Feature set for a prediction model of diabetic kidney disease progression

Masaki Ono, Takayuki Katsuki, Masaki Makino, Kyoichi Haida, Atsushi Suzuki, Reitaro Tokumasu

研究成果: Conference contribution

抄録

In this paper, we propose feature extraction method for prediction model for at the early stage of diabetic kidney disease (DKD) progression. DKD needs continuous treatment; however, a hospital visit interval of a patient at the early stage of DKD is normally from one month to three months, and this is not a short time period. Therefore it makes difficult to apply sophisticated approaches such as using convolutional neural networks because of the data limitation. The propose method uses with hierarchical clustering that can estimate a suitable interval for grouping inputted sequences. We evaluate the proposed method with a real-EMR dataset that consists of 30,810 patient records and conclude that the proposed method outperforms the baseline methods derived from related work.

本文言語English
ホスト出版物のタイトルDigital Personalized Health and Medicine - Proceedings of MIE 2020
編集者Louise B. Pape-Haugaard, Christian Lovis, Inge Cort Madsen, Patrick Weber, Per Hostrup Nielsen, Philip Scott
出版社IOS Press
ページ1289-1290
ページ数2
ISBN(電子版)9781643680828
DOI
出版ステータスPublished - 16-06-2020
外部発表はい
イベント30th Medical Informatics Europe Conference, MIE 2020 - Geneva, Switzerland
継続期間: 28-04-202001-05-2020

出版物シリーズ

名前Studies in Health Technology and Informatics
270
ISSN(印刷版)0926-9630
ISSN(電子版)1879-8365

Conference

Conference30th Medical Informatics Europe Conference, MIE 2020
国/地域Switzerland
CityGeneva
Period28-04-2001-05-20

All Science Journal Classification (ASJC) codes

  • 生体医工学
  • 健康情報学
  • 健康情報管理

フィンガープリント

「Feature set for a prediction model of diabetic kidney disease progression」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル