Advancing Alzheimer Disease Prediction With Large Language Model–Based Linguistic Feature Analysis: Development and Validation Study

Abstract Background Alzheimer disease (AD) is a progressive neurodegenerative disorder with rapidly growing global prevalence. Early detection is critical for timely intervention; yet, conventional diagnostic methods remain costly and invasive. Speech-based assessment has emerged as a noninvasive alternative, as AD characteristically impairs linguistic abilities including fluency, coherence, and informational content. Recent advances in large language models (LLMs) offer new opportunities to extract structured linguistic features from transcribed speech for automated AD classification. However, existing LLM-based approaches often lack transparency and clinical interpretability, limiting their adoption in clinical workflows. Objective This study aims to investigate the influence of linguistic features extracted from transcribed speech, as analyzed by LLMs, on the accuracy and interpretability of AD prediction. Methods We propose a framework that leverages LLMs to analyze linguistic features extracted from transcribed speech for AD classification. Our approach focuses on 4 key aspects, including readability, fluency, richness of detail, and keyword relevance. To enhance classification accuracy, the framework integrates transcript embeddings with feature explanation embeddings, forming a comprehensive linguistic representation. We conducted extensive ablation studies to evaluate the contributions of individual features and benchmarked our framework against existing LLM-driven methodologies through pairwise explainability evaluations. Output stability was assessed across 3 independent pipeline runs. A fully local configuration (Llama 3 8B + nomic-embed-text) was tested to evaluate privacy-preserving deployment feasibility. Explainability was assessed via LLM-based pairwise comparison (Gemini-3.1-flash-lite) against the method of Bang et al across 54 correctly classified cases and by blinded evaluation from 2 neurologists. Results The proposed framework achieved a mean precision of 91.52%, a sensitivity of 91.08%, a specificity of 96.29%, and F 1 -score of 91.05% across 3 independent runs on the ADReSSo 2021 dataset, outperforming existing LLM-based approaches. A fully-local configuration (Llama 3 8B+nomic-embed-text, requiring no cloud application programming interface access) achieved an F 1 -score of 81.58%, demonstrating framework transferability to privacy-preserving deployment environments. Keyword relevance was the most influential feature ( F 1 -score drop of 13.22 pp when removed). Explainability evaluations showed our method was preferred in 49 out of 54 cases via Gemini-3.1-flash-lite, with human experts preferring our method in 89 of 108 blinded assessments. Conclusions These findings highlight that a structured linguistic feature analysis using LLMs provides a robust and interpretable framework for preliminary AD detection. Our approach offers a scalable and accessible solution that bridges artificial intelligence–driven text analysis with clinical applications, supporting early detection of cognitive decline through noninvasive assessment methods.