bsuirДоклады БГУИРDoklady BGUIR1729-76482708-0382БГУИР10.35596/1729-7648-2023-21-6-106-112bsuir-3798Research ArticleЭЛЕКТРОНИКА, РАДИОФИЗИКА, РАДИОТЕХНИКА, ИНФОРМАТИКАELECTRONICS, RADIOPHYSICS, RADIOENGINEERING, INFORMATICSИспользование машинного обучения для распознавания болезни Альцгеймера на основе транскрипционной информацииUsing Machine Learning for Recognition of Alzheimer’s Disease Based on Transcription InformationВишняковВ. А.VishniakouU. A.

г. Минск

Dr. of Sci. (Tech.), Professor at the Department of Infocommunication Technologies

220013, Minsk, P. Brovki St., 6

Tel.: +375 44 486-71-82

ЮйЧу ЮэYuChu Yue

г. Минск

Postgraduate at the Department of Infocommunication Technologies

Minsk

Белорусский государственный университет информатики и радиоэлектроникиBelarusian State University of Informatics and Radioelectronics202305012024216106112Copyright © Вишняков В.А., Юй Ч., 20242024Вишняков В.А., Юй Ч.Vishniakou U.A., Yu C.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://doklady.bsuir.by/jour/article/view/3798

Выполнены аналитические и прогностические исследования по распознаванию болезни Альц геймера на основе расшифрованных текстовых речевых данных с использованием алгоритмов машинного обучения. Данные были взяты из программы ADReSS 2020 Challenge, которая содержит речевые данные пациентов с болезнью Альцгеймера и здоровых людей. Распознавание болезни Альцгеймера представляет собой проблему бинарной классификации. Сначала из расшифрованных текстов речевых данных извлекались полные тексты интервьюируемых пациентов. Затем следовало обучение модели нейронной сети на основе векторизованных текстовых признаков с использованием классификатора случайного леса, в котором авторы применяли метод GridSearchCV для оптимизации гиперпараметров. Точность классификации модели составила 85,2 %.

The purpose of this article is to perform analytical and prognostic studies on the recognition of Alzhei mer’s disease based on decoded text speech data using machine learning algorithms. The data used in this article is taken from the ADReSS 2020 Challenge program, which contains speech data from patients with Alzhei mer’s disease and healthy people. The problem under study is a binary classification problem. First, the full texts of the interviewees were extracted from the transcribed texts of the speech data. This was followed by training the model based on vectorized text features using a random forest classifier, in which the authors used the GridSearchCV method to optimize hyperparameters. The classification accuracy of the model reached 85.2 %.

