Digital pen technique can diagnose dementia faster and earlierView gallery - 2 images
Noting that most current methods of diagnosing cognitive diseases can only detect impairment after the disorders have taken hold, researchers at MIT have combined digital pen technology and some custom software to develop an objective model for early detection.
The new system, still in its concept stage, is a development on the Clock Drawing Test (CDT) that doctors use to screen for illnesses such as Alzheimer’s and Parkinson’s. In this test patients are asked to draw a clock face showing the time as 10 minutes past 11, and then asked to copy a pre-drawn clock face showing the same time. The results are then examined for signs of problems by a doctor.
Researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) swapped out the ink pen used in current tests for the Anoto Live Pen, a digitizing ballpoint pen that, with the help of a built-in camera, can measure its position on the paper more than 80 times a second. Rather than only relying on the final drawing for subjective analysis by medical practitioners, the pen can pick up on all the patient's hesitations and movements.
Working at Lahey Hospital and Medical Center, the CSAIL researchers helped produce analysis software for the Live Pen version of the test, resulting in what the team calls the digital Clock Drawing Test.
The development team used the results of 2,600 standard CDT tests administered over the last nine years to develop computational models, which when compared to traditional methods used by physicians, proved to have greater accuracy.
"We’ve improved the analysis so that it is automated and objective," says CSAIL principal investigator Cynthia Rudin, co-author of the team's paper. "With the right equipment, you can get results wherever you want, quickly, and with higher accuracy."
Beyond the projected benefits to patients, the new technique could also prove helpful to the medical profession. Currently, Neurologists reportedly spend significant time and resources documenting patient observations by hand and wading through databases. The digital system transfers much of this grunt work to software algorithms.
Having proved the effectiveness of the system, the next phase of the project will see the development of an easy to use interface that will open up the technology to specialists and non-specialists alike.