scholarly journals Language Impairment in Alzheimer’s Disease—Robust and Explainable Evidence for AD-Related Deterioration of Spontaneous Speech Through Multilingual Machine Learning

2021 ◽  
Vol 13 ◽  
Author(s):  
Hali Lindsay ◽  
Johannes Tröger ◽  
Alexandra König
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Language Processing ◽  
Language Impairment ◽  
Spontaneous Speech ◽  
Semantic Features ◽  
Equal Distribution ◽  
Depth Analysis ◽  
Picture Description

Alzheimer’s disease (AD) is a pervasive neurodegenerative disease that affects millions worldwide and is most prominently associated with broad cognitive decline, including language impairment. Picture description tasks are routinely used to monitor language impairment in AD. Due to the high amount of manual resources needed for an in-depth analysis of thereby-produced spontaneous speech, advanced natural language processing (NLP) combined with machine learning (ML) represents a promising opportunity. In this applied research field though, NLP and ML methodology do not necessarily ensure robust clinically actionable insights into cognitive language impairment in AD and additional precautions must be taken to ensure clinical-validity and generalizability of results. In this study, we add generalizability through multilingual feature statistics to computational approaches for the detection of language impairment in AD. We include 154 participants (78 healthy subjects, 76 patients with AD) from two different languages (106 English speaking and 47 French speaking). Each participant completed a picture description task, in addition to a battery of neuropsychological tests. Each response was recorded and manually transcribed. From this, task-specific, semantic, syntactic and paralinguistic features are extracted using NLP resources. Using inferential statistics, we determined language features, excluding task specific features, that are significant in both languages and therefore represent “generalizable” signs for cognitive language impairment in AD. In a second step, we evaluated all features as well as the generalizable ones for English, French and both languages in a binary discrimination ML scenario (AD vs. healthy) using a variety of classifiers. The generalizable language feature set outperforms the all language feature set in English, French and the multilingual scenarios. Semantic features are the most generalizable while paralinguistic features show no overlap between languages. The multilingual model shows an equal distribution of error in both English and French. By leveraging multilingual statistics combined with a theory-driven approach, we identify AD-related language impairment that generalizes beyond a single corpus or language to model language impairment as a clinically-relevant cognitive symptom. We find a primary impairment in semantics in addition to mild syntactic impairment, possibly confounded by additional impaired cognitive functions.

scholarly journals In-depth Insights into Alzheimer's Disease by using Explainable Machine Learning Approach - Existing Hypothesis Confronted

2021 ◽  
Author(s):  
Bojan Bogdanovic ◽  
Tome Eftimov ◽  
Monika Simjanoska
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Early Stage ◽  
Negative Influence ◽  
Data Set ◽  
Huge Data ◽  
Depth Analysis ◽  
Shapley Values ◽  
Intelligent Models

Abstract Background: Alzheimer's disease is still a field of research with lots of open questions. The complexity of the disease prevents the early diagnosis before visible symptoms regarding the individual's cognitive capabilities occur. This research presents an in-depth analysis of a huge data set encompassing medical, cognitive and lifestyle's measurements from more than 12,000 individuals. Several hypothesis were established whose validity has been questioned considering the obtained results.Methods: The importance of appropriate experimental design is highly stressed in the research. Thus, a sequence of methods for handling missing data, redundancy, data imbalance, and correlation analysis have been applied for appropriate preprocessing of the data set, and consequently Random Forest and XGBoost models have been trained and evaluated with special attention to the hyperparameters tuning. Both of the models were explained by using the Shapley values produced by the SHAP method.Results: XGBoost produced the best f1-score of 0.84 and as such is considered to be highly competitive among those published in the literature. This achievement, however, was not the main contribution of this paper. This research's goal was to perform global and local interpretability of both the intelligent models and derive valuable conclusions over the established hypothesis. Those methods led to a single scheme which presents either positive, or, negative influence of the values of each of the features whose importance has been confirmed by means of Shapley values. This scheme might be considered as additional source of knowledge for the physicians and other experts whose concern is the exact diagnosis of early stage of Alzheimer's disease.Conclusion: The conclusions derived from the intelligent models interpretability rejected all the established hypothesis. This research clearly showed the importance of Machine learning explainability approach that opens the black box and clearly unveils the relationships among the features and the diagnoses.

