Abstract

Alzheimer’s disease (AD) is an irreversible and progressive brain disease that can be stopped or slowed down with medical treatment. Language changes serve as a sign that a patient’s cognitive functions have been impacted, potentially leading to early diagnosis. In this work, we use NLP techniques to classify and analyze the linguistic characteristics of AD patients using the DementiaBank dataset. We apply three neural models based on CNNs, LSTM-RNNs, and their combination, to distinguish between language samples from AD and control patients. We achieve a new independent benchmark accuracy for the AD classification task. More importantly, we next interpret what these neural models have learned about the linguistic characteristics of AD patients, via analysis based on activation clustering and first-derivative saliency techniques. We then perform novel automatic pattern discovery inside activation clusters, and consolidate AD patients’ distinctive grammar patterns. Additionally, we show that first derivative saliency can not only rediscover previous language patterns of AD patients, but also shed light on the limitations of neural models. Lastly, we also include analysis of gender-separated AD data.

Highlights

  • Alzheimer’s dementia is the most common form of dementia, caused by Alzheimer’s disease (AD)

  • One of the early symptoms of AD, cognitive impairment—which can be evidenced by issues with word-finding, impaired reasoning or judgment, and changes in language (McKhann et al, 1984)—is motivating linguists and computer scientists to help quickly diagnose people afflicted by this disease

  • Our CNN, LSTM and CNNLSTM models achieved an accuracy of 82.8%, 83.7% and 84.9%, respectively

Read more

Summary

Introduction

Alzheimer’s dementia is the most common form of dementia, caused by Alzheimer’s disease (AD). One of the early symptoms of AD, cognitive impairment—which can be evidenced by issues with word-finding, impaired reasoning or judgment, and changes in language (McKhann et al, 1984)—is motivating linguists and computer scientists to help quickly diagnose people afflicted by this disease. This task is challenging because it requires diverse linguistic and world knowledge. The characteristics of AD-affected speech vary between stages of disease progression (Konig et al, 2015), making it harder for feature-based approaches to adapt

Objectives
Methods
Results
Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call