Related Experiment Video
Updated: Jun 14, 2025
Dynamic Digital Biomarkers of Motor and Cognitive Function in Parkinson's Disease
Published on: July 24, 2019
Digitalizing Handwritten Digits of Patients with Parkinson's Disease Utilizing Consumer Hardware and Open-Source
Christopher Gundler1, Alexander Johannes Wiederhold1, Monika Pötter-Nerger2
1Institute for Applied Medical Informatics, University Medical Center Hamburg-Eppendorf, Hamburg, Germany.
Introduction:
Parkinson's disease represents a burdensome condition with complex manifestations. A licensed, standardized paper-based questionnaire is completed by both patients and physicians to monitor the progression and state of the disease. However, integrating the obtained scores into digital systems still poses a challenge.
Methods:
Paper-based handwriting is intuitive and an efficient mode of human-computer interaction. Accordingly, we transformed a consumer-grade tablet into a device where an exact digital copy of the disease-specific questionnaire can be filled with the supplied pen. Utilizing a small convolutional neural network directly on the device and trained on MNIST data, we translated the handwritten digits to appropriate LOINC codes and made them accessible through a FHIR-compatible HTTP interface.
Results:
When evaluating the usability from a patient-centric point of view, the System Usability Score revealed an excellent rating (SUS = 83.01) from the participants. However, we identified some challenges associated with the magnetic pen and the flat design of the device.
Conclusion:
In setups where certified medical devices are not required, consumer hardware can be used to map handwritten digits of patients to appropriate medical standards without manual intervention through healthcare professionals.
