Linguistic Indicators of Early Cognitive Decline in the DementiaBank Pitt Corpus: A Statistical and Machine Learning Study

TL;DR

This study demonstrates that linguistic features derived from spontaneous speech can reliably indicate early cognitive decline, using interpretable machine learning models validated by statistical tests on the DementiaBank Pitt Corpus.

Contribution

It introduces a comprehensive analysis of linguistic markers with interpretable models, emphasizing the robustness of syntactic and grammatical features for early dementia detection.

Findings

Syntactic and grammatical features remain discriminative without lexical content.

Subject-level evaluation provides consistent results across models.

Significant differences found in word usage, sentence structure, and discourse coherence.

Abstract

Background: Subtle changes in spontaneous language production are among the earliest indicators of cognitive decline. Identifying linguistically interpretable markers of dementia can support transparent and clinically grounded screening approaches. Methods: This study analyzes spontaneous speech transcripts from the DementiaBank Pitt Corpus using three linguistic representations: raw cleaned text, a part-of-speech (POS)-enhanced representation combining lexical and grammatical information, and a POS-only syntactic representation. Logistic regression and random forest models were evaluated under two protocols: transcript-level train-test splits and subject-level five-fold cross-validation to prevent speaker overlap. Model interpretability was examined using global feature importance, and statistical validation was conducted using Mann-Whitney U tests with Cliff's delta effect sizes. Results: Across representations, models achieved stable performance, with syntactic and grammatical features retaining strong discriminative power even in the absence of lexical content. Subject-level evaluation yielded more conservative but consistent results, particularly for POS-enhanced and POS-only representations. Statistical analysis revealed significant group differences in functional word usage, lexical diversity, sentence structure, and discourse coherence, aligning closely with machine learning feature importance findings. Conclusion: The results demonstrate that abstract linguistic features capture robust markers of early cognitive decline under clinically realistic evaluation. By combining interpretable machine learning with non-parametric statistical validation, this study supports the use of linguistically grounded features for transparent and reliable language-based cognitive screening.