Parkinson's Disease Detection based on Changes of Emotions during Speech

Justyna Skibinska; Radim Burget

doi:10.1109/ICUMT51630.2020.9222446

Parkinson's Disease Detection based on Changes of Emotions during Speech

Justyna Skibinska
, Radim Burget

Tietotekniikka

Tutkimustuotos: Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

10 Sitaatiot (Scopus)

Abstrakti

Parkinson's disease (PD) is the neurodegenerative disease which affects 2-3 % of the population beyond 65 years of age in EU. When PD treatment is administered early, it is significantly more effective. Unfortunately, it is quite challenging to detect this disease at its early stage and when the symptoms can be recognized it is usually quite late. For this reason there is big motivation for development more accessible and accurate solutions for the detection of PD. One of the early symptoms is so-called hypomimia. This paper introduces an automatic method, which can objectively detect PD. The method is based on analysis of emotion changes during pronunciation defined speech exercises. We achieved balanced accuracy 69 % using XGBoost algorithm. As the exercise we proposed to use a Czech tongue twister - the difficult to pronounce sentence. The features can be explained and thus it can be used in clinical practice. We identified that the most valuable emotion for PD detection in this case is fear.

Alkuperäiskieli	Englanti
Otsikko	2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020
Kustantaja	IEEE
Sivut	124-130
Sivumäärä	7
ISBN (elektroninen)	9781728192819
DOI - pysyväislinkit	https://doi.org/10.1109/ICUMT51630.2020.9222446
Tila	Julkaistu - lokak. 2020
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	International Congress on Ultra Modern Telecommunications and Control Systems and Workshops - Kesto: 1 tammik. 2000 → …

Julkaisusarja

Nimi	International Congress on Ultra Modern Telecommunications and Control Systems and Workshops
Vuosikerta	2020-October
ISSN (painettu)	2157-0221
ISSN (elektroninen)	2157-023X

Conference

Conference	International Congress on Ultra Modern Telecommunications and Control Systems and Workshops
Ajanjakso	1/01/00 → …

Rahoitus

The authors gratefully acknowledge funding from European Union’s Horizon 2020 Research and Innovation programme under the Marie Skłodowska Curie grant agreement No. 813278 (A-WEAR: A network for dynamic wearable applications with privacy constraints, http://www.a-wear.eu/). This work does not represent the opinion of the European Union, and the European Union is not responsible for any use that might be made of its content.

Julkaisufoorumi-taso

Jufo-taso 1

!!ASJC Scopus subject areas

Computer Networks and Communications
Control and Systems Engineering

Pääsy asiakirjaan

10.1109/ICUMT51630.2020.9222446

Siteeraa tätä

Skibinska, J., & Burget, R. (2020). Parkinson's Disease Detection based on Changes of Emotions during Speech. teoksessa 2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020 (Sivut 124-130). Artikkeli 9222446 (International Congress on Ultra Modern Telecommunications and Control Systems and Workshops; Vuosikerta 2020-October). IEEE. https://doi.org/10.1109/ICUMT51630.2020.9222446

@inproceedings{a130694b58684bbfaf17230149d96778,

title = "Parkinson's Disease Detection based on Changes of Emotions during Speech",

abstract = "Parkinson's disease (PD) is the neurodegenerative disease which affects 2-3 \% of the population beyond 65 years of age in EU. When PD treatment is administered early, it is significantly more effective. Unfortunately, it is quite challenging to detect this disease at its early stage and when the symptoms can be recognized it is usually quite late. For this reason there is big motivation for development more accessible and accurate solutions for the detection of PD. One of the early symptoms is so-called hypomimia. This paper introduces an automatic method, which can objectively detect PD. The method is based on analysis of emotion changes during pronunciation defined speech exercises. We achieved balanced accuracy 69 \% using XGBoost algorithm. As the exercise we proposed to use a Czech tongue twister - the difficult to pronounce sentence. The features can be explained and thus it can be used in clinical practice. We identified that the most valuable emotion for PD detection in this case is fear. ",

author = "Justyna Skibinska and Radim Burget",

note = "Funding Information: The authors gratefully acknowledge funding from European Union{\textquoteright}s Horizon 2020 Research and Innovation programme under the Marie Sk{\l}odowska Curie grant agreement No. 813278 (A-WEAR: A network for dynamic wearable applications with privacy constraints, http://www.a-wear.eu/). This work does not represent the opinion of the European Union, and the European Union is not responsible for any use that might be made of its content. Publisher Copyright: {\textcopyright} 2020 IEEE. jufiod=72315 Copyright: Copyright 2020 Elsevier B.V., All rights reserved.; International Congress on Ultra Modern Telecommunications and Control Systems and Workshops ; Conference date: 01-01-2000",