scholarly journals Comparing Pre-trained and Feature-Based Models for Prediction of Alzheimer's Disease Based on Speech

2021 ◽  
Vol 13 ◽  
Author(s):  
Aparna Balagopalan ◽  
Benjamin Eyre ◽  
Jessica Robin ◽  
Frank Rudzicz ◽  
Jekaterina Novikova
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Domain Knowledge ◽  
Linguistic Features ◽  
Feature Based ◽  
Description Task

Introduction: Research related to the automatic detection of Alzheimer's disease (AD) is important, given the high prevalence of AD and the high cost of traditional diagnostic methods. Since AD significantly affects the content and acoustics of spontaneous speech, natural language processing, and machine learning provide promising techniques for reliably detecting AD. There has been a recent proliferation of classification models for AD, but these vary in the datasets used, model types and training and testing paradigms. In this study, we compare and contrast the performance of two common approaches for automatic AD detection from speech on the same, well-matched dataset, to determine the advantages of using domain knowledge vs. pre-trained transfer models.Methods: Audio recordings and corresponding manually-transcribed speech transcripts of a picture description task administered to 156 demographically matched older adults, 78 with Alzheimer's Disease (AD) and 78 cognitively intact (healthy) were classified using machine learning and natural language processing as “AD” or “non-AD.” The audio was acoustically-enhanced, and post-processed to improve quality of the speech recording as well control for variation caused by recording conditions. Two approaches were used for classification of these speech samples: (1) using domain knowledge: extracting an extensive set of clinically relevant linguistic and acoustic features derived from speech and transcripts based on prior literature, and (2) using transfer-learning and leveraging large pre-trained machine learning models: using transcript-representations that are automatically derived from state-of-the-art pre-trained language models, by fine-tuning Bidirectional Encoder Representations from Transformer (BERT)-based sequence classification models.Results: We compared the utility of speech transcript representations obtained from recent natural language processing models (i.e., BERT) to more clinically-interpretable language feature-based methods. Both the feature-based approaches and fine-tuned BERT models significantly outperformed the baseline linguistic model using a small set of linguistic features, demonstrating the importance of extensive linguistic information for detecting cognitive impairments relating to AD. We observed that fine-tuned BERT models numerically outperformed feature-based approaches on the AD detection task, but the difference was not statistically significant. Our main contribution is the observation that when tested on the same, demographically balanced dataset and tested on independent, unseen data, both domain knowledge and pretrained linguistic models have good predictive performance for detecting AD based on speech. It is notable that linguistic information alone is capable of achieving comparable, and even numerically better, performance than models including both acoustic and linguistic features here. We also try to shed light on the inner workings of the more black-box natural language processing model by performing an interpretability analysis, and find that attention weights reveal interesting patterns such as higher attribution to more important information content units in the picture description task, as well as pauses and filler words.Conclusion: This approach supports the value of well-performing machine learning and linguistically-focussed processing techniques to detect AD from speech and highlights the need to compare model performance on carefully balanced datasets, using consistent same training parameters and independent test datasets in order to determine the best performing predictive model.

scholarly journals Transformer-based deep neural network language models for Alzheimer’s disease risk assessment from targeted speech

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Alireza Roshanzamir ◽  
Hamid Aghajan ◽  
Mahdieh Soleymani Baghshah
Keyword(s):  
Alzheimer’S Disease ◽  
Risk Assessment ◽  
Alzheimer's Disease ◽  
Natural Language ◽  
Language Processing ◽  
Disease Risk ◽  
Large Datasets ◽  
Language Models ◽  
Classification Model ◽  
Picture Description

