A method and knowledge base for automated inference of patient problems from structured data in an electronic medical record

Background

Accurate knowledge of a patient''s medical problems is critical for clinical decision making, quality measurement, research, billing and clinical decision support. Common structured sources of problem information include the patient problem list and billing data; however, these sources are often inaccurate or incomplete.

Objective

To develop and validate methods of automatically inferring patient problems from clinical and billing data, and to provide a knowledge base for inferring problems.

Study design and methods

We identified 17 target conditions and designed and validated a set of rules for identifying patient problems based on medications, laboratory results, billing codes, and vital signs. A panel of physicians provided input on a preliminary set of rules. Based on this input, we tested candidate rules on a sample of 100 000 patient records to assess their performance compared to gold standard manual chart review. The physician panel selected a final rule for each condition, which was validated on an independent sample of 100 000 records to assess its accuracy.

Results

Seventeen rules were developed for inferring patient problems. Analysis using a validation set of 100 000 randomly selected patients showed high sensitivity (range: 62.8–100.0%) and positive predictive value (range: 79.8–99.6%) for most rules. Overall, the inference rules performed better than using either the problem list or billing data alone.

Conclusion

We developed and validated a set of rules for inferring patient problems. These rules have a variety of applications, including clinical decision support, care improvement, augmentation of the problem list, and identification of patients for research cohorts.     

A method linking statistics and knowledge engineering for making medical consulting systems

There are two methods of making medical consulting systems: the statistical method and the knowledge engineering method. Since both of these methods seem to be very different from each other, they have been recognized and applied separately. We contend, however, that a combination of statistics and knowledge engineering is a more effective and suitable way to create a medical consulting system than is the use of either method alone. In order to justify this contention, we created a medical consulting system, AUTSVR-V1.1, which detects auditory slow vertex responses (SVR) through observing and identifying background activities of the electroencephalogram (EEG) automatically during measurement of SVRs for the purpose of objective electric response audiometry (ERA), and compared it with AUTSVR-V1.0, which depends on statistics only.     

融合多维特征的医学知识图谱分步实体对齐方法

目的：提出一种融合多维特征的医学知识图谱分步实体对齐方法,从电子病历和网络资源中抽取垂体瘤相关疾病、症状数据,进行实证研究。方法：首先进行尾实体对齐,通过训练Word2Vec和BERT模型获得实体的语义特征,使用三元组训练翻译模型得到实体结构特征,利用Jaccard相似度计算字符特征,利用分类模型进行特征学习和预测;然后进行头实体对齐,利用实体的属性相似性和结构相似性构建头实体对齐模型。结果：尾实体对齐模型的F1值为99.58％,头实体对齐模型的F1值为97.32％,说明所选择的特征可以很好地表示实体,模型具有良好的对齐效果。结论：目前关于医学知识图谱的实体对齐模型研究仍处于起步阶段,融合多维特征的医学知识图谱分步实体对齐方法是对现有医学知识图谱构建方法的重要补充。     

精准医学知识库的构建

根据“精准医学本体和语义表示标准”,构建了“精准医学知识库”及“精准医学知识库管理与共享平台”。该精准医学知识库体系具有标准规范、信息全面、开放共享、用户友好以及动态更新等特点,将全面支撑精准医学基础研究和临床应用,填补了国内精准医学知识库领域的空白。     

关于医学知识组织与医学知识服务的再思考

针对传统知识组织体系缺乏语义关系描述,影响数据转换、信息检索和知识发现等问题,探讨语义网络、语义Web技术在医学知识组织方面的应用前景,提出基于语义Web的医学知识组织体系建设是我国医学知识服务的发展趋势。     

医学知识转移研究体系分析

综合使用多种数据库检索出2005-2015年近10年的医学知识转移研究相关文章,采用系统综述的方法梳理分析目前医学知识转移相关研究的层次、主体、内容,探讨该领域相关研究理论体系。结果表明,医学知识转移研究层次主要为个人、团体、组织、联盟等;研究主体主要为医生、护理人员、医疗工作者与非医疗工作者、患者以及管理者、教育者等;研究内容主要包括影响因素和实现机制等。国内外该领域研究存在一定差异,总的来说都有一定的局限性,对理论体系完善和实践探索具有重要意义。     

一流的临床技能培训中心是医学生进行早期临床实践的重要基地

汕头大学医学院于 2 0 0 2年投入使用的临床技能培训中心 ,配有标准病房、标准诊室、全自动模拟人及相应设施 ,为医学生创造了一个模拟训练平台 ,强化了对医学生早期临床技能、临床思维能力的培养 ,并有利于把临床实践贯穿于人才培养的全过程。同时 ,该中心也是评估学生学习效果的重要场所。     

骨肿瘤辅助诊断系统临床知识库的建立

目的：建立骨肿瘤辅助诊断系统的知识库。方法：通过对骨肿瘤知识的归纳总结，结合模糊理论和数据库技术，采用知识的混合表示法。结果：建立起符合临床医生诊断过程的知识库原型。结论：提出了一种用数据库技术＋逻辑程序设计技术完成知识混合表示的方法。     

