Presentation | 2023-03-18 Detection of Parkinson's disease patients from interview data using pre-trained language models Aiichiro Hayatsu, Ryohei Sasano, Koichi Takeda, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | It is estimated that Parkinson’s disease (PD) affects 150,000 people in Japan, and the number of patients increases as society gets older. The importance of engineering support for early detection and effective treatment of this neurodegenerative disease has been recognized. In this study, we used transcribed data of medical interviews conducted on healthy subjects and PD patients, and constructed a classifier based on pre-trained language models such as BERT to detect PD patients by capturing the features of their speech content when compared to that of healthy subjects. The transcribed data of the medical interview used in this study consisted of multiple questions asked by the doctor to encourage the subject to speak freely, and a classifier based on a pre-trained language model was used to verify which questions were effective in detecting PD patients. In addition, we proposed an input format for pre-trained models when multiple response sentences are used as input, and investigated methods that can effectively handle multiple sentences. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Parkinson’s disease / pre-trained language models / text classification |
Paper # | NLC2022-24 |
Date of Issue | 2023-03-11 (NLC) |
Conference Information | |
Committee | NLC / IPSJ-NL |
---|---|
Conference Date | 2023/3/18(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | OIST |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | Applications of natural language processing, and etc. |
Chair | Mitsuo Yoshida(Univ. of Tsukuba) / 須藤 克仁(奈良先端科学技術大学院大学) |
Vice Chair | Hiroki Sakaji(Univ. of Tokyo) / Takeshi Kobayakawa(NHK) |
Secretary | Hiroki Sakaji(NTT) / Takeshi Kobayakawa(Hiroshima Univ. of Economics) / (LINE株式会社) |
Assistant | Kanjin Takahashi(Sansan) / Yasuhiro Ogawa(Nagoya Univ.) |
Paper Information | |
Registration To | Technical Committee on Natural Language Understanding and Models of Communication / Special Interest Group on Natural Language |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Detection of Parkinson's disease patients from interview data using pre-trained language models |
Sub Title (in English) | |
Keyword(1) | Parkinson’s disease |
Keyword(2) | pre-trained language models |
Keyword(3) | text classification |
1st Author's Name | Aiichiro Hayatsu |
1st Author's Affiliation | Nagoya University(Nagoya Univ.) |
2nd Author's Name | Ryohei Sasano |
2nd Author's Affiliation | Nagoya University(Nagoya Univ.) |
3rd Author's Name | Koichi Takeda |
3rd Author's Affiliation | Nagoya University(Nagoya Univ.) |
Date | 2023-03-18 |
Paper # | NLC2022-24 |
Volume (vol) | vol.122 |
Number (no) | NLC-449 |
Page | pp.pp.28-31(NLC), |
#Pages | 4 |
Date of Issue | 2023-03-11 (NLC) |