A Hybrid Meta-Classifier Framework for Alzheimer’s Disease Classification Using Handwriting Analysis

Alzheimer’s disease (AD) is a progressive neurodegenerative disorder for which accurate and accessible screening approaches remain an important research objective. This study proposes a hybrid meta-classifier framework for handwriting-based AD classification using the DARWIN (Diagnosis AlzheimeR WIth haNdwriting) dataset, which comprises 174 participants, including 89 individuals with AD and 85 healthy controls, and contains 450 handwriting-related features derived from 25 tasks. The proposed framework combines a one-dimensional convolutional neural network (1D-CNN) for automated feature learning with a heterogeneous ensemble of XGBoost, support vector machine (SVM), and random forest classifiers. The predictions of the base classifiers are subsequently integrated by an AdaBoost-based meta-classifier to generate the final classification decision. The framework achieved a pooled cross-validation accuracy of 98.28%, with a mean fold-level accuracy of 97.73 ± 1.27%, a precision of 96.90 ± 2.84%, a recall of 98.89 ± 2.49%, an F1-score of 97.84 ± 1.21%, and an AUC of 0.944 ± 0.023 across the five outer folds. In addition, evaluation on an independent handwriting-signature cohort achieved an accuracy of 91.76%, with a sensitivity of 90.74% and a specificity of 93.55%. These results indicate that the proposed framework has strong discriminative capability across the evaluated datasets. Nevertheless, further validation on larger and more diverse independent cohorts is required before conclusions regarding clinical applicability can be drawn. Future work will investigate multimodal integration and the application of explainable artificial intelligence techniques to improve the interpretability of the proposed framework.