Papers
Topics
Authors
Recent
Search
2000 character limit reached

Naturalistic Language-related Movie-Watching fMRI Task for Detecting Neurocognitive Decline and Disorder

Published 10 Jun 2025 in cs.CL | (2506.08986v1)

Abstract: Early detection is crucial for timely intervention aimed at preventing and slowing the progression of neurocognitive disorder (NCD), a common and significant health problem among the aging population. Recent evidence has suggested that language-related functional magnetic resonance imaging (fMRI) may be a promising approach for detecting cognitive decline and early NCD. In this paper, we proposed a novel, naturalistic language-related fMRI task for this purpose. We examined the effectiveness of this task among 97 non-demented Chinese older adults from Hong Kong. The results showed that machine-learning classification models based on fMRI features extracted from the task and demographics (age, gender, and education year) achieved an average area under the curve of 0.86 when classifying participants' cognitive status (labeled as NORMAL vs DECLINE based on their scores on a standard neurcognitive test). Feature localization revealed that the fMRI features most frequently selected by the data-driven approach came primarily from brain regions associated with language processing, such as the superior temporal gyrus, middle temporal gyrus, and right cerebellum. The study demonstrated the potential of the naturalistic language-related fMRI task for early detection of aging-related cognitive decline and NCD.

Summary

  • The paper introduces a movie-watching fMRI task that simulates real-life language processing for early detection of neurocognitive decline.
  • It utilizes fMRI T-map analysis and machine learning to achieve an AUC of 0.86, highlighting key language-processing regions such as the STG and MTG.
  • The study offers enhanced ecological validity and potential clinical applications by objectively measuring cognitive function during naturalistic language tasks.

The study conducted by Wang et al. introduces a novel approach for the detection of neurocognitive decline (NCD) using a naturalistic language-related fMRI task centered around movie-watching. The study addresses the pressing need for early detection methods in light of the increasing prevalence of neurocognitive disorders, particularly among older adults. Utilizing functional magnetic resonance imaging (fMRI), combined with a language task performed in a naturalistic environment, the research seeks to overcome limitations of traditional language tasks, which lack ecological validity and may not fully capture the complexity of everyday language processing.

Methodology Overview

Participants comprised 97 non-demented older Chinese adults from Hong Kong. The proposed task involved watching a movie with Cantonese dialogues while undergoing fMRI scanning, thus engaging participants in a language task that mimics daily activities. This approach offers multiple advantages: high ecological validity, inclusion of multiple language processing levels, ease of compliance in the fMRI environment, and objective measurement via neuroimaging.

Specifically, fMRI data were acquired during the task, and statistical T-maps were generated for each subject, reflecting differential brain activation in response to speech events versus silence. The Montreal Cognitive Assessment (MoCA) scores served to categorize subjects' cognitive statuses as NORMAL or DECLINE. Subsequently, machine learning models were deployed to evaluate the predictive power of fMRI features combined with demographic data on cognitive status.

Findings and Significance

The classification models achieved impressive performance, with an average area under the curve (AUC) of 0.86, demonstrating the effectiveness of integrating fMRI-derived features with demographic data. Notably, feature localization highlighted that brain regions associated with language processing, such as the superior temporal gyrus (STG), middle temporal gyrus (MTG), and right cerebellum, were instrumental in the classification tasks. These regions are intrinsically linked to the processing of linguistic information, reinforcing the hypothesis that language-related brain activities can be indicative of early neurocognitive decline.

By providing a more ecologically valid and non-invasive tool for early detection, the study offers significant implications for clinical practices. The potential to identify cognitive decline before significant symptoms manifest could pave the way for timely interventions to slow the progression of NCD.

Future Directions

Although promising, the study emphasizes the need for future research to dissect language processing further to identify which subcomponents may offer enhanced diagnostic utility. Exploring broader cognitive processes beyond language perception, such as language production and complex semantic processing, could refine and extend the applicability of the proposed methodology. Additionally, expanding the scope to include clinical NCD diagnoses would provide a more comprehensive validation of the movie-watching fMRI task as a diagnostic tool.

In conclusion, the research presents a robust framework for early NCD detection, leveraging naturalistic language task environments in neuroimaging practices. This innovative fusion offers promising avenues for advancing diagnostic capabilities and enhancing the quality of life among aging populations.

Paper to Video (Beta)

No one has generated a video about this paper yet.

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Continue Learning

We haven't generated follow-up questions for this paper yet.