year = "2020",

month = oct,

doi = "10.1109/ICUMT51630.2020.9222446",

language = "English",

series = "International Congress on Ultra Modern Telecommunications and Control Systems and Workshops",

publisher = "IEEE",

pages = "124--130",

booktitle = "2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020",

address = "United States",

}

Skibinska, J & Burget, R 2020, Parkinson's Disease Detection based on Changes of Emotions during Speech. julkaisussa 2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020., 9222446, International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, Vuosikerta 2020-October, IEEE, Sivut 124-130, International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, 1/01/00. https://doi.org/10.1109/ICUMT51630.2020.9222446

Parkinson's Disease Detection based on Changes of Emotions during Speech. / Skibinska, Justyna; Burget, Radim.
2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020. IEEE, 2020. s. 124-130 9222446 (International Congress on Ultra Modern Telecommunications and Control Systems and Workshops; Vuosikerta 2020-October).

Tutkimustuotos: Konferenssiartikkeli › Tieteellinen › vertaisarvioitu

TY - GEN

T1 - Parkinson's Disease Detection based on Changes of Emotions during Speech

AU - Skibinska, Justyna

AU - Burget, Radim

N1 - Funding Information: The authors gratefully acknowledge funding from European Union’s Horizon 2020 Research and Innovation programme under the Marie Skłodowska Curie grant agreement No. 813278 (A-WEAR: A network for dynamic wearable applications with privacy constraints, http://www.a-wear.eu/). This work does not represent the opinion of the European Union, and the European Union is not responsible for any use that might be made of its content. Publisher Copyright: © 2020 IEEE. jufiod=72315 Copyright: Copyright 2020 Elsevier B.V., All rights reserved.

PY - 2020/10

Y1 - 2020/10

N2 - Parkinson's disease (PD) is the neurodegenerative disease which affects 2-3 % of the population beyond 65 years of age in EU. When PD treatment is administered early, it is significantly more effective. Unfortunately, it is quite challenging to detect this disease at its early stage and when the symptoms can be recognized it is usually quite late. For this reason there is big motivation for development more accessible and accurate solutions for the detection of PD. One of the early symptoms is so-called hypomimia. This paper introduces an automatic method, which can objectively detect PD. The method is based on analysis of emotion changes during pronunciation defined speech exercises. We achieved balanced accuracy 69 % using XGBoost algorithm. As the exercise we proposed to use a Czech tongue twister - the difficult to pronounce sentence. The features can be explained and thus it can be used in clinical practice. We identified that the most valuable emotion for PD detection in this case is fear.

AB - Parkinson's disease (PD) is the neurodegenerative disease which affects 2-3 % of the population beyond 65 years of age in EU. When PD treatment is administered early, it is significantly more effective. Unfortunately, it is quite challenging to detect this disease at its early stage and when the symptoms can be recognized it is usually quite late. For this reason there is big motivation for development more accessible and accurate solutions for the detection of PD. One of the early symptoms is so-called hypomimia. This paper introduces an automatic method, which can objectively detect PD. The method is based on analysis of emotion changes during pronunciation defined speech exercises. We achieved balanced accuracy 69 % using XGBoost algorithm. As the exercise we proposed to use a Czech tongue twister - the difficult to pronounce sentence. The features can be explained and thus it can be used in clinical practice. We identified that the most valuable emotion for PD detection in this case is fear.

U2 - 10.1109/ICUMT51630.2020.9222446

DO - 10.1109/ICUMT51630.2020.9222446

M3 - Conference contribution

AN - SCOPUS:85094871966

T3 - International Congress on Ultra Modern Telecommunications and Control Systems and Workshops

SP - 124

EP - 130

BT - 2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020

PB - IEEE

T2 - International Congress on Ultra Modern Telecommunications and Control Systems and Workshops

Y2 - 1 January 2000

ER -

Skibinska J, Burget R. Parkinson's Disease Detection based on Changes of Emotions during Speech. julkaisussa 2020 12th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops, ICUMT 2020. IEEE. 2020. s. 124-130. 9222446. (International Congress on Ultra Modern Telecommunications and Control Systems and Workshops). doi: 10.1109/ICUMT51630.2020.9222446

Parkinson's Disease Detection based on Changes of Emotions during Speech

Abstrakti

Julkaisusarja

Conference

Rahoitus

Julkaisufoorumi-taso

!!ASJC Scopus subject areas

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä