Researchers are experimenting with artificial intelligence (AI) software that is increasingly able to tell whether you suffer from Parkinson's disease, schizophrenia, depression, or other types of mental disorders, simply from watching the way you type.
The researchers are able to make these astounding diagnoses, they say, because the capabilities of computing devices have become so granular that smartphones, tablets, and computers all can measure typing activity down to the millisecond.
Essentially, today's technologies, along with the capability of AI to learn to identify specific patters in data, offer researchers a powerful lens on even the slightest abnormalities in everyday typing behavior.
In a University of Texas study published earlier this year, for example, researchers were able to identify typists suffering from Parkinson's disease simply by capturing how their study subjects worked a keyboard over time, then running that data through pattern-finding AI software.
"We envision a future where keystroke and touch-screen tracking will become a standard metric in any digital device and added to your electronic medical record," says Teresa Arroyo Gallego, a co-author of the study and lead data scientist at Cambridge, MA-based nQ Medical, a company formed to commercialize the study's findings.
Meanwhile, researchers involved in similar work at Palo Alto, CA-based healthcare innovation company Mindstrong Health say they've been able to diagnose schizophrenia by analyzing typing keystroke patterns, as well looking closely at scrolling, swiping, and tapping behaviors.
"We believe that digital biomarkers are the foundation for measurement-based mental health care, for which there is a massive unmet patient need," says Mindstrong Health founder and CEO Paul Dagum.
Researchers at Hillsborough, CA-based NeuraMetrix are using their own spin on keystroke analysis to help detect other afflictions, including Alzheimer's disease, depression, Huntington's disease, REM sleep disorder, and heart problems.
In the Texas study, researchers say they approached the Parkinson's analysis challenge by first engineering software that could capture down to the millisecond how long a typist held down a key before moving to the next key. They also gave the software the ability to capture 'flight time', the number of milliseconds it takes a typist to actually move a finger from one key to the next.
Armed with such incredible depth of detail, diagnosing typists with Parkinson's was just a matter of training the AI software to find typing patterns shared by people suffering from the disease, then running new data through the trained AI software to find matches, which they did.
"These typing patterns are quite complex and greatly vary between individuals," says Luca Giancardo, co-author of the Texas study and assistant professor at the School of Biomedical Informatics of the University of Texas. "This is why we use machine learning algorithms to automatically identify the complex relationship between hold/flight time sequences by analyzing data from cohorts of people suffering from a neurodegenerative disease and healthy controls."
The telltale signs of Parkinson's disease can be seen in typing inconsistencies, according to the Texas researchers. Over time, Parkinson's forces its sufferers to type in ways different than their normal typing manner, as the condition sometimes slows fingers or makes them less flexible.
A great advantage of the Texas researchers' diagnostic method is its sheer convenience. Patients can work with their smartphones and other digital devices as usual, and software installed on those devices will transmit their use-history over the Internet to the computers of researchers.
Even better, the Texas researchers' work appears to diagnose Parkinson's disease much earlier than usual. Psychologists and other medical professionals find this heartening, because it may enable them to begin treating the disease well before it can destroy massive amounts of brain cells, according to Timothy Ellmore, an associate professor in psychology at the City College of New York.
Too often, by the time a diagnosis of Parkinson's disease is made, "A large proportion of the brain cells—i.e., dopamine neurons—implicated in this disorder have already died," Ellmore says. "It's too late to treat the actual disorder, and current medical approaches really only tackle the symptoms, which get worse and worse."
Giancardo and Arroyo Gallego's work could change all that, Ellmore says. "Their approach could lead to a better, earlier diagnosis, where neuro-protective treatments stand a better chance to halt or slow neuron death."
Ellmore observes, "The data from these keyboard tracking techniques need further validation to objectively track progression of Parkinson's signs." Still, he says, "Looking ahead, the tool could be really useful in augmenting the current tools available to clinicians. The great thing about Giancardo and Arroyo Gallego's work is that they are pushing the limit on data analysis and visualization."
Adds Zoltan Mari, Ruvo Family Chair for Parkinson's disease and director of the Parkinson's disease & Movement Disorder Program at the Cleveland Clinic, "My overall take is that this is a very interesting and likely helpful idea, which will require further larger-scale testing in real-world clinical scenarios, further validation, and extensive feasibility testing."
Mari said he expects research like the Texas study "to greatly evolve and become refined, thanks to the availability of increasing and massive databases, as well as our continuously improving abilities to better use big data."
Joe Dysart is an Internet speaker and business consultant based in Manhattan, NY, USA.
No entries found