Pen would detect Parkinson's

MADRID (EFE).— A pen with magnetic ink and whose data is analyzed by artificial intelligence (AI) can be used to detect Parkinson's disease in its early stages, according to a study published in “Nature Chemical Engineering.” The device, tested on a group of 16 individuals, accurately recorded handwriting signals, which were analyzed by a neural network—an artificial intelligence method that uses a network of interconnected nodes to learn and distinguish between complex patterns.

The pen successfully distinguished Parkinson's patients with an average accuracy of 96.22%, according to a study led by the University of California in the United States.

The operating mechanism is based on the magnetoelastic effect of its magnetoelastic tip and the dynamic movement of the ferrofluid ink, the aforementioned article indicates.

Parkinson's disease is estimated to affect nearly 10 million people worldwide, and rapid, accessible, and effective diagnosis is crucial to improving patient outcomes, but achieving this goal remains a challenge for modern medicine.

Because the symptoms of the disease include tremors, diagnosis is often based on observation of the patient's motor skills, but this method lacks objective standards and often relies on clinician bias.

Pen data analysis can identify differences in the handwriting of people with and without the disease and could potentially allow for earlier diagnoses.

Hand movements during writing can be classified into two types: air movements, in which the pen moves between strokes without contact with the surface, and surface movements, in which it comes into contact with the writing surface and experiences pressure, forming primary strokes.

The device, which enables “efficient and scalable production through 3D printing,” could represent a low-cost, accurate, and widely distributable technology with the potential to improve disease diagnosis in large populations and in resource-limited areas, the study indicates.

The authors note that the tool should be expanded to larger patient samples and that its potential to track the progression of Parkinson's disease stages could be explored.