Automatic classification of Alzheimer’s disease through features extracted from speech recordings
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1254Keywords:
Speech Processing, Deep Learning, Alzheimer's diseaseAbstract
Alzheimer's disease is a progressive neurodegenerative pathology and is among the most common forms of dementia in older people. Changes in memory are common symptoms, and changes in speech and language can be signs of cognitive decline. Intelligent systems have the potential for use as diagnostic support tools. Objective: To propose a Convolutional Neural Network model for classifying Alzheimer's disease using features extracted from speech recordings. Method: We used speech segments with and without pauses from healthy individuals and those with Alzheimer's disease to extract features and recognize patterns in spectrograms. Model training uses a 5-fold stratified cross-validation method. Results: The results showed accuracy, sensitivity, and specificity metrics of 97.37%, 97.04%, and 97.62%, respectively. Conclusion: The proposed model presented promising results and could contribute to studying non-invasive biomarkers that detect Alzheimer's disease early.
References
World Health Organization. Dementia [Internet]. World Health Organization. 2023 [cited 2023 Dec 15]. Available from: https://www.who.int/news-room/fact-sheets/detail/dementia.
Guo Y, Li C, Roan C, Pakhomov S, Cohen T. Crossing the “Cookie Theft” Corpus Chasm: Applying What BERT Learns From Outside Data to the ADReSS Challenge Dementia Detection Task. Frontiers in Computer Science. 2021 Apr 16.
Yang A, Liu C, Wu J, Kou X, Shen R. A review on α-mangostin as a potential multi-targetdirected ligand for Alzheimer’s disease. European Journal of Pharmacology 2021 Ap;897:173950.
Mahajan P, Baths V. Acoustic and Language Based Deep Learning Approaches for Alzheimer’s Dementia Detection From Spontaneous Speech. Frontiers in Aging Neuroscience 2021 Feb 5; 13.
Haulcy R, Glass J. Classifying Alzheimer’s Disease Using Audio and Text-Based Representations of Speech. Frontiers in Psychology [Internet]. 2021 Jan 15 [cited 2023 Dec 15];11. Available from: https://www.frontiersin.org/articles/10.3389/fpsyg.2020.624137.
Chlasta K, Wołk K. Towards Computer-Based Automated Screening of Dementia Through Spontaneous Speech. Frontiers in Psychology [Internet]. 2021 Feb 12 [cited 2023 Dec 15];11. Available from: https://www.frontiersin.org/articles/10.3389/fpsyg.2020.623237.
Laguarta J, Subirana B. Longitudinal Speech Biomarkers for Automated Alzheimer’s Detection. Frontiers in Computer Science [Internet]. 2021 Apr 8 [cited 2023 Dec 15];3. Available from: https://www.frontiersin.org/articles/10.3389/fcomp.2021.624694.
de la Fuente Garcia S, Ritchie CW, Luz S. Artificial Intelligence, Speech, and Language Processing Approaches to Monitoring Alzheimer’s Disease: A Systematic Review. Journal of Alzheimer’s Disease. 2020 Dec 8; 78(4):1547–74.
Yuan J, Cai X, Bian Y, Ye Z, Church K. Pauses for Detection of Alzheimer’s Disease. Frontiers in Computer Science [Internet]. 2021 Jan 29 [cited 2023 Dec 15];2. Available from: https://www.frontiersin.org/articles/10.3389/fcomp.2020.624488.
Alkenani AH, Li Y, Xu Y, Zhang Q. Predicting Prodromal Dementia Using Linguistic Patterns and Deficits. IEEE Access [Internet]. 2020 [cited 2023 Dec 15]; 8:193856–73. Available from: https://ieeexplore.ieee.org/abstract/document/9218925.
Pompili A, Abad A, de Matos DM, Martins IP. Pragmatic Aspects of Discourse Production for the Automatic Identification of Alzheimer’s Disease. IEEE Journal of Selected Topics in Signal Processing [Internet]. 2020 Feb 1;14(2):261–71. Available from: https://ieeexplore.ieee.org/document/8963723.
Liu Z, Guo Z, Ling Z, Li Y. Detecting Alzheimer’s Disease from Speech Using Neural Networks with Bottleneck Features and Data Augmentation [Internet]. IEEE Xplore. 2021. p. 7323–7. Available from: https://ieeexplore.ieee.org/document/9413566.
Gónzalez Atienza M, González López JA, Peinado AM. An Automatic System for Dementia Detection using Acoustic and Linguistic Features. digibugugres [Internet]. 2021 Jan 28; Available from: https://digibug.ugr.es/handle/10481/66645.
Bernieri G, Duarte JC. Identifying Alzheimer’s Disease Through Speech Using Emotion Recognition. Journal of Health Informatics [Internet]. 2023 Jul 20 [cited 2023 Dec 23];15(Especial). Available from: https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/1093.
Becker JT. The Natural History of Alzheimer’s Disease. Archives of Neurology. 1994 Jun 1;51(6):585.
Luz S, Haider F, de la Fuente S, Fromm D, MacWhinney B. Alzheimer’s Dementia Recognition through Spontaneous Speech: The ADReSS Challenge. arXiv:200406833 [cs, eess, stat] [Internet]. 2020 Aug 5 [cited 2023 Dec 15]; Available from: https://arxiv.org/abs/2004.06833.
Luz S, Haider F, de la Fuente Garcia S, Fromm D, MacWhinney B. Editorial: Alzheimer’s Dementia Recognition through Spontaneous Speech. Frontiers in Computer Science [Internet]. 2021 Oct 21 [cited 2023 Dec 12];3. Available from: https://www.frontiersin.org/articles/10.3389/fcomp.2021.780169.
Goodglass H, Kaplan E, Weintraub S. BDAE: The Boston Diagnostic Aphasia Examination. Philadelphia, PA: Lippincott Williams & Wilkins; 2001. 2001.
Luz S, Haider F, de la Fuente S, Fromm D, MacWhinney B. Detecting cognitive decline using speech only: The ADReSSo Challenge. arXiv:210409356 [cs, eess] [Internet]. 2021 Mar 22 [cited 2023 Dec 23]; Available from: https://arxiv.org/abs/2104.09356.
Sainburg T. timsainb/noisereduce: v1.0. zenodoorg [Internet]. 2019 Jun 11 [cited 2023 Dec 23]; Available from: https://zenodo.org/record/3243139.
Steinmetz CJ, Reiss J. pyloudnorm: A simple yet flexible loudness meter in Python [Internet]. Audio Engineering Society Convention 150. Audio Engineering Society; 2021 [cited 2023 Dec 23]. Available from: https://csteinmetz1.github.io/pyloudnorm-eval/paper/pyloudnorm_preprint.pdf.
McFee B, Metsai A, McVicar M, Balke S, Thomé C, Raffel C, et al. librosa/librosa: 0.9.2 [Internet]. Zenodo. 2022. Available from: https://zenodo.org/record/6759664#.Y6n8x-zMK00.
Tan M, Le Q. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks [Internet]. proceedings.mlr.press. PMLR; 2019 [cited 2023 Dec 23]. p. 6105–14. Available from: https://proceedings.mlr.press/v97/tan19a.html?ref=jina-ai-gmbh.ghost.io.
Team K. Keras documentation: Keras Applications [Internet]. keras.io. [cited 2023 Dec 23]. Available from: https://keras.io/api/applications.
Tammina S. Transfer learning using VGG-16 with Deep Convolutional Neural Network for Classifying Images. International Journal of Scientific and Research Publications Volume 9, Issue 10, ISSN 2250-3153; 2019.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
