EUVIMEDEUVIMED entdecken
Open Access

Diagnosing Parkinson’s disease via behavioral biometrics of keystroke dynamics

Trinny Tat iD, Guorui Chen iD, Jing Xu iD, Xun Zhao iD, Yunsheng Fang iD, Jun Chen iD

Science Advances · 04.04.2025 · 11 (14)

DOI: 10.1126/sciadv.adt6631 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science Advances, erschienen am 04.04.2025. Verfasst von Trinny Tat und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA 90095, USA. Hauptthemen laut MEDLINE: Parkinson Disease, Biometry. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: American Heart Association-American Stroke Association, NIBIB NIH HHS, NCI NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Parkinson’s disease (PD) is one of the rapidly growing neurodegenerative diseases, affecting more than 10 million people worldwide. Early and accurate diagnosis of PD is highly desirable for therapeutic interventions but remains a substantial challenge. We developed a soft, portable intelligent keyboard leveraging magnetoelasticity to detect subtle pressure variations in keystroke dynamics by converting continuous keystrokes into high-fidelity electrical signals, thus enabling the quantitative analysis of PD motor symptoms using machine learning. Relying on a fundamental working mechanism, the intelligent keyboard demonstrates highly sensitive, intrinsically waterproof, and biocompatible properties, with the successful demonstration in a pilot study on patients with PD. To facilitate the potential continuous monitoring of PD, a customized cellphone application was developed to integrate the intelligent keyboard into a wireless platform. Together, the intelligent keyboard system’s compelling properties position it as a promising tool for advancing early diagnosis and facilitating personalized, predictive, preventative, and participatory approaches to PD healthcare.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Parkinson DiseaseBiometryHumansMaleMachine LearningFemalePilot Projects

Autor:innen und Institutionen

  • Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA 90095, USA.

ORCID-Profile: Trinny Tat, Guorui Chen, Jing Xu, Xun Zhao, Yunsheng Fang, Jun Chen

Förderung

  • American Heart Association-American Stroke Association
  • NIBIB NIH HHS
  • NCI NIH HHS

Zitieren

APA

Tat, T., Chen, G., Xu, J., Zhao, X., Fang, Y., & Chen, J. (2025). Diagnosing Parkinson’s disease via behavioral biometrics of keystroke dynamics. Science Advances, 11(14). https://doi.org/10.1126/sciadv.adt6631

Vancouver

Tat T, Chen G, Xu J, Zhao X, Fang Y, Chen J. Diagnosing Parkinson’s disease via behavioral biometrics of keystroke dynamics. Science Advances. 2025;11(14). doi:10.1126/sciadv.adt6631

BibTeX
@article{Tat2025,
  author = {Tat, Trinny and Chen, Guorui and Xu, Jing and Zhao, Xun and Fang, Yunsheng and Chen, Jun},
  title = {Diagnosing Parkinson’s disease via behavioral biometrics of keystroke dynamics},
  journal = {Science Advances},
  year = {2025},
  volume = {11},
  number = {14},
  doi = {10.1126/sciadv.adt6631}
}
Kostenlos starten →