RT Conference Proceedings
T1 Ink of Insight: Data Augmentation for Dementia Screening through Handwriting Analysis
A1 Hosseini-Kivanani, Nina
A1 García Martín, Elena Salobrar
A1 Elvira Hurtado, Lorena
A1 López Cuenca, Inés
A1 Hoz Montañana, María Rosa De
A1 Ramírez Sebastián, José Manuel
A1 Gil Gregorio, Pedro
A1 Salas Carrillo, Mario
A1 Schommer, Christoph
A1 Leiva, Luis A.
A2 Association for Computing Machinery, 
AB We investigate the use of handwriting data as a means of predicting early symptoms of Alzheimer's disease (AD). Thirty-six subjects were classified based on the standardized pentagon drawing test (PDT) using deep learning (DL) models. We also compare and contrast classic machine learning (ML) models with DL by employing different data augmentation (DA) techniques. Our findings indicate that DA greatly improves the performance of all models, but the DL-based ones are the ones that achieve the best and highest results. The best model (EfficientNet) achieved a classification accuracy of 87% and an area under the receiver operating characteristic curve (AUC) of 91% for binary classification (healthy or AD patients), whereas for multiclass classification (healthy, mild AD, or moderate AD) accuracy was 76% and AUC was 77%. These results underscore the potential of DA as a simple, cost-effective approach to aid practitioners in screening AD in larger populations, suggesting DL models are capable of analyzing handwriting data with a high degree of accuracy, which may lead to better and earlier detection of AD.tempate
SN 979-8-4007-1687-4/24/05
YR 2024
FD 2024-05-17
LK https://hdl.handle.net/20.500.14352/117870
UL https://hdl.handle.net/20.500.14352/117870
LA eng
NO Nina Hosseini-Kivanani, Elena Salobrar-Garcia, Lorena Elvira-Hurtado, Ines Lopez-Cuenca, Rosa de Hoz, Jose M. Ramirez, Pedro Gil, Mario Salas-Carrillo, Christoph Schommer, and Luis A. Leiva. 2024. Ink of Insight: Data Augmentation for Dementia Screening through Handwriting Analysis. In 2024 8th International Conference on Medical and Health Informatics (ICMHI 2024), May 17--19, 2024, Yokohama, Japan. ACM, New York, NY, USA 6 Pages. https://doi.org/10.1145/3673971.3673992
NO Se incluye en: Proceedings of the 2024 8th International Conference on Medical and Health Informatics, publicados el 9 de septiembre de 2024
DS Docta Complutense
RD 4 abr 2025