Data Masking for Chinese Electronic Medical Records with Named Entity Recognition

With the rapid development of information technology,the electronifi-cation of medical records has gradually become a trend.In China,the population base is huge and the supporting medical institutions are numerous,so this reality drives the conversion of paper medical records to electronic medical records.Electronic medical records are the basis for establishing a smart hospital and an important guarantee for achieving medical intelligence,and the massive amount of electronic medical record data is also an important data set for conducting research in the medical field.However,electronic medical records contain a large amount of private patient information,which must be desensitized before they are used as open resources.Therefore,to solve the above problems,data masking for Chinese electronic medical records with named entity recognition is proposed in this paper.Firstly,the text is vectorized to satisfy the required format of the model input.Secondly,since the input sentences may have a long or short length and the relationship between sentences in context is not negligible.To this end,a neural network model for named entity recognition based on bidirectional long short-term memory(BiLSTM)with conditional random fields(CRF)is constructed.Finally,the data masking operation is performed based on the named entity recog-nition results,mainly using regular expression filtering encryption and principal component analysis(PCA)word vector compression and replacement.In addi-tion,comparison experiments with the hidden markov model(HMM)model,LSTM-CRF model,and BiLSTM model are conducted in this paper.The experi-mental results show that the method used in this paper achieves 92.72%Accuracy,92.30%Recall,and 92.51%F1_score,which has higher accuracy compared with other models.

Deletion and Recovery Scheme of Electronic Health Records Based onMedical Certificate Blockchain

The trusted sharing of Electronic Health Records(EHRs)can realize the efficient use of medical data resources.Generally speaking,EHRs are widely used in blockchain-based medical data platforms.EHRs are valuable private assets of patients,and the ownership belongs to patients.While recent research has shown that patients can freely and effectively delete the EHRs stored in hospitals,it does not address the challenge of record sharing when patients revisit doctors.In order to solve this problem,this paper proposes a deletion and recovery scheme of EHRs based on Medical Certificate Blockchain.This paper uses cross-chain technology to connect the Medical Certificate Blockchain and the Hospital Blockchain to real-ize the recovery of deleted EHRs.At the same time,this paper uses the Medical Certificate Blockchain and the InterPlanetary File System(IPFS)to store Personal Health Records,which are generated by patients visiting different medical institutions.In addition,this paper also combines digital watermarking technology to ensure the authenticity of the restored electronic medical records.Under the combined effect of blockchain technology and digital watermarking,our proposal will not be affected by any other rights throughout the process.System analysis and security analysis illustrate the completeness and feasibility of the scheme.

Medical Knowledge Extraction and Analysis from Electronic Medical Records Using Deep Learning

Objectives Medical knowledge extraction (MKE) plays a key role in natural language processing (NLP) research in electronic medical records (EMR),which are the important digital carriers for recording medical activities of patients.Named entity recognition (NER) and medical relation extraction (MRE) are two basic tasks of MKE.This study aims to improve the recognition accuracy of these two tasks by exploring deep learning methods.Methods This study discussed and built two application scenes of bidirectional long short-term memory combined conditional random field (BiLSTM-CRF) model for NER and MRE tasks.In the data preprocessing of both tasks,a GloVe word embedding model was used to vectorize words.In the NER task,a sequence labeling strategy was used to classify each word tag by the joint probability distribution through the CRF layer.In the MRE task,the medical entity relation category was predicted by transforming the classification problem of a single entity into a sequence classification problem and linking the feature combinations between entities also through the CRF layer.Results Through the validation on the I2B2 2010 public dataset,the BiLSTM-CRF models built in this study got much better results than the baseline methods in the two tasks,where the F1-measure was up to 0.88 in NER task and 0.78 in MRE task.Moreover,the model converged faster and avoided problems such as overfitting.Conclusion This study proved the good performance of deep learning on medical knowledge extraction.It also verified the feasibility of the BiLSTM-CRF model in different application scenarios,laying the foundation for the subsequent work in the EMR field.

基于Transformer交互指导的医患对话联合信息抽取方法

针对电子病历构建过程中难以捕捉信息抽取任务之间的关联性和医患对话上下文信息的问题,提出了一种基于Transformer交互指导的联合信息抽取方法,称为CT-JIE(collaborative Transformer for joint information extraction)。首先,该方法使用滑动窗口并结合Bi-LSTM获取对话中的历史信息,利用标签感知模块捕捉对话语境中与任务标签相关的信息;其次,通过全局注意力模块提高了模型对于症状实体及其状态的上下文感知能力;最后,通过交互指导模块显式地建模了意图识别、槽位填充与状态识别三个任务之间的交互关系,以捕捉多任务之间的复杂语境和关系。实验表明,该方法在IMCS21和CMDD两个数据集上的性能均优于其他基线模型和消融模型,在处理联合信息抽取任务时具有较强的泛化能力和性能优势。

Effect of Electronic Medical Record Utilization on Depression, Anxiety and Stress among Doctors and Nurses in Johor, Malaysia

Background： The usage of modem technology in healthcare record system is now a must throughout the world. However, many doctors and nurses has been reporting facing numerous challenges and obstacles in the implementation. The aim of the present study is to determine the prevalence of depression, anxiety and stress among doctors and nurses who utilize EMR （electronic medical record） and its associated factor. Methods： A comparative cross-sectional study was conducted ~om January till April 2012 among doctors and nurses in two public tertiary hospitals in Johor in which one of them uses EMR and the other one still using the MMR （manual medical record） system. Data was collected using self-administered validated Malay version of DASS-21 （Depression, Anxiety, and Stress Scales-21） items questionnaire. It comprises of socio-demographic and occupational characteristics. Findings： There were 130 respondents with a response rate of 91% for EMR and 123 respondents with a response rate of 86% for MMR. The mean （SD） age of respondents in EMR and MMR groups were 34.7 （9.42） and 29.7 （6.15） respectively. The mean （SD） duration of respondents using EMR was 46.1 （35.83） months. The prevalence of depression, anxiety and stress among respondents using EMR were 6.9%, 25.4% and 12.3%. There were no significant difference between the study groups related to the depression, anxiety and stress scores. In multivariable analysis, the significant factors associated with depression among respondents using EMR was age （OR 1.10, 95% CI 1.02, 1.19）. The significant factors associated with stress among respondents using EMR was marital status （OR 3.33, 95% CI 1.10, 10.09） and borderline significant was computer skill course （OR 2.94, 95% CI 0.98, 8.78）. Conclusion： The prevalence of depression, anxiety and stress of those who uses EMR were within acceptable range. Age, marital status and computer skill are the identified factor associated with the depression and stress level which need to be considered in its implementation.

Maturity Assessment of Hospital Information Systems Based on Electronic Medical Record Adoption Model (EMRAM)— Private Hospital Cases in Iran

Introduction: Today, information technology is considered as an important national development principle in each country which is applied in different fields. Health care as a whole and the hospitals could be regarded as a field and organizations with most remarkable IT applications respectively. Although different benchmarks and frameworks have been developed to assess different aspects of Hospital Information Systems (HISs) by various researchers, there is not any suitable reference model yet to benchmark HIS in the world. Electronic Medical Record Adoption Model (EMRAM) has been currently presented and is globally well-known to benchmark the rate of HIS utilization in the hospitals. Notwithstanding, this model has not been introduced in Iran so far. Methods: This research was carried out based on an applied descriptive method in three private hospitals of Isfahan—one of the most important provinces of Iran—in the year 2015. The purpose of this study was to investigate IT utilization stage in three selected private hospitals. Conclusion: The findings revealed that HIS is not at the center of concern in studied hospitals and is in the first maturity stage in accordance with EMRAM. However, hospital managers are enforced and under the pressure of different beneficiaries including insurance companies to improve their HIS. Therefore, it could be concluded that these types of hospitals are still far away from desirable conditions and need to enhance their IT utilization stage significantly.

Cautionary note:Electronic medical records,a potential disaster in the making?

Concern is expressed that electronic medical records may actually compromise care.Reports are electronically collated with patient charts, but when are they examined? Current electronic transmission of results to patients' electronic medical records do not seem to notify of new information.The unknown time from prescription to patient action and the variable time required for individual test performance seem to mandate that a physician attempting to be conscientious would have to examine all sections of every patient medical record in their practice, every day.That is quite inefficient and error-prone.Electronic medical record still contains what appear to be dangerous "bugs" which compromise our ability to provide the care we believe our patients deserve? I remain unsure that outpatient electronic medical records are "ready for prime time."

