Comparing Natural Language Processing Techniques for Alzheimer's Dementia Prediction in Spontaneous Speech

@inproceedings{Searle2020ComparingNL,
  title={Comparing Natural Language Processing Techniques for Alzheimer's Dementia Prediction in Spontaneous Speech},
  author={Thomas Searle and Zina M. Ibrahim and Richard J. B. Dobson},
  booktitle={INTERSPEECH},
  year={2020}
}
Alzheimer's Dementia (AD) is an incurable, debilitating, and progressive neurodegenerative condition that affects cognitive function. Early diagnosis is important as therapeutics can delay progression and give those diagnosed vital time. Developing models that analyse spontaneous speech could eventually provide an efficient diagnostic modality for earlier diagnosis of AD. The Alzheimer's Dementia Recognition through Spontaneous Speech task offers acoustically pre-processed and balanced datasets… Expand

Figures and Tables from this paper

Learning Language and Acoustic Models for Identifying Alzheimer’s Dementia From Speech
TLDR
The promise of using machine learning for detecting cognitive decline from speech in AD patients is demonstrated by methods for learning models using speech samples from the DementiaBank database, for identifying which subjects have Alzheimer’s dementia. Expand
Classifying Alzheimer's Disease Using Audio and Text-Based Representations of Speech
TLDR
The feasibility of using speech to classify AD and predict neuropsychological scores is illustrated and the top-performing classification models were the support vector machine and random forest classifiers trained on BERT embeddings, which both achieved an accuracy of 85.4% on the test set. Expand
Recognition of Alzheimer’s Dementia From the Transcriptions of Spontaneous Speech Using fastText and CNN Models
TLDR
This work explores the transcriptions of spontaneous speech for dementia recognition and suggests that the n-gram-based features are worth pursuing, for the task of AD detection. Expand
Crossing the “Cookie Theft” Corpus Chasm: Applying What BERT Learns From Outside Data to the ADReSS Challenge Dementia Detection Task
TLDR
It is found that incorporating WLS data during training a BERT model on ADRe SS data improves its performance on the ADReSS dementia detection task, supporting the hypothesis that incorporatingWLS data adds value in this context. Expand
Uncertainty-Aware Boosted Ensembling in Multi-Modal Settings
TLDR
This work proposes an uncertainty-aware boosting technique for multi-modal ensembling in order to focus on the data points with higher associated uncertainty estimates, rather than the ones with higher loss values, and suggests that introducing uncertainty-awareness into the boosted ensembles decreases the overall entropy of the system. Expand
Alzheimers Dementia Detection using Acoustic & Linguistic features and Pre-Trained BERT
TLDR
This study focuses on three models for the classification task in the ADReSS (The Alzheimer's Dementia Recognition through Spontaneous Speech) 2021 Challenge and uses various acoustic features from the eGeMAPs feature-set to extract features using a Pre-trained BERT and TF-IDF. Expand
Robustness and Sensitivity of BERT Models Predicting Alzheimer's Disease from Text
TLDR
This paper analyzes how a controlled amount of desired and undesired text alterations impacts performance of BERT and shows that BERT is robust to natural linguistic variations in text and not sensitive to removing clinically important information from text. Expand
Temporal Integration of Text Transcripts and Acoustic Features for Alzheimer's Diagnosis Based on Spontaneous Speech
TLDR
The proposed combination of ADR audio and textual features is capable of successfully modelling temporal aspects of the data and achieves best performance when ADR features are combined with strong semantic bag-of-n-grams features. Expand
Uncertainty-Aware Multi-Modal Ensembling for Severity Prediction of Alzheimer's Dementia
TLDR
This work proposes an uncertainty-aware boosting technique for multi-modal ensembling to predict Alzheimer's Dementia Severity and aims to encourage fair and aware models. Expand

References

SHOWING 1-10 OF 30 REFERENCES
Alzheimer's Dementia Recognition through Spontaneous Speech: The ADReSS Challenge
TLDR
The ADReSS Challenge at INTERSPEECH 2020 defines a shared task through which different approaches to the automated recognition of Alzheimer's dementia based on spontaneous speech can be compared, including feature extraction procedures and results for classification and regression models. Expand
Detecting Alzheimer's Disease from Continuous Speech Using Language Models.
TLDR
The perplexity features extracted by LMs can benefit the automatic AD detection from continuous speech and show that AD patients tend to use more general, less informative, and less accurate words to describe characters and actions than healthy controls. Expand
Using linguistic features longitudinally to predict clinical scores for Alzheimer’s disease and related dementias
TLDR
A bivariate dynamic Bayes net is used to represent the longitudinal progression of observed linguistic features and MMSE scores over time, and a mean absolute error of 3.83 is obtained in predicting MMSE, comparable to within-subject interrater standard deviation. Expand
Speech Recognition in Alzheimer's Disease and in its Assessment
TLDR
This work optimize automatic speech recognition for participants with Alzheimer’s disease (AD) in a relatively large clinical database and extracts text features from the resulting transcripts and uses these features to identify AD with an SVM classifier. Expand
Prediction of cognitive impairment via deep learning trained with multi-center neuropsychological test data
  • Min Ju Kang, Sang Yun Kim, +21 authors Y. Youn
  • Computer Science, Medicine
  • BMC Medical Informatics and Decision Making
  • 2019
TLDR
The machine learning algorithm for NPTs has suggested potential use as a reference in differentiating cognitive impairment in the clinical setting and the ‘time orientation’ and ‘3-word recall’ score of MMSE were highly ranked features in predicting CI and cognitive state. Expand
Predicting Clinical Scores from Magnetic Resonance Scans in Alzheimer's Disease
Machine learning and pattern recognition methods have been used to diagnose Alzheimer's disease (AD) and Mild Cognitive Impairment (MCI) from individual MRI scans. Another application of such methodsExpand
Alzheimer’s Disease – Why We Need Early Diagnosis
TLDR
How Alzheimer’s disease diagnosis rates can be improved, the implications of an early diagnosis for the individual, carer and society, and the importance of risk reduction to prevent or delay progression are examined. Expand
Attention is All you Need
TLDR
A new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely is proposed, which generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data. Expand
Epidemiology of Alzheimer disease
TLDR
An overview of the criteria used in the diagnosis of Alzheimer disease is provided, highlighting how this disease is related to, but distinct from, normal aging. Expand
Transfer Learning in Natural Language Processing
TLDR
An overview of modern transfer learning methods in NLP, how models are pre-trained, what information the representations they learn capture, and review examples and case studies on how these models can be integrated and adapted in downstream NLP tasks are presented. Expand
...
1
2
3
...