A Transfer Learning Method for Detecting Alzheimer's Disease Based on Speech and Natural Language Processing
TLDR
The transfer learning method in this study improves AD prediction, which does not only reduces the need for feature engineering but also addresses the lack of sufficiently large datasets.Abstract:
Alzheimer's disease (AD) is a neurodegenerative disease that is difficult to be detected using convenient and reliable methods. The language change in patients with AD is an important signal of their cognitive status, which potentially helps in early diagnosis. In this study, we developed a transfer learning model based on speech and natural language processing (NLP) technology for the early diagnosis of AD. The lack of large datasets limits the use of complex neural network models without feature engineering, while transfer learning can effectively solve this problem. The transfer learning model is firstly pre-trained on large text datasets to get the pre-trained language model, and then, based on such a model, an AD classification model is performed on small training sets. Concretely, a distilled bidirectional encoder representation (distilBert) embedding, combined with a logistic regression classifier, is used to distinguish AD from normal controls. The model experiment was evaluated on Alzheimer's dementia recognition through spontaneous speech datasets in 2020, including the balanced 78 healthy controls (HC) and 78 patients with AD. The accuracy of the proposed model is 0.88, which is almost equivalent to the champion score in the challenge and a considerable improvement over the baseline of 75% established by organizers of the challenge. As a result, the transfer learning method in this study improves AD prediction, which does not only reduces the need for feature engineering but also addresses the lack of sufficiently large datasets.read more
Citations
More filters
Journal ArticleDOI
Is cross-linguistic advert flaw detection in Wikipedia feasible? A multilingual-BERT-based transfer learning approach
TL;DR: In this paper , transfer learning based on a pretraining multilanguage model was introduced to verify whether it is feasible to conduct cross-language flaw detection in Wikipedia articles. But most of them considered only one language version, typically English.
Journal ArticleDOI
Exploring Multimodal Approaches for Alzheimer's Disease Detection Using Patient Speech Transcript and Audio Data
Hongmin Cai,Zheng Liu,Wenxiong Liao,Haixing Dai,Zihao Wu,Dajiang Zhu,Hui Ren,Quanzheng Li,Tianming Liu,Xiang (Robert) Li +9 more
TL;DR: In this paper , the authors used pre-trained language models and Graph Neural Network (GNN) to construct a graph from the speech transcript, and extracts features using GNN for AD detection.
Journal ArticleDOI
Learning implicit sentiments in Alzheimer's disease recognition with contextual attention features
TL;DR: In this article , a two-level attention mechanism was proposed to detect deep semantic information toward words and sentences, which enables it to attend to more words and fewer sentences differentially when constructing document representation.
Journal ArticleDOI
Characterizing and detecting delirium with clinical and computational measures of speech and language disturbance
Sunny X. Tang,Yan Cong,Gwenyth Mercep,Mutahira Bhatti,V. Gromova,Sarah Berretta,Majnu John,Liron Sinvani +7 more
TL;DR: This article used binomial, elastic net, and machine learning models to predict delirium status in 33 older adults admitted to hospital, of which 10 met criteria for deliriam, including total language disturbances and incoherence and lower category fluency.
Proceedings Article
Training Models on Oversampled Data and a Novel Multi-class Annotation Scheme for Dementia Detection
TL;DR: In this article , a novel three-class annotation scheme for text-based dementia classification in patients, based on their recorded visit interactions, was introduced, using BERT, RoBERTa and DistilBERT.
References
More filters
Journal ArticleDOI
Toward defining the preclinical stages of Alzheimer's disease: Recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease
Reisa A. Sperling,Paul S. Aisen,Laurel A. Beckett,David A. Bennett,Suzanne Craft,Anne M. Fagan,Takeshi Iwatsubo,Clifford R. Jack,Jeffrey Kaye,Thomas J. Montine,Denise C. Park,Eric M. Reiman,Christopher C. Rowe,Eric Siemers,Yaakov Stern,Kristine Yaffe,Maria C. Carrillo,Bill Thies,Marcelle Morrison-Bogorad,Molly V. Wagster,Creighton H. Phelps +20 more
TL;DR: A conceptual framework and operational research criteria are proposed, based on the prevailing scientific evidence to date, to test and refine these models with longitudinal clinical research studies and it is hoped that these recommendations will provide a common rubric to advance the study of preclinical AD.
Posted Content
DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter
TL;DR: This work proposes a method to pre-train a smaller general-purpose language representation model, called DistilBERT, which can be fine-tuned with good performances on a wide range of tasks like its larger counterparts, and introduces a triple loss combining language modeling, distillation and cosine-distance losses.
Proceedings ArticleDOI
Opensmile: the munich versatile and fast open-source audio feature extractor
TL;DR: The openSMILE feature extraction toolkit is introduced, which unites feature extraction algorithms from the speech processing and the Music Information Retrieval communities and has a modular, component based architecture which makes extensions via plug-ins easy.
Journal ArticleDOI
Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
Melvin Johnson,Mike Schuster,Quoc V. Le,Maxim Krikun,Yonghui Wu,Zhifeng Chen,Nikhil Thorat,Fernanda B. Viégas,Martin Wattenberg,Greg S. Corrado,Macduff Hughes,Jeffrey Dean +11 more
TL;DR: This work proposes a simple solution to use a single Neural Machine Translation (NMT) model to translate between multiple languages using a shared wordpiece vocabulary, and introduces an artificial token at the beginning of the input sentence to specify the required target language.
Proceedings ArticleDOI
Recent developments in openSMILE, the munich open-source multimedia feature extractor
TL;DR: OpenSMILE 2.0 as mentioned in this paper unifies feature extraction paradigms from speech, music, and general sound events with basic video features for multi-modal processing, allowing for time synchronization of parameters, on-line incremental processing as well as off-line and batch processing, and the extraction of statistical functionals (feature summaries).
Related Papers (5)
Sparse autoencoder based feature learning for unmanned aerial vehicle landforms image classification
Liu Fang,Lu Lixia,Huang Guangwei +2 more