Devising a Set of Compact and Explainable Spoken Language Feature for Screening Alzheimer's Disease
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915039496110080 |
|---|---|
| author | Li, Junan Li, Yunxiang Wang, Yuren Wu, Xixin Meng, Helen |
| author_facet | Li, Junan Li, Yunxiang Wang, Yuren Wu, Xixin Meng, Helen |
| contents | Alzheimer's disease (AD) has become one of the most significant health challenges in an aging society. The use of spoken language-based AD detection methods has gained prevalence due to their scalability due to their scalability. Based on the Cookie Theft picture description task, we devised an explainable and effective feature set that leverages the visual capabilities of a large language model (LLM) and the Term Frequency-Inverse Document Frequency (TF-IDF) model. Our experimental results show that the newly proposed features consistently outperform traditional linguistic features across two different classifiers with high dimension efficiency. Our new features can be well explained and interpreted step by step which enhance the interpretability of automatic AD screening. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_18922 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Devising a Set of Compact and Explainable Spoken Language Feature for Screening Alzheimer's Disease Li, Junan Li, Yunxiang Wang, Yuren Wu, Xixin Meng, Helen Computation and Language Artificial Intelligence Alzheimer's disease (AD) has become one of the most significant health challenges in an aging society. The use of spoken language-based AD detection methods has gained prevalence due to their scalability due to their scalability. Based on the Cookie Theft picture description task, we devised an explainable and effective feature set that leverages the visual capabilities of a large language model (LLM) and the Term Frequency-Inverse Document Frequency (TF-IDF) model. Our experimental results show that the newly proposed features consistently outperform traditional linguistic features across two different classifiers with high dimension efficiency. Our new features can be well explained and interpreted step by step which enhance the interpretability of automatic AD screening. |
| title | Devising a Set of Compact and Explainable Spoken Language Feature for Screening Alzheimer's Disease |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2411.18922 |