A Proposed Layered Architecture to Maintain Privacy Issues in Electronic Medical Records

Securing large amounts of electronic medical records stored in different forms and in many locations, while making availability to authorized users is considered as a great challenge. Maintaining protection and privacy of personal information is a strong motivation in the development of security policies. It is critical for health care organizations to access, analyze, and ensure security policies to meet the challenge and to develop the necessary policies to ensure the security of medical information. The problem, then, is how we can maintain the availability of the electronic medical records and at the same time maintain the privacy of patients’ information. This paper will propose a novel architecture model for the Electronic Medical Record (EMR), in which useful statistical medical records will be available to the interested parties while maintaining the privacy of patients’ information.

Implementing of Electronic Medical Record in Pelvic Floor Ward: A Pilot Study

The electronic medical record is an essential technology tool to improve the quality of care. In present study we reported on the design and feasibility of electronic medical records in Female Pelvic Floor Dysfunction Ward. Our main goal was documentation with the least possible missed data, evidence-based decision making, documented active patient follow up and increasing patient’s satisfaction. The Electronic Registry System of Female Pelvic Floor Dysfunction (Vali e Asr Hospital, Tehran, Iran) was designed in mid 2014 and tested till March 2015. The software description was designed based on previous paper questionnaire used in this ward. The electronic questionnaires were filled in upon hospitalization and thereafter including follow ups. The questionnaire included 10 demographic and 15 main questions. A digital analog scale (1 - 10) in each part quantified the effects of problem on patient’s quality of life and also the effects of interventions as well. Entered information in each step was available for those with defined access. Reporting design was dependent on the needed data. Our supervised data entry was a guarantee to the quality of information with the least errors. Access to all para clinical data made rapid and evidence-based decision making. Patient satisfaction was achieved because of unified approach. The most interesting part was access to evidence-based results and data to be used in research projects. This study showed that EMRs in Female Pelvic Floor Dysfunction Wards could provide valuable information, improve the quality of care and increase patient’s satisfaction.

Endoscopic electronic record:A new approach for improving management of colorectal cancer prevention

Digestive endoscopy is currently the main diagnostic procedure for investigation of the digestive tract when a digestive disease is suspected.The use of computers and electronic medical records for the management of endoscopic data are an important key to improving endoscopy unit efficiency and productivity.This technology supports optimal program operation,monitoring and evaluation colorectal cancer screening.This article is a comprehensive survey of endoscopic electronic medical records and information systems.Computerized clinical records have the capability of identifying patients due for screening and to calculate baseline rates of colorectal cancer screening by patient characteristics and by primary care physician and practice group.This paper describes data flow in the endoscopy unit,the minimum data set of colorectal cancer and key features of endoscopic electronic medical record.In addition,the researchers state standards in different aspects,especially terminology standards and interoperability standards for image and text.

Impact of Bar-Code Medication Administration and Electronic Medication Administration Record System in Clinical Practice for an Effective Medication Administration Process

Clinical innovations are ideations resulting from collective experiences that enhance the “norm” and embrace an avenue for change with an invention. As such, collective data that were suggestive of increased medication errors that compromised patient safety initiated the exploration of methods that could reduce multifactorial human errors. The pursuit for an appropriate system followed with the discovery of barcode medication administration system (BCMA) and electronic medication administration system (e-MAR). Prior to the adoption of BCMA and e-MAR, it was crucial to assess the impact of the new medication administration system and the rate of medication administration errors recorded, specifically those that resulted in harm. The purpose of the study was to evaluate BCMA and e-MAR usage outcomes, clinical practices, policies, and processes impacting nurses administering medications in the clinical environment using BCMA and e-MAR system. Thus, an annotated literature review was conducted prior to the implementation of the innovation which analyzed various studies that elaborated on their study methods, data collection and analysis that deliberated on the advantages and disadvantages of barcode medication administration system. It is evident in the researched journals that increased compliance was observed with appropriate guidance, processes and policies in place. There was also a significant reduction in reported errors. The incorporation of barcode technology with electronic medication administration record (e-MAR) had greatly improved the efficiency of the BCMA system. BCMAs method was one of the proposed solutions to medication administration errors and to enhance patient safety measures. As such, the innovation could significantly reduce medication error resulting from intrinsic and extrinsic factors. This paper will further elaborate on the advantages and disadvantages of BCMA and e-MAR, the strategies assumed in the development of BCMA and e-MAR system and its implementation process by identifying and overcoming potential challenges that may arise.

