A cascaded approach for Chinese clinical text de-identification with less annotation effort

De-identification of clinical free text using natural language processing: A systematic review of current approaches

BACKGROUND

Electronic health records (EHRs) are a valuable resource for data-driven medical research. However, the presence of protected health information (PHI) makes EHRs unsuitable to be shared for research purposes. De-identification, i.e. the process of removing PHI is a critical step in making EHR data accessible. Natural language processing has repeatedly demonstrated its feasibility in automating the de-identification process.

OBJECTIVES

Our study aims to provide systematic evidence on how the de-identification of clinical free text written in English has evolved in the last thirteen years, and to report on the performances and limitations of the current state-of-the-art systems for the English language. In addition, we aim to identify challenges and potential research opportunities in this field.

METHODS

A systematic search in PubMed, Web of Science, and the DBLP was conducted for studies published between January 2010 and February 2023. Titles and abstracts were examined to identify the relevant studies. Selected studies were then analysed in-depth, and information was collected on de-identification methodologies, data sources, and measured performance.

RESULTS

A total of 2125 publications were identified for the title and abstract screening. 69 studies were found to be relevant. Machine learning (37 studies) and hybrid (26 studies) approaches are predominant, while six studies relied only on rules. The majority of the approaches were trained and evaluated on public corpora. The 2014 i2b2/UTHealth corpus is the most frequently used (36 studies), followed by the 2006 i2b2 (18 studies) and 2016 CEGS N-GRID (10 studies) corpora.

CONCLUSION

Earlier de-identification approaches aimed at English were mainly rule and machine learning hybrids with extensive feature engineering and post-processing, while more recent performance improvements are due to feature-inferring recurrent neural networks. Current leading performance is achieved using attention-based neural models. Recent studies report state-of-the-art F1-scores (over 98 %) when evaluated in the manner usually adopted by the clinical natural language processing community. However, their performance needs to be more thoroughly assessed with different measures to judge their reliability to safely de-identify data in a real-world setting. Without additional manually labeled training data, state-of-the-art systems fail to generalise well across a wide range of clinical sub-domains.

Optimizing healthcare system by amalgamation of text processing and deep learning: a systematic review

The explosion of clinical textual data has drawn the attention of researchers. Owing to the abundance of clinical data, it is becoming difficult for healthcare professionals to take real-time measures. The tools and methods are lacking when compared to the amount of clinical data generated every day. This review aims to survey the text processing pipeline with deep learning methods such as CNN, RNN, LSTM, and GRU in the healthcare domain and discuss various applications such as clinical concept detection and extraction, medically aware dialogue systems, sentiment analysis of drug reviews shared online, clinical trial matching, and pharmacovigilance. In addition, we highlighted the major challenges in deploying text processing with deep learning to clinical textual data and identified the scope of research in this domain. Furthermore, we have discussed various resources that can be used in the future to optimize the healthcare domain by amalgamating text processing and deep learning.

An Efficient Method for Deidentifying Protected Health Information in Chinese Electronic Health Records: Algorithm Development and Validation

Background

With the popularization of electronic health records in China, the utilization of digitalized data has great potential for the development of real-world medical research. However, the data usually contains a great deal of protected health information and the direct usage of this data may cause privacy issues. The task of deidentifying protected health information in electronic health records can be regarded as a named entity recognition problem. Existing rule-based, machine learning–based, or deep learning–based methods have been proposed to solve this problem. However, these methods still face the difficulties of insufficient Chinese electronic health record data and the complex features of the Chinese language.

Objective

This paper proposes a method to overcome the difficulties of overfitting and a lack of training data for deep neural networks to enable Chinese protected health information deidentification.

Methods

We propose a new model that merges TinyBERT (bidirectional encoder representations from transformers) as a text feature extraction module and the conditional random field method as a prediction module for deidentifying protected health information in Chinese medical electronic health records. In addition, a hybrid data augmentation method that integrates a sentence generation strategy and a mention-replacement strategy is proposed for overcoming insufficient Chinese electronic health records.

Results

We compare our method with 5 baseline methods that utilize different BERT models as their feature extraction modules. Experimental results on the Chinese electronic health records that we collected demonstrate that our method had better performance (microprecision: 98.7%, microrecall: 99.13%, and micro-F1 score: 98.91%) and higher efficiency (40% faster) than all the BERT-based baseline methods.

Conclusions

Compared to baseline methods, the efficiency advantage of TinyBERT on our proposed augmented data set was kept while the performance improved for the task of Chinese protected health information deidentification.

