De-identifying free text of Japanese electronic health records
- PDF / 934,972 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 56 Downloads / 307 Views
(2020) 11:11
RESEARCH
Open Access
De-identifying free text of Japanese electronic health records Kohei Kajiyama1, Hiromasa Horiguchi2, Takashi Okumura3, Mizuki Morita4 and Yoshinobu Kano1*
Abstract Background: Recently, more electronic data sources are becoming available in the healthcare domain. Electronic health records (EHRs), with their vast amounts of potentially available data, can greatly improve healthcare. Although EHR de-identification is necessary to protect personal information, automatic de-identification of Japanese language EHRs has not been studied sufficiently. This study was conducted to raise de-identification performance for Japanese EHRs through classic machine learning, deep learning, and rule-based methods, depending on the dataset. Results: Using three datasets, we implemented de-identification systems for Japanese EHRs and compared the deidentification performances found for rule-based, Conditional Random Fields (CRF), and Long-Short Term Memory (LSTM)-based methods. Gold standard tags for de-identification are annotated manually for age, hospital, person, sex, and time. We used different combinations of our datasets to train and evaluate our three methods. Our best F1scores were 84.23, 68.19, and 81.67 points, respectively, for evaluations of the MedNLP dataset, a dummy EHR dataset that was virtually written by a medical doctor, and a Pathology Report dataset. Our LSTM-based method was the best performing, except for the MedNLP dataset. The rule-based method was best for the MedNLP dataset. The LSTM-based method achieved a good score of 83.07 points for this MedNLP dataset, which differs by 1.16 points from the best score obtained using the rule-based method. Results suggest that LSTM adapted well to different characteristics of our datasets. Our LSTM-based method performed better than our CRF-based method, yielding a 7.41 point F1-score, when applied to our Pathology Report dataset. This report is the first of study applying this LSTM-based method to any de-identification task of a Japanese EHR. Conclusions: 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 deidentification tools. Therefore, our system will be applied to actual de-identification tasks in hospitals. Keywords: De-identification, Electronic health records, Japanese language
Background Recently, more electronic data sources are becoming available in the healthcare domain. Utilization of * Correspondence: [email protected] 1 Faculty of Informatics, Shizuoka University, Johoku 3-5-1, Naka-ku, Hamamatsu, Shizuoka 432-8011, Japan Full list of author information is available at the end
Data Loading...
