De-identifying Free Text of Japanese Dummy Electronic Health Records

Kajiyama, Kohei; Horiguchi, Hiromasa; Okumura, Takashi; Morita, Mizuki; Kano, Yoshinobu

doi:10.18653/v1/w18-5608

Cited by 10 publications

(14 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to Dernoncourt et al [33], the plain LSTM approach works best. However, from a consistency perspective, Kajiyama et al [39] recommend their hybrid method, but the highest F-measure score was recorded for their rule-based system. Trienes et al [47] are the only researchers whose results favor a combined LSTM-CRF approach.…”

Section: Discussion Of Surveyed Workmentioning

confidence: 99%

“…We expected to encounter a moderate level of inconsistency since there is obviously no universal standard on reporting dataset information, but unfortunately, the issue borders on the extreme. On one hand, researchers such as Trienes et al [47] provide adequate information, and on the other hand, researchers such as Kajiyama et al [39] are not as forthcoming. The inconsistency makes the process of drawing comparisons between the surveyed works more challenging.…”

Section: Discussion Of Surveyed Workmentioning

confidence: 99%

See 1 more Smart Citation

Survey on RNN and CRF models for de-identification of medical free text

Leevy

Khoshgoftaar

Villanustre³

2020

J Big Data

View full text Add to dashboard Cite

As the use and volume of medical records continues to rapidly grow in various areas, including research, there is a growing need to safeguard patient privacy for ethical and legal reasons [1]. In the USA, the confidentiality of patient information is legislated by the Health Insurance Portability and Accountability Act (HIPAA) [2]. The act lists 18 categories of protected health information (PHI), such as telephone numbers, geographic data, social security numbers, email addresses, and full face photos [3], that require special attention (see Table 1). PHI is health information capable of being linked, through the operations of a HIPAA-covered entity or business associate of the entity, to an individual patient. In the HIPAA world, the de-identification of PHI involves the reduction of risk to an acceptable level not subject to predefined privacy restrictions [4]. This process is carried out through the Expert Determination Method or the Safe Harbor method [5]. The Expert Determination method requires the opinion of a qualified statistician to

show abstract

Section: Discussion Of Surveyed Workmentioning

confidence: 99%

Section: Discussion Of Surveyed Workmentioning

confidence: 99%

Survey on RNN and CRF models for de-identification of medical free text

Leevy

Khoshgoftaar

Villanustre³

2020

J Big Data

View full text Add to dashboard Cite

show abstract

“…A major milestone was achieved in 2017, when the government legalized the use of big data (including cloud applications) in healthcare through the Medical Big Data Law, which detailed provisions for handling personal medical data and telemedicine, and covered online consultation within health insurance [ 84 ]. In the same year, the Personal Information Protection Act was passed, which established standards for careful handling of EHRs compared to other forms of personal information [ 85 ].…”

Section: Casesmentioning

confidence: 99%

Public Health Innovation through Cloud Adoption: A Comparative Analysis of Drivers and Barriers in Japan, South Korea, and Singapore

Raghavan

Demircioğlu

Taeihagh

2021

IJERPH

View full text Add to dashboard Cite

Governments are increasingly using cloud computing to reduce cost, increase access, improve quality, and create innovations in healthcare. Existing literature is primarily based on successful examples from developed western countries, and there is a lack of similar evidence from Asia. With a population close to 4.5 billion people, Asia faces healthcare challenges that pose an immense burden on economic growth and policymaking. Cloud computing in healthcare can potentially help increase the quality of healthcare delivery and reduce the economic burden, enabling governments to address healthcare challenges effectively and within a short timeframe. Advanced Asian countries such as Japan, South Korea, and Singapore provide successful examples of how cloud computing can be used to develop nationwide databases of electronic health records; real-time health monitoring for the elderly population; genetic database to support advanced research and cancer treatment; telemedicine; and health cities that drive the economy through medical industry, tourism, and research. This article examines these countries and identifies the drivers and barriers of cloud adoption in healthcare and makes policy recommendations to enable successful public health innovations through cloud adoption.

show abstract

“…We have observed the coherency of the original annotations of the datasets. Overall, this study differs from our earlier work [20] in that we added a new pathology dataset and its annotations, trained and evaluated our machine learning models using the new dataset, and evaluated the results using newly created annotations by three annotators to observe characteristics of the original and our own annotations.…”

mentioning

confidence: 99%

“…To evaluate the effectiveness of such different methods for the Japanese language, we implemented two EHR deidentification systems for the Japanese language in our earlier work [20]. We used the MedNLP shared task dataset and our own dummy EHR dataset, which was written as a virtual database by medical professionals who hold medical doctor certification.…”

mentioning

confidence: 99%

De-identifying free text of Japanese electronic health records

et al. 2020

Self Cite

View full text Add to dashboard Cite

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 de-identification 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 F1-scores 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 de-identification tools. Therefore, our system will be applied to actual de-identification tasks in hospitals.

show abstract

De-identifying Free Text of Japanese Dummy Electronic Health Records

Cited by 10 publications

References 7 publications

Survey on RNN and CRF models for de-identification of medical free text

Survey on RNN and CRF models for de-identification of medical free text

Public Health Innovation through Cloud Adoption: A Comparative Analysis of Drivers and Barriers in Japan, South Korea, and Singapore

De-identifying free text of Japanese electronic health records

Contact Info

Product

Resources

About