The study found that characteristics of patients’ drawing process can determine the type of dementia

The two most common neurodegenerative dementias are Alzheimer’s disease (AD) and dementia with Lewy bodies (DLB). The symptoms of these two diseases often overlap, which can make diagnosis difficult. Although CSF and neuroimaging biomarkers are the most validated diagnostic biomarkers, they can be invasive, time-consuming, and expensive. Japanese researchers have found that characteristics of patients’ drawing process can differentiate between AD and DLB patients, offering a low-cost, non-invasive and rapid screening tool.

Recently, drawing test analysis has been shown to be useful in identifying AD as well as Parkinson’s disease, another form of Lewy body spectrum disorders. However, no such investigation has been conducted to identify DLB or distinguish between AD and DLB. Researchers from the University of Tsukuba and IBM Research set out to explore what can be achieved for diagnostic decision-making by combining data obtained from these drawing tests with machine learning approaches.

Using an electronic tablet and pen, AD and DLB patients and healthy controls completed digital versions of conventional drawing tests such as drawing a clock face and mastering pentagon patterns. They found that DLB patients showed differences from healthy controls in speed-, pressure-, and pause-related features, while AD patients showed differences only in pause-related features. These discriminative differences in features characterizing the drawing process reflected cognitive and motor impairments in AD and DLB. These features were combined into a machine learning model to classify patients based on their drawing profiles. The model distinguished the three groups with high accuracy, and importantly, AD patients from LBD patients.

Interestingly, different drawing tasks played a determining role in the classification of different pairs of these three diagnostic groups. This is the first study to highlight the utility of combining multiple drawing tasks to enable the identification and differentiation of AD and DLB.”

Professor Tetsuaki Arai, lead author

Previous studies have suggested that the visuospatial deficits of AD and DLB patients reflect specific neuropathological features of the disease. The team’s next step is therefore to investigate pathological biomarkers, which Professor Arai says “may reveal unique signatures of drawing impairments that reflect the underlying pathologies of AD and DLB”.

Importantly, the proposed approach can be easily incorporated into clinical practice. Commercial digital devices are readily available to collect data from patients, so clinicians can use this highly feasible, easy-to-use and economical tool to improve diagnostic decision-making in dementia without significantly changing their current routines.

This work was supported by the Japan Society for the Promotion of Science, KAKENHI (grant 19H01084). The donor had no active role in the scientific research or reporting of the study.