Abstract Background We developed transformer-based deep learning models based on natural language processing for early risk assessment of Alzheimer’s disease from the picture description test. Methods The lack of large datasets poses the most important limitation for using complex models that do not require feature engineering. Transformer-based pre-trained deep language models have recently made a large leap in NLP research and application. These models are pre-trained on available large datasets to understand natural language texts appropriately, and are shown to subsequently perform well on classification tasks with small training sets. The overall classification model is a simple classifier on top of the pre-trained deep language model. Results The models are evaluated on picture description test transcripts of the Pitt corpus, which contains data of 170 AD patients with 257 interviews and 99 healthy controls with 243 interviews. The large bidirectional encoder representations from transformers (BERTLarge) embedding with logistic regression classifier achieves classification accuracy of 88.08%, which improves the state-of-the-art by 2.48%. Conclusions Using pre-trained language models can improve AD prediction. This not only solves the problem of lack of sufficiently large datasets, but also reduces the need for expert-defined features.

scholarly journals Transformer-based deep neural network language models for Alzheimer’s disease detection from targeted speech

2020 ◽  
Author(s):  
Alireza Roshanzamir ◽  
Hamid Aghajan ◽  
Mahdieh Soleymani Baghshah
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Natural Language ◽  
Language Processing ◽  
Language Model ◽  
Large Datasets ◽  
Language Models ◽  
Classification Model ◽  
Picture Description ◽  
Network Language

Abstract Background: We developed transformer-based deep learning models based on natural language processing for early diagnosis of Alzheimer’s disease from the picture description test.Methods: The lack of large datasets poses the most important limitation for using complex models that do not require feature engineering. Transformer-based pre-trained deep language models have recently made a large leap in NLP research and application. These models are pre-trained on available large datasets to understand natural language texts appropriately, and are shown to subsequently perform well on classification tasks with small training sets. The overall classification model is a simple classifier on top of the pre-trained deep language model.Results: The models are evaluated on picture description test transcripts of the Pitt corpus, which contains data of 170 AD patients with 257 interviews and 99 healthy controls with 243 interviews. The large bidirectional encoder representations from transformers (BERTLarge) embedding with logistic regression classifier achieves classification accuracy of 88.08%, which improves thestate-of-the-art by 2.48%.Conclusions: Using pre-trained language models can improve AD prediction. This not only solves the problem of lack of sufficiently large datasets, but also reduces the need for expert-defined features.

scholarly journals Transformer-based deep neural network language models for Alzheimer's disease risk assessment from targeted speech

2021 ◽  
Author(s):  
Alireza Roshanzamir ◽  
Hamid Aghajan ◽  
Mahdieh Soleymani Baghshah
Keyword(s):  
Alzheimer’S Disease ◽  
Risk Assessment ◽  
Alzheimer's Disease ◽  
Natural Language ◽  
Language Processing ◽  
Disease Risk ◽  
Large Datasets ◽  
Language Models ◽  
Classification Model ◽  
Picture Description

Abstract Background: We developed transformer-based deep learning models based on natural language processing for early risk assessment of Alzheimer’s disease from the picture description test.Methods: The lack of large datasets poses the most important limitation for using complex models that do not require feature engineering. Transformer-based pre-trained deep language models have recently made a large leap in NLP research and application. These models are pre-trained on available large datasets to understand natural language texts appropriately, and are shown to subsequently perform well on classification tasks with small training sets. The overall classification model is a simple classifier on top of the pre-trained deep language model.Results: The models are evaluated on picture description test transcripts of the Pitt corpus, which contains data of 170 AD patients with 257 interviews and 99 healthy controls with 243 interviews. The large bidirectional encoder representations from transformers (BERTLarge) embedding with logistic regression classifier achieves classification accuracy of 88.08%, which improves the state-of-the-art by 2.48%.Conclusions: Using pre-trained language models can improve AD prediction. This not only solves the problem of lack of sufficiently large datasets, but also reduces the need for expert-defined features.

scholarly journals Machine learning of transcripts and audio recordings of spontaneous speech for diagnosis of Alzheimer’s disease

