Login / Signup

De-identifying free text of Japanese electronic health records.

Kohei KajiyamaHiromasa HoriguchiTakashi OkumuraMizuki MoritaYoshinobu Kano
Published in: Journal of biomedical semantics (2020)
Our LSTM-based machine learning method was able to extract named entities to be de-identified with better performance, in general, than that of our rule-based methods. However, machine learning methods are inadequate for processing expressions with low occurrence. Our future work will specifically examine the combination of LSTM and rule-based methods to achieve better performance. Our currently achieved level of performance is sufficiently higher than that of publicly available Japanese de-identification tools. Therefore, our system will be applied to actual de-identification tasks in hospitals.
Keyphrases
  • machine learning
  • electronic health record
  • artificial intelligence
  • healthcare
  • neural network
  • risk assessment
  • oxidative stress
  • big data
  • bioinformatics analysis
  • smoking cessation