Linguistic-based Mild Cognitive Impairment detection using Informative Loss

• Published in: Computers in biology and medicine Vol. 176; p. 108606
• Main Authors: Pourramezan Fard, Ali, Mahoor, Mohammad H., Alsuhaibani, Muath, Dodge, Hiroko H.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.06.2024; Elsevier Limited
• Subjects: Aged; Classification; Cognitive ability; Cognitive Dysfunction - diagnosis; Deep Learning; Embedding; Female; Humans; I-CONECT dataset; Impairment; Informative Loss function; Internal Medicine; Linguistic features detection; Linguistics; Male; Mild Cognitive Impairment classification; Modules; Multilayer perceptrons; Multilayers; Natural Language Processing; Other; Sentences; Temporal variations; Transformers; I-CONECT dataset; Transformers; Informative Loss function; Mild Cognitive Impairment classification; Linguistic features detection; Natural Language Processing
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.108606

This paper presents a deep learning method using Natural Language Processing (NLP) techniques, to distinguish between Mild Cognitive Impairment (MCI) and Normal Cognitive (NC) conditions in older adults. We propose a framework that analyzes transcripts generated from video interviews collected within the I-CONECT study project, a randomized controlled trial aimed at improving cognitive functions through video chats. Our proposed NLP framework consists of two Transformer-based modules, namely Sentence Embedding (SE) and Sentence Cross Attention (SCA). First, the SE module captures contextual relationships between words within each sentence. Subsequently, the SCA module extracts temporal features from a sequence of sentences. This feature is then used by a Multi-Layer Perceptron (MLP) for the classification of subjects into MCI or NC. To build a robust model, we propose a novel loss function, called InfoLoss, that considers the reduction in entropy by observing each sequence of sentences to ultimately enhance the classification accuracy. The results of our comprehensive model evaluation using the I-CONECT dataset show that our framework can distinguish between MCI and NC with an average area under the curve of 84.75%. •Introducing a novel deep learning method for cognitive impairment detection.•Employs Natural Language Processing to analyze speech patterns.•Distinguishing Mild Cognitive Impairment from Normal Cognitive conditions.•Utilizing Transformer-based modules to capture contextual relationships.•Extracting temporal features from video interview transcripts.•Introducing InfoLoss to improve classification accuracy.