Classifying Cyber-Risky Clinical Notes by Employing Natural Language Processing

Clinical notes, which can be embedded into electronic medical records, document patient care delivery and summarize interactions between healthcare providers and patients. These clinical notes directly inform patient care and can also indirectly inform research and quality/safety metrics, among other indirect metrics. Recently, some states within the United States of America require patients to have open access to their clinical notes to improve the exchange of patient information for patient care. Thus, developing methods to assess the cyber risks of clinical notes before sharing and exchanging data is critical. While existing natural language processing techniques are geared to de-identify clinical notes, to the best of our knowledge, few have focused on classifying sensitive-information risk, which is a fundamental step toward developing effective, widespread protection of patient health information. To bridge this gap, this research investigates methods for identifying security/privacy risks within clinical notes. The classification either can be used upstream to identify areas within notes that likely contain sensitive information or downstream to improve the identification of clinical notes that have not been entirely de-identified. We develop several models using unigram and word2vec features with different classifiers to categorize sentence risk. Experiments on i2b2 de-identification dataset show that the SVM classifier using word2vec features obtained a maximum F1-score of 0.792. Future research involves articulation and differentiation of risk in terms of different global regulatory requirements.

De-identifying Spanish medical texts - named entity recognition applied to radiology reports

BACKGROUND

Medical texts such as radiology reports or electronic health records are a powerful source of data for researchers. Anonymization methods must be developed to de-identify documents containing personal information from both patients and medical staff. Although currently there are several anonymization strategies for the English language, they are also language-dependent. Here, we introduce a named entity recognition strategy for Spanish medical texts, translatable to other languages.

RESULTS

We tested 4 neural networks on our radiology reports dataset, achieving a recall of 97.18% of the identifying entities. Alongside, we developed a randomization algorithm to substitute the detected entities with new ones from the same category, making it virtually impossible to differentiate real data from synthetic data. The three best architectures were tested with the MEDDOCAN challenge dataset of electronic health records as an external test, achieving a recall of 69.18%.

CONCLUSIONS

The strategy proposed, combining named entity recognition tasks with randomization of entities, is suitable for Spanish radiology reports. It does not require a big training corpus, thus it could be easily extended to other languages and medical texts, such as electronic health records.

De-identifying free text of Japanese electronic health records

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.

Extraction of risk factors for cardiovascular diseases from Chinese electronic medical records

BACKGROUND AND OBJECTIVE

Early prevention of cardiovascular diseases (CVDs) can effectively prevent later loss of health, and the detection of CVDs risk factors is a simple method to achieve early prevention. Personal health records play a prominent role in the field of health information extraction because of their factuality and reliability. This present study describes how to extract risk factors for CVDs from Chinese electronic medical records (CEMRs).

METHODS

The extraction process involves two tasks: (a) CVDs risk factor recognition and (b) risk factor time and assertion classification. We considered risk factor recognition as a named entity recognition (NER) task and time and assertion classification as a textual classification task. An information extraction pipeline system consisting of NER and textual classification modules with machine learning models was developed. In the risk factor recognition module, bidirectional long short term memory (BLSTM) with extra risk factor textual feature input was built, as well, convolutional neural networks (CNNs) with risk factor type and section label input and support vector machine (SVM) were built for time and assertion classification.

RESULTS

We have achieved the best performance of risk factor recognition with F1 value of 0.9609, time and assertion classification with F1 of 0.9812 and 0.9612, respectively. The experimental results showed that our system achieved a high performance and can extract risk factors from CEMRs efficiently.

CONCLUSIONS

The proposed system is the first system for CVDs risk factors extraction from CEMRs and shows competition to risk factor extraction systems that developed on English EMRs. Further, its good performance should have a strong influence on CVDs prevention.

A machine learning based approach to identify protected health information in Chinese clinical text

BACKGROUND

With the increasing application of electronic health records (EHRs) in the world, protecting private information in clinical text has drawn extensive attention from healthcare providers to researchers. De-identification, the process of identifying and removing protected health information (PHI) from clinical text, has been central to the discourse on medical privacy since 2006. While de-identification is becoming the global norm for handling medical records, there is a paucity of studies on its application on Chinese clinical text. Without efficient and effective privacy protection algorithms in place, the use of indispensable clinical information would be confined.

OBJECTIVES

We aimed to (i) describe the current process for PHI in China, (ii) propose a machine learning based approach to identify PHI in Chinese clinical text, and (iii) validate the effectiveness of the machine learning algorithm for de-identification in Chinese clinical text.

METHODS

Based on 14,719 discharge summaries from regional health centers in Ya'an City, Sichuan province, China, we built a conditional random fields (CRF) model to identify PHI in clinical text, and then used the regular expressions to optimize the recognition results of the PHI categories with fewer samples.

RESULTS

We constructed a Chinese clinical text corpus with PHI tags through substantial manual annotation, wherein the descriptive statistics of PHI manifested its wide range and diverse categories. The evaluation showed with a high F-measure of 0.9878 that our CRF-based model had a good performance for identifying PHI in Chinese clinical text.

CONCLUSION

The rapid adoption of EHR in the health sector has created an urgent need for tools that can parse patient specific information from Chinese clinical text. Our application of CRF algorithms for de-identification has shown the potential to meet this need by offering a highly accurate and flexible solution to analyzing Chinese clinical text.