Changes in drawing traits have been reported in people with cognitive impairments in the early stages, but most studies have used only a single drawing task.
In a study recently published in the Journal of Alzheimer’s Disease, researchers at the University of Tsukuba and IBM Research have found that they could classify people with normal cognition, mild cognitive impairment (MCI), and Alzheimer’s disease (AD) much more accurately by combining features extracted from five different drawing tasks that using only one or two tasks.
About 75% of people with dementia have not been diagnosed, and this is due in part to the lack of accurate screening tests that can be done outside of the doctor’s office or hospital. Recently, the search for better screening techniques has become more important as new therapies are developed that can slow the progression of cognitive impairment. Researchers at Tsukuba University wanted to address this lack of accurate screening tests by automated drawing analysis.
While it is clear that drawing and pause-related drawing features can be used to detect cognitive impairments, most screening tests remain relatively inaccurate. We wondered what would happen if we analyzed these features while people were doing different drawing tasks. “
Tetsuaki Arai, lead author and professor of the study, Tsukuba University
To do so, the researchers used five different drawing tests that capture different aspects of cognition and are commonly used in the diagnosis of AD and MCI. While performing these tests, 22 different drawing characteristics, related to pencil pressure, pencil posture, speed, and pauses, were automatically analyzed by test. The researchers then compared these characteristics with the scores of seven different cognitive function tests and used a computer program to see how the features of the drawing could be used to identify people with normal cognition, MCI, or AD.
“We were amazed at how well the combination of drawing features drawn from multiple tasks worked by capturing different and complementary aspects of cognitive impairments,” explains Professor Arai. “The classification accuracy of three groups of the five tests was 75.2%, almost 10% better than that of any of the tests themselves.”
In addition, most of the drawing features that were different between the three groups had greater changes between normal and AD subjects compared to normal and MCI subjects; this is important because MCI is often considered an early (and less severe) form. of AD.
“While this was a relatively small study, the results are encouraging,” says Professor Arai. “Our results pave the way for better screening tests for cognitive impairments.”
With the growing number of therapies targeting the early stages of cognitive impairment, screening tests are becoming increasingly important. Better screening will lead to an earlier diagnosis, which in turn will improve patients ’quality of life.
Source:
Magazine reference:
Masatomo, K., et al. (2022) Automated early detection of Alzheimer’s disease by capturing impairments in multiple cognitive domains with multiple drawing tasks. Journal of Alzheimer’s disease. doi.org/10.3233/JAD-215714