Detecting Neurocognitive Disorders through Analyses of Topic Evolution and Cross-modal Consistency in Visual-Stimulated Narratives

2025-01-07

AI Summary

Early screening for neurocognitive disorders (NCDs) in older adults remains challenging, as conventional approaches rely predominantly on static, micro-linguistic features (e.g., lexical or syntactic markers), lacking sensitivity to higher-order cognitive decline. Method: This work proposes a novel paradigm centered on *dynamic macro-narrative structure*, integrating Dynamic Topic Modeling (DTM) with a Text–Image Temporal Alignment Network (TITAN) to jointly model thematic evolution in spoken narratives and temporal alignment between linguistic output and multimodal (textual + visual) stimuli. Contribution/Results: The framework extracts two interpretable biolinguistic biomarkers: *thematic drift abnormality* and *stimulus-response desynchronization*. Evaluated on the CU-MARVEL Rabbit Story corpus, TITAN achieves F1 = 0.72 and AUC = 0.81—significantly outperforming both micro- and macro-level baselines. DTM independently validates dynamic topic consistency as an effective macro-level indicator (F1 = 0.61, AUC = 0.78).

Technology Category

• Natural Language Processing: Language Grounding & Multi-modal NLP
• Machine Learning: Multimodal Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Web Mining and Content Analysis: Topic discovery and tracking
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Early detection of neurocognitive disorders (NCDs) is crucial for timely intervention and disease management. Speech analysis offers a non-intrusive and scalable screening method, particularly through narrative tasks in neuropsychological assessment tools. Traditional narrative analysis often focuses on local indicators in microstructure, such as word usage and syntax. While these features provide insights into language production abilities, they often fail to capture global narrative patterns, or microstructures. Macrostructures include coherence, thematic organization, and logical progressions, reflecting essential cognitive skills potentially critical for recognizing NCDs. Addressing this gap, we propose to investigate specific cognitive and linguistic challenges by analyzing topical shifts, temporal dynamics, and the coherence of narratives over time, aiming to reveal cognitive deficits by identifying narrative impairments, and exploring their impact on communication and cognition. The investigation is based on the CU-MARVEL Rabbit Story corpus, which comprises recordings of a story-telling task from 758 older adults. We developed two approaches: the Dynamic Topic Models (DTM)-based temporal analysis to examine the evolution of topics over time, and the Text-Image Temporal Alignment Network (TITAN) to evaluate the coherence between spoken narratives and visual stimuli. DTM-based approach validated the effectiveness of dynamic topic consistency as a macrostructural metric (F1=0.61, AUC=0.78). The TITAN approach achieved the highest performance (F1=0.72, AUC=0.81), surpassing established microstructural and macrostructural feature sets. Cross-comparison and regression tasks further demonstrated the effectiveness of proposed dynamic macrostructural modeling approaches for NCD detection.

Problem

• Neurocognitive Disorders
• Elderly Population
• Detection and Identification

Innovation

• Neurocognitive Disorders Detection
• Narrative Analysis
• Consistency of Sensory Modalities