Integrating Electronic Systems for Requesting Clinical Laboratory Test into Digital Clinical Records: Design and Implementation

Clinical laboratory tests are basic elements that support healthcare tasks such as disease detection, diagnosis and monitoring of response to treatments. Current laboratory information systems focus on the patient database, tests and results, with multiple modules available, connecting with the various analytical systems or work areas. However laboratory information systems functioned as “islands of information”, because their design was fundamentally inward-looking and disconnected from other healthcare computer applications. Actually, the Electronic Health Register (EHR) is considered by clinicians as a tool with great potential healthcare benefits. The EHR, in the sense of a unique and complete record of a patient’s healthcare and state of health, regardless of the healthcare level used, is a real attempt to eliminate these “islands of information” and need modules to act as “bridges” with the laboratory information systems. This type of module, which in generic terms may be referred to as a laboratory test request module, has become an essential feature of the EHR. These modules need to use a laboratory coding system as a common language for exchanging information, ensuring that tests and results are unequivocally identified. The development of the laboratory test request module requires the commitment of professionals and political authorities, being necessary time for their design and an adequate pilot phase. The laboratory professionals have to assume a leadership role in the whole process of design, development and implementation of these modules, integrating in the equipment of information technologies of healthcare providers. In our manuscript we review the elements that may prove electronic systems for requesting clinical laboratory test into digital clinical records and the key elements to move from theory to practice.

Setting up a Customized Electronic Health Record System Fit for Internal Medicine in Dakar, Senegal

Objective: Describe the design and implementation of an electronic medical record—E-INTMED—customized for Internal Medicine in Dakar, Senegal. Methodology: This study was carried out in a public teaching hospital in Dakar Senegal. It entailed collaboration between physicians specialized in various fields in Internal Medicine and Computer Scientists to carry out the compilation of data and their electronic transcription to produce a prototype which met users’ needs. Results: E-INTMED software is structured around several hierarchical tables allowing users to register and store all relevant patients’ information. E-INTMED structures patient’s data to provide a clear overview of their medical history and users’ activity performance. E-INTMED makes medical users’ life so much easier. Users can generate and send letters and prescriptions quickly and efficiently using the customized templates which they can modify or create new ones. In addition to these capabilities, all of the features expected in an Internal Medicine EHR are handled by E-INTMED, such as lab orders and results, mechanisms for continuity of care, embedding and access to images and documents, and so much more. E-INTMED provides medical students with a number of educational, practical and administrative advantages. Conclusion: Computerization of medical records has become a necessity today. Crossing the line to Electronic medical records could help to improve medical practice and medical training.

Development of Medical Informatization in the Era of Big Data

The purpose of this paper is to discuss the development of medical informatization in the era of big data.Through literature review and theoretical analysis,the development of medical informatization in the era of big data is deeply discussed.The results show that medical informatization has developed rapidly in the era of big data,and its role in clinical decision-making,scientific research,teaching,and management has become increasingly prominent.The development of medical informatization in the era of big data has important purposes and methods,which can produce important results and conclusions and provide strong support for the development of the medical field.

基于后结构化技术的临床病种库系统设计与应用

目的:为解决传统临床病种库系统存在的依赖大量人工判断、缺乏辅助标注、电子病历数据可用性差等问题,设计一种基于后结构化技术的临床病种库系统。方法:先通过I2B2标准以及双向长短期记忆网络(bi-directional long short-term memory,BiLSTM)模型构建实体识别模型,形成病历模板库,然后组合病历模板库形成关系模板,抽取复杂的医学实体,实现电子病历的后结构化。之后,基于电子病历后结构化技术构建包括病历结构化、结构化评估、数据标注、常规功能和系统管理5个模块的临床病种库系统。结果:该系统可以将电子病历文本转化为结构化语言,提供更精细化的数据要素提取、更智能的结构化服务,提高了临床和科研工作的效率。结论:该系统提高了临床病种的数据可用性,减轻了用户数据加工的工作强度,保证了数据应用的高质量,为医学研究、临床辅助决策打下了坚实的基础。

