Beyond surface form: A pipeline for semantic analysis in Alzheimer's Disease detection from spontaneous speech

2025-12-15

AI Summary

Distinguishing semantic impairments in spontaneous speech of Alzheimer’s disease (AD) patients—arising from genuine cognitive decline—from confounding surface-level linguistic patterns remains a key challenge. Method: We propose the first semantics-preserving speech-to-text transformation pipeline, which achieves form–meaning disentanglement via syntactic rewriting and lexical substitution, and jointly evaluates transformation fidelity using BLEU/chrF and semantic similarity metrics. Contribution/Results: On semantically purified texts, AD classification remains robust (minimal macro-F1 fluctuation), demonstrating that deep semantic features alone suffice for early detection. Conversely, injecting noise into semantic representations significantly degrades performance, validating both the efficacy and purity of the semantic pathway. This work overcomes the limitations of prior approaches reliant on superficial linguistic cues and provides the first empirical evidence that large language models can achieve automatic AD identification solely through robust semantic representations.

Technology Category

• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Large language models for search
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Alzheimer's Disease (AD) is a progressive neurodegenerative condition that adversely affects cognitive abilities. Language-related changes can be automatically identified through the analysis of outputs from linguistic assessment tasks, such as picture description. Language models show promise as a basis for screening tools for AD, but their limited interpretability poses a challenge in distinguishing true linguistic markers of cognitive decline from surface-level textual patterns. To address this issue, we examine how surface form variation affects classification performance, with the goal of assessing the ability of language models to represent underlying semantic indicators. We introduce a novel approach where texts surface forms are transformed by altering syntax and vocabulary while preserving semantic content. The transformations significantly modify the structure and lexical content, as indicated by low BLEU and chrF scores, yet retain the underlying semantics, as reflected in high semantic similarity scores, isolating the effect of semantic information, and finding models perform similarly to if they were using the original text, with only small deviations in macro-F1. We also investigate whether language from picture descriptions retains enough detail to reconstruct the original image using generative models. We found that image-based transformations add substantial noise reducing classification accuracy. Our methodology provides a novel way of looking at what features influence model predictions, and allows the removal of possible spurious correlations. We find that just using semantic information, language model based classifiers can still detect AD. This work shows that difficult to detect semantic impairment can be identified, addressing an overlooked feature of linguistic deterioration, and opening new pathways for early detection systems.

Problem

• Analyzing semantic indicators in Alzheimer's speech detection
• Isolating semantic from surface-level linguistic patterns
• Assessing language models for early AD detection

Innovation

• Transforming text surface forms while preserving semantics
• Using semantic similarity to isolate cognitive decline indicators
• Assessing image-based noise impact on classification accuracy