Linguistic-Based Mild Cognitive Impairment Detection Using Informative Loss

TL;DR

This paper introduces a novel NLP-based deep learning framework utilizing Transformer modules and a new loss function, InfoLoss, to accurately classify Mild Cognitive Impairment from normal cognition using video interview transcripts.

Contribution

The study presents a new NLP framework with Transformer modules and a novel loss function, achieving improved accuracy in MCI detection from linguistic data.

Findings

Achieved an average AUC of 84.75% in distinguishing MCI from NC.

Proposed a new loss function, InfoLoss, enhancing classification performance.

Demonstrated effectiveness of Transformer-based modules in analyzing linguistic features for cognitive impairment detection.

Abstract

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%.