EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Writing the Signs: An Explainable Machine Learning Approach for Alzheimer's Disease Classification from Handwriting

Ngoc Truc Ngan Ho, Paulina Gonzalez, Gideon K Gogovi iD

Healthcare Technology Letters · 2025-01 · 12 (1)

DOI: 10.1049/htl2.70006 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Healthcare Technology Letters, online erschienen am 13.02.2025. Verfasst von Ngoc Truc Ngan Ho und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science Lehigh University Bethlehem Pennsylvania USA. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Alzheimer's disease is a global health challenge, emphasizing the need for early detection to enable timely intervention and improve outcomes. This study analyzes handwriting data from individuals with and without Alzheimer's to identify predictive features across copying, graphic and memory‐based tasks. Machine learning models, including Random Forest, Bootstrap Aggregating (Bagging), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost) and Gradient Boosting, were applied to classify patients, with SHapley Additive exPlanations (SHAP) enhancing model interpretability. Time‐related features were crucial in copying and graphic tasks, reflecting cognitive processing speed, while pressure‐related features were significant in memory tasks, indicating recall confidence. Simpler graphic tasks showed strong discriminatory power, aiding early detection. Performance metrics demonstrated model effectiveness: For memory tasks, Random Forest achieved the highest accuracy (), while Bagged SVC was the lowest (). Copying tasks recorded a peak accuracy of with Gradient Boost and a low of for Bagged SVC. Graphic tasks reached with Gradient Boost and 0.643 ± 0.071 with AdaBoost. For all tasks combined, Random Forest excelled (), while Gradient Boost performed worst (). These results highlight handwriting analysis's potential in Alzheimer's detection.

Schlagwörter

Stichwörter der Autor:innen

Alzheimer's diseaseSHAPensemble learningexplainabilityhandwriting

Autor:innen und Institutionen

  • Department of Computer Science Lehigh University Bethlehem Pennsylvania USA.
  • Department of Population Health Lehigh University Bethlehem Pennsylvania USA.
  • Department of Biostatistics and Health Data Science Lehigh University Bethlehem Pennsylvania USA.

ORCID-Profile: Gideon K Gogovi

Zitieren

APA

Ho, N. T. N., Gonzalez, P., & Gogovi, G. K. (2025). Writing the Signs: An Explainable Machine Learning Approach for Alzheimer's Disease Classification from Handwriting. Healthcare Technology Letters, 12(1). https://doi.org/10.1049/htl2.70006

Vancouver

Ho NTN, Gonzalez P, Gogovi GK. Writing the Signs: An Explainable Machine Learning Approach for Alzheimer's Disease Classification from Handwriting. Healthcare Technology Letters. 2025;12(1). doi:10.1049/htl2.70006

BibTeX
@article{Ho2025,
  author = {Ho, Ngoc Truc Ngan and Gonzalez, Paulina and Gogovi, Gideon K},
  title = {Writing the Signs: An Explainable Machine Learning Approach for Alzheimer's Disease Classification from Handwriting},
  journal = {Healthcare Technology Letters},
  year = {2025},
  volume = {12},
  number = {1},
  doi = {10.1049/htl2.70006}
}
Kostenlos starten →