# Unifying Acoustic Features and Text with Multimodal LLMs for Neurodegenerative Screening

Source: [Unifying Acoustic Features and Text with Multimodal LLMs for Neurodegenerative Screening](<https://www.sota2.com/research/paper/6a30d88ed33dfb23e783cbd9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-06-17T05:00:05.807Z

Authors: Qingfeng Zhang, Yuanxiong Guo, Yanmin Gong

Published: 2026-06-10T21:43:44.000Z

## Abstract

Voice-based screening offers a scalable and non-invasive way to assess neurodegenerative diseases such as Alzheimer's disease (AD) and Parkinson's disease (PD), but their staging remains challenging due to the difficulty of integrating heterogeneous data. This paper presents NeurMLLM, an efficient multimodal generative framework for neurodegenerative disease staging. NeurMLLM first encodes the spectrograms and Mel-frequency cepstral coefficients of audio data with vision transformers and projects their representations into the embedding space of a large language model (LLM), where they are concatenated with transcript and demographic instruction tokens as a single unified sequence. The LLM is then instruction-tuned via Low-Rank Adaptation using task prompts to autoregressively predict a constrained label token, enabling a generative classification. By evaluating on the Bridge2AI-Voice dataset for fine-grained staging of AD and PD, we observe that NeurMLLM achieves strong performance, consistently outperforming classical machine learning methods and existing LLM-based approaches. The results show the high potential of multimodal LLMs in neurodegenerative disease staging, improving staging accuracy and supporting accessible deployment.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Alzheimer's Disease Staging on Bridge2AI-Voice AD](<https://www.sota2.com/research/sota/alzheimer-s-disease-staging-on-bridge2ai-voice-ad.md>): Alzheimer's Disease (AD) staging; Bridge2AI-Voice AD; Macro AUROC: 91.7.

- [Parkinson's Disease (PD) staging on Bridge2AI-Voice PD](<https://www.sota2.com/research/sota/parkinson-s-disease-pd-staging-on-bridge2ai-voice-pd.md>): Parkinson's Disease (PD) staging; Bridge2AI-Voice PD; Macro AUROC: 0.872.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2606.14788>)

[PDF](<https://arxiv.org/pdf/2606.14788.pdf>)