scholarly journals Pauses for Detection of Alzheimer’s Disease

2021 ◽  
Vol 2 ◽  
Author(s):  
Jiahong Yuan ◽  
Xingyu Cai ◽  
Yuchen Bian ◽  
Zheng Ye ◽  
Kenneth Church
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Fine Tuning ◽  
Language Models ◽  
Test Set ◽  
Language Problems ◽  
Improved Accuracy ◽  
Cognitive Perspectives ◽  
Training Sets

Pauses, disfluencies and language problems in Alzheimer’s disease can be naturally modeled by fine-tuning Transformer-based pre-trained language models such as BERT and ERNIE. Using this method with pause-encoded transcripts, we achieved 89.6% accuracy on the test set of the ADReSS (Alzheimer’s Dementia Recognition through Spontaneous Speech) Challenge. The best accuracy was obtained with ERNIE, plus an encoding of pauses. Robustness is a challenge for large models and small training sets. Ensemble over many runs of BERT/ERNIE fine-tuning reduced variance and improved accuracy. We found that um was used much less frequently in Alzheimer’s speech, compared to uh. We discussed this interesting finding from linguistic and cognitive perspectives.

Disfluencies and Fine-Tuning Pre-Trained Language Models for Detection of Alzheimer’s Disease

2020 ◽  
Author(s):  
Jiahong Yuan ◽  
Yuchen Bian ◽  
Xingyu Cai ◽  
Jiaji Huang ◽  
Zheng Ye ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Fine Tuning ◽  
Language Models

P4-309: MULTIMODAL-CNN: IMPROVED ACCURACY OF MRI-BASED CLASSIFICATION OF ALZHEIMER'S DISEASE BY INCORPORATING CLINICAL DATA IN DEEP LEARNING

2006 ◽  
Vol 14 (7S_Part_30) ◽  
pp. P1574-P1574
Author(s):  
Taeho Jo ◽  
Kwangsik Nho ◽  
Shannon L. Risacher ◽  
Jingwen Yan ◽  
Andrew J. Saykin
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Deep Learning ◽  
Clinical Data ◽  
Improved Accuracy

scholarly journals Accelerating Hyperparameter Tuning in Machine Learning for Alzheimer’s Disease With High Performance Computing

2021 ◽  
Vol 4 ◽  
Author(s):  
Fan Zhang ◽  
Melissa Petersen ◽  
Leigh Johnson ◽  
James Hall ◽  
Sid E. O’Bryant
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
High Performance ◽  
Support Vector ◽  
Massive Datasets ◽  
Complexity Of Algorithms ◽  
Magnetic Resonance Imaging Mri ◽  
Research Challenge ◽  
Improved Accuracy

Driven by massive datasets that comprise biomarkers from both blood and magnetic resonance imaging (MRI), the need for advanced learning algorithms and accelerator architectures, such as GPUs and FPGAs has increased. Machine learning (ML) methods have delivered remarkable prediction for the early diagnosis of Alzheimer’s disease (AD). Although ML has improved accuracy of AD prediction, the requirement for the complexity of algorithms in ML increases, for example, hyperparameters tuning, which in turn, increases its computational complexity. Thus, accelerating high performance ML for AD is an important research challenge facing these fields. This work reports a multicore high performance support vector machine (SVM) hyperparameter tuning workflow with 100 times repeated 5-fold cross-validation for speeding up ML for AD. For demonstration and evaluation purposes, the high performance hyperparameter tuning model was applied to public MRI data for AD and included demographic factors such as age, sex and education. Results showed that computational efficiency increased by 96%, which helped to shed light on future diagnostic AD biomarker applications. The high performance hyperparameter tuning model can also be applied to other ML algorithms such as random forest, logistic regression, xgboost, etc.

The fine-tuning of proteolytic pathways in Alzheimer’s disease

2016 ◽  
Vol 73 (18) ◽  
pp. 3433-3451 ◽  
Author(s):  
Valentina Cecarini ◽  
Laura Bonfili ◽  
Massimiliano Cuccioloni ◽  
Matteo Mozzicafreddo ◽  
Mauro Angeletti ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Fine Tuning ◽  
Proteolytic Pathways

scholarly journals A Comparative Analysis of Machine Learning Algorithms to Predict Alzheimer’s Disease

