Automatic Classification of Dementia Using Text and Speech Data

Hee Jeong Han; Suhas B. N; Ling Qiu; Saeed Abdullah

doi:10.1007/978-3-031-14771-5_29

Automatic Classification of Dementia Using Text and Speech Data

Hee Jeong Han
, Suhas B. N
, Ling Qiu
, Saeed Abdullah

College of Information Sciences and Technology

Research output: Chapter in Book/Report/Conference proceeding › Chapter

5 Scopus citations

Abstract

Dementia is a serious public health concern. It does not have any cure. Early detection of dementia is, thus, critical for effective symptom management as well as delaying cognitive and functional decline. This paper focuses on detecting onset of dementia using text and speech features provided by two publicly available datasets from the AAAI 2022 hackallenge. Our approach resulted in developing ACOUSTICS (AutomatiC classificatiOn of sUbjectS with demenTIa and healthy Controls using text transcriptions and Speech data)—an ensemble model with two deep learning-based architectures for text and speech analysis. ACOUSTICS achieved 89.8% accuracy when classifying individuals with dementia and health controls. Our approach outperforms current state-of-the-art methods in dementia detection.

Original language	English (US)
Title of host publication	Studies in Computational Intelligence
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	399-407
Number of pages	9
DOIs	https://doi.org/10.1007/978-3-031-14771-5_29
State	Published - 2023

Publication series

Name	Studies in Computational Intelligence
Volume	1060
ISSN (Print)	1860-949X
ISSN (Electronic)	1860-9503

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

All Science Journal Classification (ASJC) codes

Artificial Intelligence

Access to Document

10.1007/978-3-031-14771-5_29

Cite this

@inbook{f420a20512f744cca3437d791a1d8117,

title = "Automatic Classification of Dementia Using Text and Speech Data",

abstract = "Dementia is a serious public health concern. It does not have any cure. Early detection of dementia is, thus, critical for effective symptom management as well as delaying cognitive and functional decline. This paper focuses on detecting onset of dementia using text and speech features provided by two publicly available datasets from the AAAI 2022 hackallenge. Our approach resulted in developing ACOUSTICS (AutomatiC classificatiOn of sUbjectS with demenTIa and healthy Controls using text transcriptions and Speech data)—an ensemble model with two deep learning-based architectures for text and speech analysis. ACOUSTICS achieved 89.8\% accuracy when classifying individuals with dementia and health controls. Our approach outperforms current state-of-the-art methods in dementia detection.",

author = "Han, \{Hee Jeong\} and \{B. N\}, Suhas and Ling Qiu and Saeed Abdullah",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.",

year = "2023",

doi = "10.1007/978-3-031-14771-5\_29",

language = "English (US)",

series = "Studies in Computational Intelligence",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "399--407",

booktitle = "Studies in Computational Intelligence",

address = "Germany",

}

TY - CHAP

T1 - Automatic Classification of Dementia Using Text and Speech Data

AU - Han, Hee Jeong

AU - B. N, Suhas

AU - Qiu, Ling

AU - Abdullah, Saeed

PY - 2023

Y1 - 2023

N2 - Dementia is a serious public health concern. It does not have any cure. Early detection of dementia is, thus, critical for effective symptom management as well as delaying cognitive and functional decline. This paper focuses on detecting onset of dementia using text and speech features provided by two publicly available datasets from the AAAI 2022 hackallenge. Our approach resulted in developing ACOUSTICS (AutomatiC classificatiOn of sUbjectS with demenTIa and healthy Controls using text transcriptions and Speech data)—an ensemble model with two deep learning-based architectures for text and speech analysis. ACOUSTICS achieved 89.8% accuracy when classifying individuals with dementia and health controls. Our approach outperforms current state-of-the-art methods in dementia detection.

AB - Dementia is a serious public health concern. It does not have any cure. Early detection of dementia is, thus, critical for effective symptom management as well as delaying cognitive and functional decline. This paper focuses on detecting onset of dementia using text and speech features provided by two publicly available datasets from the AAAI 2022 hackallenge. Our approach resulted in developing ACOUSTICS (AutomatiC classificatiOn of sUbjectS with demenTIa and healthy Controls using text transcriptions and Speech data)—an ensemble model with two deep learning-based architectures for text and speech analysis. ACOUSTICS achieved 89.8% accuracy when classifying individuals with dementia and health controls. Our approach outperforms current state-of-the-art methods in dementia detection.

UR - https://www.scopus.com/pages/publications/85143122906

UR - https://www.scopus.com/pages/publications/85143122906#tab=citedBy

U2 - 10.1007/978-3-031-14771-5_29

DO - 10.1007/978-3-031-14771-5_29

M3 - Chapter

AN - SCOPUS:85143122906

T3 - Studies in Computational Intelligence

SP - 399

EP - 407

BT - Studies in Computational Intelligence

PB - Springer Science and Business Media Deutschland GmbH

ER -

Automatic Classification of Dementia Using Text and Speech Data

Abstract

Publication series

UN SDGs

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this