Enriching Neural Models with Targeted Features for Dementia Detection

Palo, Flavio Di; Parde, Natalie

doi:10.48550/arxiv.1906.05483

Cited by 2 publications

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many current AD detection studies use medical imaging [18,19,20] with deep neural networks and random forests. Several studies claim that AD can be sensitively detected in early stages by doing linguistic analysis which leverages speech and language features to train machine learning models for the detection of AD [13,14,15,16,17,21].…”

Section: Related Workmentioning

confidence: 99%

Multimodal Inductive Transfer Learning for Detection of Alzheimer’s Dementia and its Severity

Sarawgi

Zulfikar

Soliman³

et al. 2020

Interspeech 2020

View full text Add to dashboard Cite

Alzheimer's disease is estimated to affect around 50 million people worldwide and is rising rapidly, with a global economic burden of nearly a trillion dollars. This calls for scalable, cost-effective, and robust methods for detection of Alzheimer's dementia (AD). We present a novel architecture that leverages acoustic, cognitive, and linguistic features to form a multimodal ensemble system. It uses specialized artificial neural networks with temporal characteristics to detect AD and its severity, which is reflected through Mini-Mental State Exam (MMSE) scores. We first evaluate it on the ADReSS challenge dataset, which is a subject-independent and balanced dataset matched for age and gender to mitigate biases, and is available through DementiaBank. Our system achieves state-of-the-art test accuracy, precision, recall, and F1-score of 83.3% each for AD classification, and state-of-the-art test root mean squared error (RMSE) of 4.60 for MMSE score regression. To the best of our knowledge, the system further achieves state-of-the-art AD classification accuracy of 88.0% when evaluated on the full benchmark DementiaBank Pitt database. Our work highlights the applicability and transferability of spontaneous speech to produce a robust inductive transfer learning model, and demonstrates generalizability through a task-agnostic feature-space. The source code is available at https://github.com/ wazeerzulfikar/alzheimers-dementia

show abstract

Section: Related Workmentioning

confidence: 99%

Multimodal Inductive Transfer Learning for Detection of Alzheimer’s Dementia and its Severity

Sarawgi

Zulfikar

Soliman³

et al. 2020

Interspeech 2020

View full text Add to dashboard Cite

show abstract

“…Dementia, a syndrome in which there is deterioration in cognitive function beyond what might be expected from normal ageing, is mostly affected by Alzheimers Disease [5]. There were previous researches with various approaches to recognize Alzheimer's Dementia [6,7,8,9], which has shown excellent performance. However, datasets used in these works were sufficient with quantity than the one used in this paper.…”

Section: Introductionmentioning

confidence: 99%

“…We compare 3 and 4 different acoustic and textual features, respectively, and use the hand-crafted (HC) feature and part-of-speech (POS) tagging as additional inputs. The usage of POS and HC is influenced by previous research, which has approved that using these features gained from transcript can improve the performance [8]. The proposed network is a modified version of Convolutional Recurrent Neural Network (CRNN); capable of computing conversations with variable lengths, and implemented with methods to fit with a small amount of data.…”

Section: Introductionmentioning

confidence: 99%

Exploiting Multi-Modal Features From Pre-trained Networks for Alzheimer's Dementia Recognition

Junghyun¹,

Lee²,

Pyo³

et al. 2020

Preprint

View full text Add to dashboard Cite

Collecting and accessing a large amount of medical data is very time-consuming and laborious, not only because it is difficult to find specific patients but also because it is required to resolve the confidentiality of a patient's medical records. On the other hand, there are deep learning models, trained on easily collectible, large scale datasets such as Youtube or Wikipedia, offering useful representations. It could therefore be very advantageous to utilize the features from these pre-trained networks for handling a small amount of data at hand. In this work, we exploit various multi-modal features extracted from pre-trained networks to recognize Alzheimer's Dementia using a neural network, with a small dataset provided by the ADReSS Challenge at INTERSPEECH 2020. The challenge regards to discern patients suspicious of Alzheimers Dementia by providing acoustic and textual data. With the multi-modal features, we modify a Convolutional Recurrent Neural Network based structure to perform classification and regression tasks simultaneously and is capable of computing conversations with variable lengths. Our test results surpass baseline's accuracy by 18.75%, and our validation result for the regression task shows the possibility of classifying 4 classes of cognitive impairment with an accuracy of 78.70%.

show abstract

Enriching Neural Models with Targeted Features for Dementia Detection

Cited by 2 publications

References 0 publications

Multimodal Inductive Transfer Learning for Detection of Alzheimer’s Dementia and its Severity

Multimodal Inductive Transfer Learning for Detection of Alzheimer’s Dementia and its Severity

Exploiting Multi-Modal Features From Pre-trained Networks for Alzheimer's Dementia Recognition

Contact Info

Product

Resources

About