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Morshedul Bari Antor ◽  
A. H. M. Shafayet Jamil ◽  
Maliha Mamtaz ◽  
Mohammad Monirujjaman Khan ◽  
Sultan Aljahdali ◽  
...  
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Support Vector Machine ◽  
Machine Learning Algorithms ◽  
Learning System ◽  
Fine Tuning ◽  
Support Vector ◽  
Learning Models ◽  
Machine Learning Models

Alzheimer’s disease has been one of the major concerns recently. Around 45 million people are suffering from this disease. Alzheimer’s is a degenerative brain disease with an unspecified cause and pathogenesis which primarily affects older people. The main cause of Alzheimer’s disease is Dementia, which progressively damages the brain cells. People lost their thinking ability, reading ability, and many more from this disease. A machine learning system can reduce this problem by predicting the disease. The main aim is to recognize Dementia among various patients. This paper represents the result and analysis regarding detecting Dementia from various machine learning models. The Open Access Series of Imaging Studies (OASIS) dataset has been used for the development of the system. The dataset is small, but it has some significant values. The dataset has been analyzed and applied in several machine learning models. Support vector machine, logistic regression, decision tree, and random forest have been used for prediction. First, the system has been run without fine-tuning and then with fine-tuning. Comparing the results, it is found that the support vector machine provides the best results among the models. It has the best accuracy in detecting Dementia among numerous patients. The system is simple and can easily help people by detecting Dementia among them.

scholarly journals Computer-Based Drug Design of Positive Modulators of Store-Operated Calcium Channels to Prevent Synaptic Dysfunction in Alzheimer’s Disease

2021 ◽  
Vol 22 (24) ◽  
pp. 13618
Author(s):  
Lernik Hunanyan ◽  
Viktor Ghamaryan ◽  
Ani Makichyan ◽  
Elena Popugaeva
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Drug Design ◽  
Dendritic Spines ◽  
Structural Features ◽  
Fine Tuning ◽  
3D Structures ◽  
Drug Candidates ◽  
Store Operated Calcium Entry ◽  
Computer Based

Store-operated calcium entry (SOCE) constitutes a fine-tuning mechanism responsible for the replenishment of intracellular stores. Hippocampal SOCE is regulated by store-operated channels (SOC) organized in tripartite complex TRPC6/ORAI2/STIM2. It is suggested that in neurons, SOCE maintains intracellular homeostatic Ca2+ concentration at resting conditions and is needed to support the structure of dendritic spines. Recent evidence suggests that positive modulators of SOC are prospective drug candidates to treat Alzheimer’s disease (AD) at early stages. Although STIM2 and ORAI2 are definitely involved in the regulation of nSOC amplitude and a play major role in AD pathogenesis, growing evidence suggest that it is not easy to target these proteins pharmacologically. Existing positive modulators of TRPC6 are unsuitable for drug development due to either bad pharmacokinetics or side effects. Thus, we concentrate the review on perspectives to develop specific nSOC modulators based on available 3D structures of TRPC6, ORAI2, and STIM2. We shortly describe the structural features of existing models and the methods used to prepare them. We provide commonly used steps applied for drug design based on 3D structures of target proteins that might be used to develop novel AD preventing therapy.

scholarly journals Classifying Alzheimer's Disease Using Audio and Text-Based Representations of Speech

2021 ◽  
Vol 11 ◽  
Author(s):  
R'mani Haulcy ◽  
James Glass
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Regression Model ◽  
Short Term Memory ◽  
Mean Squared Error ◽  
Gradient Boosting ◽  
Support Vector ◽  
Test Set ◽  
Audio Features ◽  
Text Features

Alzheimer's Disease (AD) is a form of dementia that affects the memory, cognition, and motor skills of patients. Extensive research has been done to develop accessible, cost-effective, and non-invasive techniques for the automatic detection of AD. Previous research has shown that speech can be used to distinguish between healthy patients and afflicted patients. In this paper, the ADReSS dataset, a dataset balanced by gender and age, was used to automatically classify AD from spontaneous speech. The performance of five classifiers, as well as a convolutional neural network and long short-term memory network, was compared when trained on audio features (i-vectors and x-vectors) and text features (word vectors, BERT embeddings, LIWC features, and CLAN features). The same audio and text features were used to train five regression models to predict the Mini-Mental State Examination score for each patient, a score that has a maximum value of 30. 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. The best-performing regression model was the gradient boosting regression model trained on BERT embeddings and CLAN features, which had a root mean squared error of 4.56 on the test set. The performance on both tasks illustrates the feasibility of using speech to classify AD and predict neuropsychological scores.

Sign in / Sign up

Export Citation Format

Share Document