Characteristics of Drawing Process Differentiate Alzheimer’s Disease and Dementia with Lewy Bodies

Abstract

Background: Early differential diagnosis of Alzheimer’s disease (AD) and dementia with Lewy bodies (DLB) is important for treatment and disease management, but it remains challenging. Although computer-based drawing analysis may help differentiate AD and DLB, it has not been extensively studied. Objective: We aimed to identify the differences in features characterizing the drawing process between AD, DLB, and cognitively normal (CN) individuals, and to evaluate the validity of using these features to identify and differentiate AD and DLB. Methods: We collected drawing data with a digitizing tablet and pen from 123 community-dwelling older adults in three clinical diagnostic groups of mild cognitive impairment or dementia due to AD (n = 47) or Lewy body disease (LBD; n = 27), and CN (n = 49), matched for their age, sex, and years of education. We then investigated drawing features in terms of the drawing speed, pressure, and pauses. Results: Reduced speed and reduced smoothness in speed and pressure were observed particularly in the LBD group, while increased pauses and total durations were observed in both the AD and LBD groups. Machine-learning models using these features achieved an area under the receiver operating characteristic curve (AUC) of 0.80 for AD versus CN, 0.88 for LBD versus CN, and 0.77 for AD versus LBD. Conclusion: Our results indicate how different types of drawing features were particularly discriminative between the diagnostic groups, and how the combination of these features can facilitate the identification and differentiation of AD and DLB.

A New Early Warning Method for Human-Computer Interaction of Alzheimer's Disease Patients Based on Deep Learning

“…In this study, the traditional early AD prediction model based on clock score calculation did not show a good prediction ability. This may be due to the fact that the traditional prediction method based on clock score calculation is aimed at the dCDT of digital pen [14][15][16][17]. However, in this study, fingertip interaction was used instead of digital pen.…”

“…For normal cognition (NC) and MCI, the model's classification accuracy was 77.5%. Using a machine learning model, Yasunori Yamada et al [17] investigated the stress and other factors involved in the testing procedure. The model's NC and AD classification accuracy was 80%.…”

Speech patterns during memory recall relates to early tau burden across adulthood

“…This suggests that speech changes reflect development of AD pathology even in the absence of overt cognitive impairment. Although many aspects of speech can be quantified, individuals with mild cognitive impairment and AD dementia exhibit longer and more frequent pauses in speech than CU older adults, 5–14 and between‐utterance pauses in particular may reflect memory retrieval and semantic knowledge deficits that are the earliest AD cognitive symptoms 7 . Changes in patterns that occur within utterances, such as increased repetition (which would reduce the percentage of unique words) and reduced speech rate, may also reflect memory ability and, thus, be especially relevant to AD.…”

Digitális múlt, analóg jövő

“…Yamada et al (2022) investigated hand drawing as a tool for early detection of Alzheimer's disease and dementia. Early detection in these diseases is very important, it can increase the effectiveness of therapy.…”

“…Early detection in these diseases is very important, it can increase the effectiveness of therapy. The drawings were made on a digital interface by the subjects.During the studies, subjects in the early stages of the diseases showed decreasing line drawing speed, decreasing pen pressure, increasing pauses and total duration (Yamada et al, 2022). Chang and Yu (2010) investigated the rate of developmental delays in children with different literacy difficulties compared to children with healthy development in learning Chinese characters.…”