大脑CT图像三维重建的快速内插技术

基于相关弧概念研究了一种医学三维图像内插算法，计算速度快，适用范围广。     

A neuro-symbolic method for understanding free-text medical evidence

ObjectiveWe introduce Medical evidence Dependency (MD)–informed attention, a novel neuro-symbolic model for understanding free-text clinical trial publications with generalizability and interpretability.Materials and MethodsWe trained one head in the multi-head self-attention model to attend to the Medical evidence Ddependency (MD) and to pass linguistic and domain knowledge on to later layers (MD informed). This MD-informed attention model was integrated into BioBERT and tested on 2 public machine reading comprehension benchmarks for clinical trial publications: Evidence Inference 2.0 and PubMedQA. We also curated a small set of recently published articles reporting randomized controlled trials on COVID-19 (coronavirus disease 2019) following the Evidence Inference 2.0 guidelines to evaluate the model’s robustness to unseen data. ResultsThe integration of MD-informed attention head improves BioBERT substantially in both benchmark tasks—as large as an increase of +30% in the F1 score—and achieves the new state-of-the-art performance on the Evidence Inference 2.0. It achieves 84% and 82% in overall accuracy and F1 score, respectively, on the unseen COVID-19 data.Conclusions MD-informed attention empowers neural reading comprehension models with interpretability and generalizability via reusable domain knowledge. Its compositionality can benefit any transformer-based architecture for machine reading comprehension of free-text medical evidence.     

建立肝病结构化电子病程记录的思路及方法

结合电子病程记录在实际应用中的一些问题,如“克隆”病历和临床科研数据库信息不便于数据挖掘等,新开发了“结构化病程记录”模块,针对电子病历中存在的问题,提出相关的解决方案和对策,旨在推动电子病历的进一步发展,以最终提高临床医疗质量和效率。     

TOPSIS法评价住院医师规范化培训基地建设质量

目的  对新疆某三甲医院住院医师规范化培训基地中15个临床专业基地（科室）进行综合评价,了解目前各另临床专业基地（科室）的现况,为基地医院规范化培训工作的开展提供有意义的改进对策与建议。 方法  采用TOPSIS法对新疆某三甲医院住院医师规范化培训基地中15个临床专业基地（科室）进行综合评价。结果  对TOPSIS评价得分进行排序,15个临床专业基地（科室）当中排在前3位的专业基地为外科、内科和、急诊科,排在后3位的专业基地为全科、放射肿瘤科及康复科。结论  住院医师规范化培训基地建设质量受多因素、多指标的影响,TOPSIS法对样本资料无特殊要求,使用灵活简单,适用性较强,在评价住院医师规范化培训基地建设质量中有着很大的应用价值。

     

创新网络教学模式打造医学本科教学课程中心

本科教学课程中心是近几年国内外重点大学教学改革和发展中创建的一种新的网络教学模式.它具有基础性强、受益面广,集网络化、数字化、资源应用一体化等特点.文章介绍了国内外"本科教学课程中心"建设的进展和吉林大学"医学本科教学课程中心"的建设及建设过程中的一些做法和体会.     

Data base design for natural language medical data

The natural language of clinical reporting exhibits the properties of a sublanguage, having a grammar and vocabulary greatly restricted in comparison to the language as a whole. This paper presents a CODASYL-type (network) data base schema for natural language medical records based on the structures and relationships identified in such material through computerized language processing. While the schema described is special to the medical sublanguage, the methods of analysis and of schema design are applicable to natural language material in other subject areas.     

The requirement for bioscience knowledge in medical education

The recent 100-year anniversary of the Flexner review and the release of the Australian Medical Education Study have stimulated vigorous debate about the role of bioscience knowledge in medical education. Two critical questions define debate in this area: does bioscience learning assist in educating medical students to become competent doctors, and, if so, what are the most effective teaching and learning methods to facilitate this outcome? There is tacit acceptance that specific bioscience knowledge is critical for the development of clinical expertise; however, there are few empirical data to support this notion. Two differing theories have been proposed to describe the role of bioscience learning in the development of clinical reasoning skills - the "two-worlds" model and the "encapsulation" model. A series of studies provides support for the encapsulation model. Some medical programs are now integrating bioscience teaching into the clinical years of the course. Evidence of the effectiveness of this on outcomes, such as improved clinical reasoning, is inconclusive.     

知识经济对医学生的创新要求

知识经济和医学的发展呼唤医学创新人才,医学生必须适时应变,转变学习观念与学习方式,全面提高自身素质,使自己成为具有综合素质的创新人才,以适应知识经济发展的要求.     

创设音乐背景培养医学高职学生综合能力的研究

音乐教育能够提高人的素质，开发人的智力，改善人的精神生活质量。医学基础课程的教学相对于医学临床课程教学缺乏灵活性，生动性，因此，在医学基础教学中，创设音乐背景，培养学生综合能力，其研究结果对于今后的教育具有启发意义。     

老年腹壁巨大切口疝修补方法的改进

我科2000年4月～2003年12月共收治老年腹壁巨大切口疝26例,均采用改进的无张力疝修补方法,临床效果满意.现报告如下: