This paper proposes a novel dual semi-supervised learning (DSSL) method for classifying Alzheimer's disease (AD), mild cognitive impairment (MCI), and normal controls (NC) using neuropsychological test scores. The method utilizes difference regularization and consistency regularization with pseudo-labeling, achieving high accuracy (85.47% with 60 labels and 88.40% with 120 labels) and stability compared to other semi-supervised methods on the ADNI database. The study first selected the 15 most relevant features from seven neuropsychological tests using feature selection. DSSL is presented as a valuable tool for clinical diagnosis.
Publisher
Brain Sciences
Published On
Feb 10, 2023
Authors
Francesco Di Lorenzo, Annibale Antonioni, Yan Wang, Xuming Gu, Wenju Hou, Meng Zhao, Li Sun, Chunjie Guo
Tags
Alzheimer's Disease
Mild Cognitive Impairment
Semi-Supervised Learning
Neuropsychological Tests
Feature Selection
Clinical Diagnosis
Related Publications
Explore these studies to deepen your understanding of the subject.
