Researchers at the University of California, Los Angeles have created a new kind of diagnostic tool that looks like a pen but does something far more powerful—it can help detect early signs of Parkinson’s disease with 96.22% accuracy.
This innovative pen was tested in a small pilot study and could become a low-cost, easy-to-use tool for identifying the disease early, especially in places with limited access to doctors or medical equipment.
Parkinson’s disease affects the brain’s control over movement. It causes symptoms like tremors, muscle stiffness, and slower movements.
One of the early signs is a change in fine motor skills, like handwriting.
Today, doctors often diagnose Parkinson’s based on how a person moves or walks, or how their handwriting looks.
But these judgments can vary between doctors and depend heavily on experience. Other more advanced tests use biological markers, but they are expensive and need special equipment, making them less accessible in many parts of the world.
To solve these problems, the UCLA team developed a pen that can “listen” to how someone writes. It does this by turning the movements of the hand into electrical signals. These signals can then be analyzed to spot patterns linked with Parkinson’s.
The study, titled “Neural network-assisted personalized handwriting analysis for Parkinson’s disease diagnostics,” was published in Nature Chemical Engineering.
The pen’s tip is made of a soft silicone material filled with tiny magnetic particles. It also uses a special ink called ferrofluid, which contains nanosized magnets. As a person writes, the pressure and motion cause changes in magnetic fields inside the pen. These changes generate electrical signals, which are picked up by a coil inside the pen.
In the pilot study, 16 people used the pen. Three of them had Parkinson’s disease and 13 were healthy. They were asked to perform several writing tasks, such as drawing spirals, straight lines, and writing letters—both on paper and in the air. The electrical signals generated by their writing were then analyzed by computer models.
Among the models tested, a special type of artificial intelligence called a one-dimensional convolutional neural network gave the most accurate results. It correctly identified Parkinson’s patients more than 96% of the time. That level of accuracy is especially impressive considering the small number of participants in the study.
One of the best parts about this new pen is that it doesn’t rely on analyzing how the handwriting looks—which can vary a lot between people. Instead, it measures how the hand moves while writing.
This makes it less dependent on expert judgment and more objective. It could be especially useful in low-resource settings, at home, or even in remote areas where people don’t have easy access to specialists.
The pen also has potential beyond just diagnosing the disease. If tested in larger groups, it could be used to track how a patient’s symptoms change over time, helping doctors adjust treatments and monitor progress more precisely.
The researchers describe their creation as “a low-cost, widely usable, and reliable” device that could change how Parkinson’s is diagnosed and managed.
If future studies confirm its benefits in larger and more diverse populations, this smart pen might soon become a common tool in both hospitals and homes, offering hope for earlier detection and better care for millions living with Parkinson’s disease.
If you care about Parkinson’s disease, please read studies that Vitamin B may slow down cognitive decline, and Mediterranean diet could help lower risk of Parkinson’s.
For more information about brain health, please see recent studies that blueberry supplements may prevent cognitive decline, and results showing Plant-based diets could protect cognitive health from air pollution.
The research findings can be found in Nature Chemical Engineering.
Copyright © 2025 Knowridge Science Report. All rights reserved.
