Related Experiment Video
Updated: Apr 24, 2026

Handwriting Analysis Indicates Spontaneous Dyskinesias in Neuroleptic Naïve Adolescents at High Risk for Psychosis
Published on: November 21, 2013
Neural network-assisted personalized handwriting analysis for Parkinson's disease diagnostics
Guorui Chen1, Trinny Tat1, Yihao Zhou1
1Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA, USA.
A new diagnostic pen uses magnetoelasticity and ferrofluid ink to detect Parkinson's disease (PD) through handwriting analysis. This low-cost, reliable technology achieved 96.22% accuracy in a pilot study, improving PD diagnostics.
Area of Science:
- Biomedical Engineering
- Neurology
- Materials Science
Background:
- Accurate and accessible diagnosis of Parkinson's disease (PD) is critical for timely intervention and improved patient outcomes.
- Current diagnostic methods can be invasive, costly, or inaccessible in certain regions, highlighting the need for innovative solutions.
- Handwriting impairments are a common early symptom of PD, offering a potential avenue for non-invasive diagnosis.
Purpose of the Study:
- To develop a novel, self-powered diagnostic pen for the sensitive and quantitative detection of Parkinson's disease.
- To investigate the efficacy of a magnetoelastic pen combined with ferrofluid ink for analyzing handwriting signals.
- To assess the clinical potential of this technology in distinguishing individuals with PD from healthy controls.
Main Methods:
- Development of a diagnostic pen with a magnetoelastic tip and ferrofluid ink to convert writing motions into analyzable signals.
- Utilizing the magnetoelastic effect and ferrofluid dynamics for signal generation.
- Conducting a pilot human study involving patients with PD and healthy participants.
- Employing a one-dimensional convolutional neural network for signal analysis and classification.
Main Results:
- The diagnostic pen successfully captured high-fidelity handwriting signals from participants.
- The developed system demonstrated the ability to quantitatively analyze writing motions.
- A one-dimensional convolutional neural network-assisted analysis distinguished patients with PD with an average accuracy of 96.22%.
Conclusions:
- The diagnostic pen is a low-cost, reliable, and widely disseminable technology for Parkinson's disease diagnostics.
- This innovative approach has the potential to significantly improve PD diagnosis, particularly in resource-limited settings.
- The technology offers a promising non-invasive method for early detection and monitoring of Parkinson's disease.
Related Concept Videos
Neural Regulation
Parkinson Disease l: Introduction
Parkinson's Disease: Overview
Parkinson Disease ll: Pathophysiology
Parkinson's Disease: Treatment
Parkinson's Disease is primarily a result of the loss of dopaminergic neurons in the substantia nigra pars compacta. The cornerstone of...

