Small-sized Reasoning Language Models for Linguistic Screening of Alzheimer's Disease
Addepalli, V. r.; Abdalnabi, N.; Kummerfeld, E.; Hembroff, G.; Kiselica, A. M.; Rao, P.; Lee, K.
Show abstract
Alzheimers disease (AD) is increasing in prevalence, and early detection is essential for timely care. Clinical services face growing demand, leading to delays in diagnostic appointments and increasing the risk of disease progression before evaluation. This work examines artificial intelligence (AI) methods for assessing cognitive status from linguistic features. The proposed architecture uses small language models (SLMs) to analyze speech patterns, and its compact design allows deployment on mobile devices. Recent reasoning-focused models, including Deepseek-R1 and Llama, were evaluated for dementia classification. Multiple fine-tuning strategies were compared, and the best model achieved 91% accuracy and an F1 score. The findings show that AI systems built on SLMs can achieve performance comparable to large language models, indicating their potential as efficient tools that may support health care providers through accessible pre-clinical screening for AD.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
Similar papers in this journal
- Interpretable deep learning approach for extracting cognitive features from hand-drawn images of intersecting pentagons in older adults 93%
- A Framework to Assess Clinical Safety and Hallucination Rates of LLMs for Medical Text Summarisation 93%
- Quantifying Device Type and Handedness Biases in a Remote Parkinson’s Disease AI-Powered Assessment 92%
Similar papers in this journal
Similar papers in this journal
- Enhancing Fairness in Disease Prediction by Optimizing Multiple Domain Adversarial Networks 93%
- Modular Clinical Decision Support Networks (MoDN)—Updatable, Interpretable, and Portable Predictions for Evolving Clinical Environments 92%
- Natural language processing to evaluate texting conversations between patients and healthcare providers during COVID-19 Home-Based Care in Rwanda at scale 92%
Similar papers in this journal
- LCD Benchmark: Long Clinical Document Benchmark on Mortality Prediction for Language Models 95%
- Annotation-preserving machine translation of English corpora to validate Dutch clinical concept extraction tools 92%
- Large Language Models Facilitate the Generation of Electronic Health Record Phenotyping Algorithms 92%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.