Determination of people with cognitive impairment based on their drawing behaviors
Changes in drawing strokes have been reported in people with early-stage cognitive impairment, but most studies have used only one drawing task.
In a study recently published in the Alzheimer’s Disease Journalresearchers from the University of Tsukuba and IBM Research found that they could classify people with normal cognition, mild cognitive impairment (MCI) and Alzheimer’s disease (AD) much more accurately by combining strokes from five different drawing tasks than using just one or two tasks.
About 75% of people with dementia have not been diagnosed, and this is partly due to the lack of accurate screening tests that can be done outside of a doctor’s office or hospital. Recently, the quest for better screening techniques has become more important as new therapies are developed that can slow the progression of cognitive impairment. Researchers at the University of Tsukuba wanted to address this lack of accurate screening tests by using automatic drawing analysis.
Although it is clear that drawing strokes related to movement and pausing can be used to screen for cognitive impairment, most screening tests remain relatively imprecise. We wondered what might happen if we were to analyze these strokes while people were performing a range of different drawing tasks..”
Tetsuaki Arai, Study Lead Author and Professor, University of Tsukuba
To do this, the researchers used five different drawing tests that capture different aspects of cognition and are commonly used when diagnosing AD and MCI. While performing these tests, 22 different design features; related to pen pressure, pen posture, speed, and pauses; were automatically analyzed by test. The researchers then compared these features with scores from seven different cognitive function tests and used a computer program to see how well the drawing traits could be used to identify people with normal cognition, MCI or AD.
“We were surprised how well the combination of drawing strokes taken from multiple tasks worked in capturing different complementary aspects of cognitive impairment,” says Professor Arai. “The accuracy of the three-group classification of the five tests was 75.2%, nearly 10% better than any of the tests alone.”
Additionally, the majority of drawing features that were different between the three groups showed 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. from AD.
“Although this is a relatively small study, the results are encouraging,” says Professor Arai. “Our results pave the way for better screening tests for cognitive impairment.”
With the ever-increasing number of therapies targeting the early stages of cognitive impairment, screening tests are becoming increasingly important. Better screening will lead to earlier diagnoses, which in turn will improve the quality of life of patients.
Masatomo, K. et al. (2022) Automated early detection of Alzheimer’s disease by capturing impairments in multiple cognitive domains with multiple drawing tasks. Alzheimer’s Disease Journal. doi.org/10.3233/JAD-215714