2021 ◽  
Vol 17 (S5) ◽  
Author(s):  
Ziming Liu ◽  
Lauren Proctor ◽  
Parker Collier ◽  
Devin Casenhiser ◽  
Eun Jin Paek ◽  
...  
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Spontaneous Speech ◽  
Audio Recordings

scholarly journals Transformer-Based Deep Neural Network Language Models for Alzheimer's Disease Detection from Targeted Speech

2020 ◽  
Author(s):  
Alireza Roshanzamir ◽  
Hamid Aghajan ◽  
Mahdieh Soleymani Baghshah
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Natural Language ◽  
Language Processing ◽  
Large Datasets ◽  
Language Models ◽  
Classification Model ◽  
Complex Models ◽  
Picture Description ◽  
Network Language

Abstract Background: We developed transformer-based deep learning models based on natural language processing for early diagnosis of Alzheimer’s disease from the picture description test.Methods: The lack of large datasets poses the most important limitation for using complex models that do not require feature engineering. Transformer-based pre-trained deep language models have recently made a large leap in NLP research and application. These models are pre-trained on available large datasets to understand natural language texts appropriately, and are shown to subsequently perform well on classification tasks with small training sets. The overall classification model is a simple classifier on top of the pre-trained deep language model.Results: The models are evaluated on picture description test transcripts of the Pitt corpus, which contains data of 170 AD patients with 257 interviews and 99 healthy controls with 243 interviews. The large bidirectional encoder representations from transformers (BERTLarge) embedding with logistic regression classifier achieves classification accuracy of 88.08%, which improves the state-of-the-art by 2.48%.Conclusions: Using pre-trained language models can improve AD prediction. This not only solves the problem of lack of sufficiently large datasets, but also reduces the need for expert-defined features.

A Community-Based Study Identifying Metabolic Biomarkers of Mild Cognitive Impairment and Alzheimer’s Disease Using Artificial Intelligence and Machine Learning

2020 ◽  
Vol 78 (4) ◽  
pp. 1381-1392
Author(s):  
Ali Yilmaz ◽  
Ilyas Ustun ◽  
Zafer Ugur ◽  
Sumeyya Akyol ◽  
William T. Hu ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Lipid Metabolism ◽  
Mild Cognitive Impairment ◽  
Proton Nuclear Magnetic Resonance ◽  
Community Based ◽  
Depth Analysis

Background: Currently, there is no objective, clinically available tool for the accurate diagnosis of Alzheimer’s disease (AD). There is a pressing need for a novel, minimally invasive, cost friendly, and easily accessible tool to diagnose AD, assess disease severity, and prognosticate course. Metabolomics is a promising tool for discovery of new, biologically, and clinically relevant biomarkers for AD detection and classification. Objective: Utilizing artificial intelligence and machine learning, we aim to assess whether a panel of metabolites as detected in plasma can be used as an objective and clinically feasible tool for the diagnosis of mild cognitive impairment (MCI) and AD. Methods: Using a community-based sample cohort acquired from different sites across the US, we adopted an approach combining Proton Nuclear Magnetic Resonance Spectroscopy (1H NMR), Liquid Chromatography coupled with Mass Spectrometry (LC-MS) and various machine learning statistical approaches to identify a biomarker panel capable of identifying those patients with AD and MCI from healthy controls. Results: Of the 212 measured metabolites, 5 were identified as optimal to discriminate between controls, and individuals with MCI or AD. Our models performed with AUC values in the range of 0.72–0.76, with the sensitivity and specificity values ranging from 0.75–0.85 and 0.69–0.81, respectively. Univariate and pathway analysis identified lipid metabolism as the most perturbed biochemical pathway in MCI and AD. Conclusion: A comprehensive method of acquiring metabolomics data, coupled with machine learning techniques, has identified a strong panel of diagnostic biomarkers capable of identifying individuals with MCI and AD. Further, our data confirm what other groups have reported, that lipid metabolism is significantly perturbed in those individuals suffering with dementia. This work may provide additional insight into AD pathogenesis and encourage more in-depth analysis of the AD lipidome.

Sign in / Sign up

Export Citation Format

Share Document