An automatic Alzheimer’s disease classifier based on reading task for Spanish language

• Published in: The European physical journal. ST, Special topics Vol. 234; no. 1; pp. 85 - 99
• Main Authors: Orozco-Chavez, Isabel, Martínez-Estrada, Moisés, Itzá-Ortiz, Benjamín A.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.03.2025; Springer Nature B.V
• Subjects: Accuracy; Advancing Biocomplexity in Multidisciplinary Research; Algorithms; Alzheimer's disease; Artificial intelligence; Artificial neural networks; Atomic; Audio data; Biomarkers; Classical and Continuum Physics; Cognitive ability; Condensed Matter Physics; Data augmentation; Datasets; Deep learning; Dementia; English language; Health care; Language disorders; Linguistics; Machine learning; Materials Science; Measurement Science and Instrumentation; Metadata; Molecular; Optical and Plasma Physics; Physics; Physics and Astronomy; Populations; Python; Reading comprehension; Regular Article; Spanish language; Speaking; Speech; Voice recognition; Womens health; United States > US
• ISSN: 1951-6355; 1951-6401
• DOI: 10.1140/epjs/s11734-024-01428-4

This research develops and evaluates a deep learning model designed to identify Alzheimer’s disease (AD) and mild cognitive impairment (MCI) through Spanish language audio recordings. Addressing the scarcity of data on Spanish-speaking populations in Alzheimer’s research, our study presents a tailored strategy to bridge this gap. A convolutional neural network (CNN) was trained with a dataset comprising reading task audio from 361 participants, encompassing healthy individuals, MCI, and AD patients. The model’s accuracy was enhanced through data augmentation techniques and refined with an attention layer during fine-tuning. Our method achieved a classification accuracy of 73.03% in distinguishing between the three groups. Offering a cost-effective, non-invasive, and readily deployable solution for the early detection of Alzheimer’s and MCI, this approach shows promising results and potential for integration into clinical settings, especially in regions where such populations are largely underrepresented.