity of medial temporal lobe atrophy with R2 of 0.293. Our findings suggest that automated analysis of the drawing process provide information about cognitive impairments and neuropathological changes due to dementia, which can help to identify prodromal and clinical dementia as a digital biomarker.

Date

10 Jul 2022

Publication

ICDH 2022

Authors

Topics

Share