Digital Toolbox May Help Diagnose Dementia Earlier

Detecting cognitive changes early in the onset of dementia would be a game-changer for thousands impacted by the disease and would allow for interventions well before significant brain changes occur.

While cognitive function is often measured using paper and pencil tests with scores calculated by the number of correct answers, this number (score) omits a lot of information about the process a person uses to answer a question that might reveal important information about their brain function.

In a new study from Boston University Schools of Medicine (BUSM) and Public Health (BUSPH), participants were tested using a digital pen that recorded the entire process of completing the cognitive test and allowed the researchers to pick up subtle measures of cognitive function beyond what is captured in traditional scoring.

"Rather than just being able to say that someone performed poorly on a cognitive test, these digital metrics allow us to delve further into the specific cognitive and physical functions that may be underlying poor test performance for a specific individual," said corresponding author Mandy (Mengtian) Du, PhD, a former graduate student at BUSPH.

Participants were asked to connect a series of dots spread out across a page in sequential numerical order (1, 2, 3, etc.) or to alternate between numbers and letters (such as 1, A, 2, B, and so on) while using a digital pen which records the movement of the pen across specialized paper and allows for a time-stamped playback of the entire drawing process. The researchers used the digital pen data to derive measures of drawing time, meaning the amount of time that the pen was used to draw on the paper and thinking time, or the time that the pen was held stationary and the participant was planning their next move.

According to the researchers, the digital pen data also allowed them to quantify the number of segments or straight lines that the participant used to complete the connections between the dots. They then looked at how these novel digital metrics were associated with other tests of cognitive and physical function. They found that the digital metrics were associated with specific cognitive functions such as processing speed, auditory attention, learning and working memory and physical functions such as walking speed and grip strength.

"We use our brains to carry out all of the activities in our daily lives. With digital technologies, such as digital pens or even our smart phones and activity trackers, we have the ability to record high-precision data on our cognitive behaviors every day," added coauthor Stacy Andersen, PhD, assistant professor of medicine at BUSM.

The researchers hope they will eventually be able to take what they have learned about early, subtle digital markers of cognitive impairment and assess cognitive health through the technologies that are used every day.

Du M, Andersen SL, Cosentino S, Boudreau RM, Perls TT, Sebastiani P.
Digitally generated Trail Making Test data: Analysis using hidden Markov modeling.
Alzheimer's Dement. 2022; 14:e12292. doi: 10.1002/dad2.12292

Most Popular Now

Do Fitness Apps do More Harm than Good?

A study published in the British Journal of Health Psychology reveals the negative behavioral and psychological consequences of commercial fitness apps reported by users on social media. These impacts may...

AI Tool Beats Humans at Detecting Parasi…

Scientists at ARUP Laboratories have developed an artificial intelligence (AI) tool that detects intestinal parasites in stool samples more quickly and accurately than traditional methods, potentially transforming how labs diagnose...

Making Cancer Vaccines More Personal

In a new study, University of Arizona researchers created a model for cutaneous squamous cell carcinoma, a type of skin cancer, and identified two mutated tumor proteins, or neoantigens, that...

AI can Better Predict Future Risk for He…

A landmark study led by University' experts has shown that artificial intelligence can better predict how doctors should treat patients following a heart attack. The study, conducted by an international...

A New AI Model Improves the Prediction o…

Breast cancer is the most commonly diagnosed form of cancer in the world among women, with more than 2.3 million cases a year, and continues to be one of the...

AI System Finds Crucial Clues for Diagno…

Doctors often must make critical decisions in minutes, relying on incomplete information. While electronic health records contain vast amounts of patient data, much of it remains difficult to interpret quickly...