машинное обучениеметод случайного лесабинарная классификацияпараметры оптимизацииmachine learningrandom forest methodbinary classificationoptimization parametersReferencesMartínez-Sánchez F., Meilán J. J. G., Carro J., Ivanova O. (2018) A Prototype for the Voice Analysis Diagnosis of Alzheimer’s Disease. Journal of Alzheimer’s Disease. 64 (2), 473–481.Martínez-Sánchez F., Meilán J. J. G., Carro J., Ivanova O. (2018) A Prototype for the Voice Analysis Diagnosis of Alzheimer’s Disease. Journal of Alzheimer’s Disease. 64 (2), 473–481.Pulido M. L. B., Hernández J. B. A., Ballester M. Á. F., González C. M. T., Mekyska J., Smékal Z. (2020) Alzheimer’s Disease and Automatic Speech Analysis: A Review. Expert Systems with Applications. 150, 113213.Pulido M. L. B., Hernández J. B. A., Ballester M. Á. F., González C. M. T., Mekyska J., Smékal Z. (2020) Alzheimer’s Disease and Automatic Speech Analysis: A Review. Expert Systems with Applications. 150, 113213.Lorenz K., Freddolino P. P., Comas-Herrera A., Knapp M., Damant J. (2019) Technology-Based Tools and Services for Peop le with Dementia and Carers: Mapping Technology Onto the Dementia Care Pathway. Dementia. 18 (2), 725–741.Lorenz K., Freddolino P. P., Comas-Herrera A., Knapp M., Damant J. (2019) Technology-Based Tools and Services for Peop le with Dementia and Carers: Mapping Technology Onto the Dementia Care Pathway. Dementia. 18 (2), 725–741.Szatloczki G., Hoffmann I., Vincze V., Kalman J., Pakaski M. (2015) Speaking in Alzheimer’s Disease, is That an Early Sign? Importance of Changes in Language Abilities in Alzheimer’s Disease. Frontiers in Aging Neuroscience. (7), 195.Szatloczki G., Hoffmann I., Vincze V., Kalman J., Pakaski M. (2015) Speaking in Alzheimer’s Disease, is That an Early Sign? Importance of Changes in Language Abilities in Alzheimer’s Disease. Frontiers in Aging Neuroscience. (7), 195.Fraser K. C., Meltzer J. A., Rudzicz F. (2016) Linguistic Features Identify Alzheimer’s Disease in Narrative Speech. Journal of Alzheimer’s Disease. 49 (2), 407–422.Fraser K. C., Meltzer J. A., Rudzicz F. (2016) Linguistic Features Identify Alzheimer’s Disease in Narrative Speech. Journal of Alzheimer’s Disease. 49 (2), 407–422.Gosztolya G., Vincze V., Tóth L. Pákáski M., Kálmán János, Hoffmann Ildikó (2019) Identifying Mild Cognitive Impairment and Mild Alzheimer’s Disease Based on Spontaneous Speech Using ASR and Linguistic Features. Computer Speech & Language. 53, 181–197.Gosztolya G., Vincze V., Tóth L. Pákáski M., Kálmán János, Hoffmann Ildikó (2019) Identifying Mild Cognitive Impairment and Mild Alzheimer’s Disease Based on Spontaneous Speech Using ASR and Linguistic Features. Computer Speech & Language. 53, 181–197.Garreta R., Moncecchi G. (2013) Learning Scikit-Learn: Machine Learning in Python. Great Britain, Packt Publ.Garreta R., Moncecchi G. (2013) Learning Scikit-Learn: Machine Learning in Python. Great Britain, Packt Publ.Luz S., Haider F., de la Fuente S., Fromm D., MacWhinney B. (2004) Alzheimer’s Dementia Recognition Through Spontaneous Speech: The ADReSS Challenge. arXiv Preprint arXiv. 06833, 2172–2176.Luz S., Haider F., de la Fuente S., Fromm D., MacWhinney B. (2004) Alzheimer’s Dementia Recognition Through Spontaneous Speech: The ADReSS Challenge. arXiv Preprint arXiv. 06833, 2172–2176.Pompili A., Abad A., de Matos D. M. (2020) Pragmatic Aspects of Discourse Production for the Automatic Identification of Alzheimer’s Disease. IEEE Journal of Selected Topics in Signal Processing. 14 (2), 261–271.Pompili A., Abad A., de Matos D. M. (2020) Pragmatic Aspects of Discourse Production for the Automatic Identification of Alzheimer’s Disease. IEEE Journal of Selected Topics in Signal Processing. 14 (2), 261–271.Brian MacWhinney (2014) The CHILDES Project: Tools for Analyzing Talk. Vol. II: The Database. Moscow, Psychology Publ. 432.Brian MacWhinney (2014) The CHILDES Project: Tools for Analyzing Talk. Vol. II: The Database. Moscow, Psychology Publ. 432.Manning C. D. (2009) An Introduction to Information Retrieval. Cambridge, Cambridge University Publ. 581.Manning C. D. (2009) An Introduction to Information Retrieval. Cambridge, Cambridge University Publ. 581.Breiman L. (2001) Random Forests. Machine Learning. 45, 5–32.Breiman L. (2001) Random Forests. Machine Learning. 45, 5–32.Yuan J., Bian J., Cai X., Huang J, Ye Z., Church K. (2020) Disfluencies and Fine-Tuning Pre-Trained Language Models for Detection of Alzheimer’s Disease. Interspeech. 2020, 2162–2166.Yuan J., Bian J., Cai X., Huang J, Ye Z., Church K. (2020) Disfluencies and Fine-Tuning Pre-Trained Language Models for Detection of Alzheimer’s Disease. Interspeech. 2020, 2162–2166.

The authors declare that there are no conflicts of interest present.