Computer Technology Can Now Analyze People’s Typing Patterns for Signs of Alzheimer’s Disease

Alzheimer’s disease is not currently a curable condition, but detecting it early is essential to being able to slow the progression of Alzheimer’s-related symptoms. Alzheimer’s disease is notoriously difficult to diagnose, but now a new technology may be able to determine whether a person likely has Alzheimer’s disease based on the patterns found in their typing.

NeuroQWERTY technology is capable of analyzing people’s typing for signs of motor deficiencies and other patterns that may indicate a cognitive condition like Parkinson’s or Alzheimer’s disease. The team hopes their new technology will reshape cognitive screening in the future.

Until now, the world of neuroscience has largely remained in the “analog era.” Other sciences have advanced toward digital forms of diagnosis and treatment, but this particular branch has not.

“Neurology is particularly slow in digital adoption, partly because it is not as well understood as diseases like oncology and diabetes, and there are fewer standards against which to validate technologies,” says nQ Medical’s chief data scientist Teresa Arroyo-Gallego, who helped develop neuroQWERTY technology.

Remaining in the analog era, however, has significant disadvantages, as Arroyo-Gallego explains:

“These tests are not only very subjective but also expensive and time-intensive since they require an expert to be with the patient. This also means they can only be conducted in a clinic, and the patient will be aware they’re being monitored, which can introduce noise to the results.”

The team hopes that they can solve some of these issues by analyzing typing patterns in elderly people. When they search for Parkinson’s disease, they analyze the time taken between pressing and releasing a key, but the technology can analyze other metrics as well. Dementia is not as well-defined as Parkinson’s disease, making it difficult to find a metric that does a good job diagnosing the disease, but the team believes it can be done.

“The initial hypothesis was very similar to the one in Parkinson’s – i.e. if there’s any damage or any decline that affects those processes, that should be in some way reflected in the way we type,” says Arroyo-Gallego. “We asked the patients to go through a series of semi-controlled typing tasks, both on mechanical keyboards and touch screen devices that were designed to mimic natural use of the device.”

Ultimately, the team decided to use metrics that are similar to those for Parkinson’s, but with five extra typing metrics. Those metrics include analyzing pauses between different units of language, the semantic and syntactic complexity of what is being typed, and the keystroke dynamics based on the physical position of the key on the keyboard.

“Even when we had a very small subset of data we were able to achieve a very good separation between what we defined as cognitively normal and cognitively impaired,” says Arroyo-Gallego. “The performance was comparable to the Mini-Mental State Examination (MMSE), one of the standards for cognitive screening, and similar to the Montreal Cognitive Assessment (MoCA), which is the gold standard for screening in Alzheimer’s disease. We’ve seen that we’re not only able to detect cognitive decline but we are able to break down those typing patterns to specifically assess how different aspects are affected by the disease.”

The nQ team believes they can use this system to identify biomarkers that are linked to aspects of Alzheimer’s disease such as attention, verbal memory, or nonverbal memory.

“We want to close the loop from typing to the brain and provide a better understanding of cognitive function,” says Arroyo-Gallego.

If the neuroQWERTY technology proves effective with Alzheimer’s disease, Arroyo-Gallego hopes it will help provide a more objective and sensitive way of monitoring all aspects of cognition. It will likely be useful not only for screening but also for treatment and potential self-monitoring for patients.

“We want to give physicians visibility on what is really happening to the patient and how they are evolving, rather than just a snapshot from a single clinic visit,” she says. “There might even be existing Alzheimer’s treatments out there that work, and we just haven’t been able to measure their positive impact properly,” she says.

The team also hopes to look into other diseases the technology may be able to help with, such as ALS, multiple sclerosis, concussion, or cancer-related cognitive impairment.

“Enabling precision medicine and personalised care is something that is critical in many of these conditions diseases, as they vary massively on a case by case basis,” says Arroyo-Gallego.

We hope to see this technology working its magic soon to help people with Alzheimer’s get earlier diagnoses and better treatment and monitoring.