Balancing Privacy Protection and Reproducible Entity Extraction in Real-World Data in the Development of a Framework for Deidentified Japanese Electronic Health Record Narratives Using BERT: Retrospective Observational Study
Balancing Privacy Protection and Reproducible Entity Extraction in Real-World Data in the Development of a Framework for Deidentified Japanese Electronic Health Record Narratives Using BERT: Retrospective Observational Study
Nobuo Mochizuki
1
, PhD ;
Atsushi Ikeda
1
, MS ;
Hideyuki Ohshima
1
, MS ;
Yukika Fukuda
1
, BS ;
Kyoko Okuda
1
, BS ;
Ryota Komaki
1
, MS ;
Tomoyuki Matsunaga
1
, MS ;
Kenichi Kudo
2
, BS ;
Shintaro Goto
3
, BS ;
Motoki Amai
3
, PhD ;
Yusuke Suzuki
1
, MS
1
Health Data Business Development Center, Business Development Division, TOPPAN Holdings Inc., Bunkyo-ku, Tokyo, Japan
2
Japan Medical Association Medical Information Management Organization, Bunkyo-ku, Tokyo, Japan
3
Department of Data Management, Integrated Clinical Care Informatics Inc, Bunkyo-ku, Tokyo, Japan
Corresponding Author:
-
Nobuo Mochizuki, PhD
-
Health Data Business Development Center, Business Development Division
-
TOPPAN Holdings Inc.
-
1-3-3, Suido
-
Bunkyo-ku, Tokyo 112-8531
-
Japan
-
Phone:
81 3-3835-5111
-
Email: nobuo.mochizuki@toppan.co.jp