A Review of Automated Speech and Language Features for Assessment of Cognitive and Thought Disorders

Voleti, Rohit; Liss, Julie; Berisha, Visar

doi:10.1109/jstsp.2019.2952087

Cited by 65 publications

(73 citation statements)

References 77 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The review by [ 20 ] is, to our knowledge, the only published work with a comparable aim to the the present review, although there are important scope differences. First of all, the review by Voleti et al.…”

Section: Resultsmentioning

confidence: 92%

“…This section briefly defines key terminology and abbreviations referring and offers a taxonomy of features, adapted from Voleti et al [ 20 ], to enhance the readability of the systematic review tables. This section also briefly describes the most commonly used databases and neuropsychological assessments, with the intention of making these accessible for the reader.…”

Section: Methodsmentioning

confidence: 99%

“…Notwithstanding, while most of the papers hereby reviewed highlight the potential of AI and machine learning methods, no actual translation into clinical practice has been achieved. One might speculate that this slow uptake, Voleti et al[20], which we adapted inTable 1,becomes essential in order to make cross-study comparisons. Surprisingly, many studies do not report on their approach to feature set reduction, or do it very vaguely, giving less than enough detail for replication.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Artificial Intelligence, Speech, and Language Processing Approaches to Monitoring Alzheimer’s Disease: A Systematic Review

Garcia

Ritchie

Luz

2020

JAD

153

View full text Add to dashboard Cite

Background: Language is a valuable source of clinical information in Alzheimer’s disease, as it declines concurrently with neurodegeneration. Consequently, speech and language data have been extensively studied in connection with its diagnosis. Objective: Firstly, to summarize the existing findings on the use of artificial intelligence, speech, and language processing to predict cognitive decline in the context of Alzheimer’s disease. Secondly, to detail current research procedures, highlight their limitations, and suggest strategies to address them. Methods: Systematic review of original research between 2000 and 2019, registered in PROSPERO (reference CRD42018116606). An interdisciplinary search covered six databases on engineering (ACM and IEEE), psychology (PsycINFO), medicine (PubMed and Embase), and Web of Science. Bibliographies of relevant papers were screened until December 2019. Results: From 3,654 search results, 51 articles were selected against the eligibility criteria. Four tables summarize their findings: study details (aim, population, interventions, comparisons, methods, and outcomes), data details (size, type, modalities, annotation, balance, availability, and language of study), methodology (pre-processing, feature generation, machine learning, evaluation, and results), and clinical applicability (research implications, clinical potential, risk of bias, and strengths/limitations). Conclusion: Promising results are reported across nearly all 51 studies, but very few have been implemented in clinical research or practice. The main limitations of the field are poor standardization, limited comparability of results, and a degree of disconnect between study aims and clinical applications. Active attempts to close these gaps will support translation of future research into clinical practice.

show abstract

Section: Resultsmentioning

confidence: 92%

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Artificial Intelligence, Speech, and Language Processing Approaches to Monitoring Alzheimer’s Disease: A Systematic Review

Garcia

Ritchie

Luz

2020

JAD

153

View full text Add to dashboard Cite

show abstract

“…More recently, some studies employ acoustic information extracted from spontaneous speech to detect dementia from preclinical stages of subjective memory loss, to more severe conditions like mild cognitive impairment and Alzheimer's dementia [40]. Some studies in this area combine natural language processing, looking for lexical/syntactic complexity and semantic coherence, with speech signal processing, analyzing prosody, pause and speech rates, as well as articulation [40]- [42].…”

Section: State Of the Artmentioning

confidence: 99%

Implantable and Wearable Neuroengineering Education: A Review of Postgraduate Programmes

et al. 2020

View full text Add to dashboard Cite

Neurological diseases (NDs) such as epilepsy, dementia, Alzheimer's and Parkinson's disease currently affect almost two thirds of Europe's population. Furthermore, enormous financial commitments are required to deal with these diseases. Therefore, there is growing concern that countries with transitional economies may struggle to handle this financial burden, which warrants the urgent development of new technologies for early disease identification and treatment. Consequently, the aim of our article is to survey the range of postgraduate programmes that strive to nurture neuroengineering graduates who will excel in designing and developing implantable and wearable technologies for ND applications. Based on the basic building blocks of these technologies, we have identified four key areas that programmes need to cover, which include Neuroscience, Integrated Circuits, Communications and Signal Processing as well as Electronic Devices. According to our systematic review, a total of fifteen institutes satisfied our search criteria and provided the necessary neuroengineering training. The majority of these programmes are located in Europe and North America, which means that cross border and interdisciplinary efforts are required to develop educational programmes in countries most vulnerable to these diseases. We also provide recommendations for how these programmes can be delivered using non-traditional teaching approaches to ensure that graduates develop the necessary soft skills required by the constantly shifting job market. INDEX TERMS Neuroengineering, Wearables, Implantables, Engineering Education.

show abstract

“…Although promising research has been done, the datasets that have been used are often imbalanced and vary across studies, making it difficult to compare the effectiveness of different modalities. Two recent review papers (Voleti et al, 2019 ; de la Fuente Garcia et al, 2020 ) explain that an important future direction for the detection of cognitive impairment is providing a balanced, standardized dataset that will allow researchers to compare the effectiveness of different classification techniques and feature extraction methods. This is what the ADReSS challenge attempted to do.…”

Section: Introductionmentioning

confidence: 99%

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

Haulcy

Glass

2021

Front. Psychol.

View full text Add to dashboard Cite

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.

show abstract

A Review of Automated Speech and Language Features for Assessment of Cognitive and Thought Disorders

Cited by 65 publications

References 77 publications

Artificial Intelligence, Speech, and Language Processing Approaches to Monitoring Alzheimer’s Disease: A Systematic Review

Artificial Intelligence, Speech, and Language Processing Approaches to Monitoring Alzheimer’s Disease: A Systematic Review

Implantable and Wearable Neuroengineering Education: A Review of Postgraduate Programmes

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

Contact Info

Product

Resources

About