老年慢性心力衰竭住院患者中重度心力衰竭发生风险预测模型的构建

目的基于电子病历的方式,构建慢性心力衰竭(CHF)患者中重度心力衰竭发生风险预测模型,并验证该模型的预测效果。方法2019年1月-2020年12月,选择上海市某三级甲等医院心血管临床医学中心诊断为CHF的299例患者为研究对象,采用Logistic回归建立CHF患者中重度心力衰竭发生风险预测模型,采用Hosmer-Lemeshow和受试者操作特征曲线分别检验模型的拟合优度及预测效果,并纳入100例患者对模型进行验证。结果心超(运动幅度降低)(OR=5.109)、双下肢水肿(OR=3.947)、心房颤动(OR=2.772)、血肌酐升高(OR=1.015)是CHF患者发生中重度心力衰竭的危险因素;血清白蛋白升高(OR=0.939)是保护因素;Hosmer-Lemeshow检验P=0.127,受试者操作特征曲线下面积为0.858,约登指数为0.528,最佳临界值为0.805,灵敏度为0.731,特异度为0.797,实际应用的正确率为77.00%。结论本课题建立的CHF患者中重度心力衰竭发生风险的预测模型效果良好,有利于以后早期识别中重度心力衰竭发生风险电子系统报警提示程序的更新提供依据。

基于字形特征的血管外科命名实体识别

电子病历(EMR)作为医疗信息化建设的核心,蕴含着众多有价值的医疗实体,对电子病历进行命名实体识别有助于推进医学研究。为解决血管外科电子病历研究数据匮乏、实体复杂识别困难等问题,基于某三甲医院血管外科的真实临床数据,构建一个小规模的专科数据集作为实验数据集,并提出一种基于字形特征的命名实体识别模型。首先,采用掩码校正的来自Transformer的双向编码器表示(MacBERT)生成动态字向量,引入汉字四角码与汉字五笔两个维度的字形信息;然后,将文本表示传入双向门控循环单元(BiGRU)与门控空洞卷积神经网络(DGCNN)进行特征提取,并对输出结果进行拼接;最后,通过多头自注意力机制捕捉序列内部元素间的关系,利用条件随机场(CRF)进行标签解码。实验结果表明,所提模型在自建血管外科数据集上的精确率、召回率、F1值分别为96.45%、97.77%、97.10%,均优于对比模型,具有更好的实体识别性能。

基于电子病历六级标准建设门诊合理用药闭环管理模式

目的:基于电子病历系统应用水平六级标准创建该院门诊合理用药闭环管理模式,旨在为门诊患者合理用药保驾护航,为智慧药学建设提供参考。方法:利用人工智能技术对医师开方、药师审核、药品调剂、处方点评等门诊合理用药各环节进行管理,建立符合国家电子病历六级标准的闭环体系。同时,回顾性分析该院闭环管理前(2023年3—5月)、闭环管理前后(2023年6—8月)门诊处方用药不合理率。结果:应用门诊合理用药闭环管理模式后,门诊处方用药不合理率为3.56%(40723/1145056),较管理前的4.57%(52681/1153154)降低了1.01%,差异有统计学意义(P<0.01);除遴选药品不适宜外,其他类型不适宜用药处方数均较管理前显著减少;门诊次均药品费用为146.20元,较管理前的158.35元减少了7.67%,有效改善了公立医院绩效考核指标。结论:该院建设的门诊合理用药闭环管理体系满足国家电子病历六级评级要求,能够规范医疗人员的工作流程,减少门诊不合理用药。

基于中文电子病历知识图谱的实体对齐研究

医疗知识图谱中知识重叠和互补的现象普遍存在,利用实体对齐进行医疗知识图谱融合成为迫切需要。然而据作者调研,目前医疗领域中的实体对齐尚没有一个完整的处理方案。因此该文提出了一个规范的基于中文电子病历的医疗知识图谱实体对齐流程,为医疗领域的实体对齐提供了一种可行的方案。同时针对基于中文电子病历医疗知识图谱之间结构异构性的特点,该文设计了一个双视角并行图神经网络(DuPNet)模型用于解决医疗领域实体对齐,并取得较好的效果。

基于平行交互注意力网络的中文电子病历实体及关系联合抽取

基于电子病历构建医学知识图谱对医疗技术的发展具有重要意义,实体和关系抽取是构建知识图谱的关键技术。该文针对目前实体关系联合抽取中存在的特征交互不充分的问题,提出了一种平行交互注意力网络(PIAN)以充分挖掘实体与关系的相关性,在多个标准的医学和通用数据集上取得最优结果;当前中文医学实体及关系标注数据集较少,该文基于中文电子病历构建了实体和关系抽取数据集(CEMRIE),与医学专家共同制定了语料标注规范,并基于该文所提出的模型实验得出基准结果。