Traditional Chinese Medicine (TCM) Domain Ontology: Current Status and Rethinking for the Future Development

The past twenty years have seen the increasingly important role of ontology in traditional Chinese medicine (TCM). However, the development of TCM ontology faces many challenges. Since the epistemologies dramatically differ between TCM and contemporary biomedicine, it is hard to apply the existing top-level ontology mechanically. “Data silos” are widely present in the currently available terminology standards, term sets, and ontologies. The formal representation of ontology needs to be further improved in TCM. Therefore, we propose a unified basic semantic framework of TCM based on in-depth theoretical research on the existing top-level ontology and a re-study of important concepts in TCM. Under such a framework, ontologies in TCM subdomains should be built collaboratively and be represented formally in a common format. Besides, extensive cooperation should be encouraged by establishing ontology research communities to promote ontology peer review and reuse.     

Getting the foot out of the pelvis: modeling problems affecting use of SNOMED CT hierarchies in practical applications

Objectives

(a) To determine the extent and range of errors and issues in the Systematised Nomenclature of Medicine – Clinical Terms (SNOMED CT) hierarchies as they affect two practical projects. (b) To determine the origin of issues raised and propose methods to address them.

Methods

The hierarchies for concepts in the Core Problem List Subset published by the Unified Medical Language System were examined for their appropriateness in two applications. Anomalies were traced to their source to determine whether they were simple local errors, systematic inferences propagated by SNOMED''s classification process, or the result of problems with SNOMED''s schemas. Conclusions were confirmed by showing that altering the root cause and reclassifying had the intended effects, and not others.

Main results

Major problems were encountered, involving concepts central to medicine including myocardial infarction, diabetes, and hypertension. Most of the issues raised were systematic. Some exposed fundamental errors in SNOMED''s schemas, particularly with regards to anatomy. In many cases, the root cause could only be identified and corrected with the aid of a classifier.

Limitations

This is a preliminary ‘experiment of opportunity.’ The results are not exhaustive; nor is consensus on all points definitive.

Conclusions

The SNOMED CT hierarchies cannot be relied upon in their present state in our applications. However, systematic quality assurance and correction are possible and practical but require sound techniques analogous to software engineering and combined lexical and semantic techniques. Until this is done, anyone using SNOMED codes should exercise caution. Errors in the hierarchies, or attempts to compensate for them, are likely to compromise interoperability and meaningful use.     

Community annotation experiment for ground truth generation for the i2b2 medication challenge

Objective

Within the context of the Third i2b2 Workshop on Natural Language Processing Challenges for Clinical Records, the authors (also referred to as ‘the i2b2 medication challenge team’ or ‘the i2b2 team’ for short) organized a community annotation experiment.

Design

For this experiment, the authors released annotation guidelines and a small set of annotated discharge summaries. They asked the participants of the Third i2b2 Workshop to annotate 10 discharge summaries per person; each discharge summary was annotated by two annotators from two different teams, and a third annotator from a third team resolved disagreements.

Measurements

In order to evaluate the reliability of the annotations thus produced, the authors measured community inter-annotator agreement and compared it with the inter-annotator agreement of expert annotators when both the community and the expert annotators generated ground truth based on pooled system outputs. For this purpose, the pool consisted of the three most densely populated automatic annotations of each record. The authors also compared the community inter-annotator agreement with expert inter-annotator agreement when the experts annotated raw records without using the pool. Finally, they measured the quality of the community ground truth by comparing it with the expert ground truth.

Results and conclusions

The authors found that the community annotators achieved comparable inter-annotator agreement to expert annotators, regardless of whether the experts annotated from the pool. Furthermore, the ground truth generated by the community obtained F-measures above 0.90 against the ground truth of the experts, indicating the value of the community as a source of high-quality ground truth even on intricate and domain-specific annotation tasks.     

Auditing the Semantic Completeness of SNOMED CT Using Formal Concept Analysis

Objective

This study sought to develop and evaluate an approach for auditing the semantic completeness of the SNOMED CT contents using a formal concept analysis (FCA)-based model.

Design

We developed a model for formalizing the normal forms of SNOMED CT expressions using FCA. Anonymous nodes, identified through the analyses, were retrieved from the model for evaluation. Two quasi-Poisson regression models were developed to test whether anonymous nodes can evaluate the semantic completeness of SNOMED CT contents (Model 1), and for testing whether such completeness differs between 2 clinical domains (Model 2). The data were randomly sampled from all the contexts that could be formed in the 2 largest domains: Procedure and Clinical Finding. Case studies (n = 4) were performed on randomly selected anonymous node samples for validation.

Measurements

In Model 1, the outcome variable is the number of fully defined concepts within a context, while the explanatory variables are the number of lattice nodes and the number of anonymous nodes. In Model 2, the outcome variable is the number of anonymous nodes and the explanatory variables are the number of lattice nodes and a binary category for domain (Procedure/Clinical Finding).

Results

A total of 5,450 contexts from the 2 domains were collected for analyses. Our findings revealed that the number of anonymous nodes had a significant negative correlation with the number of fully defined concepts within a context (p < 0.001). Further, the Clinical Finding domain had fewer anonymous nodes than the Procedure domain (p < 0.001). Case studies demonstrated that the anonymous nodes are an effective index for auditing SNOMED CT.

Conclusion

The anonymous nodes retrieved from FCA-based analyses are a candidate proxy for the semantic completeness of the SNOMED CT contents. Our novel FCA-based approach can be useful for auditing the semantic completeness of SNOMED CT contents, or any large ontology, within or across domains.     

Migrating existing clinical content from ICD-9 to SNOMED

Objective

To identify challenges in mapping internal International Classification of Disease, 9th edition, Clinical Modification (ICD-9-CM) encoded legacy data to Systematic Nomenclature of Medicine (SNOMED), using SNOMED-prescribed compositional approaches where appropriate, and to explore the mapping coverage provided by the US National Library of Medicine (NLM)''s SNOMED clinical core subset.

Design

This study selected ICD-CM codes that occurred at least 100 times in the organization''s problem list or diagnosis data in 2008. After eliminating codes whose exact mappings were already available in UMLS, the remainder were mapped manually with software assistance.

Results

Of the 2194 codes, 784 (35.7%) required manual mapping. 435 of these represented concept types documented in SNOMED as deprecated: these included the qualifying phrases such as ‘not elsewhere classified’. A third of the codes were composite, requiring multiple SNOMED code to map. Representing 45 composite concepts required introducing disjunction (‘or’) or set-difference (‘without’) operators, which are not currently defined in SNOMED. Only 47% of the concepts required for composition were present in the clinical core subset. Search of SNOMED for the correct concepts often required extensive application of knowledge of both English and medical synonymy.

Conclusion

Strategies to deal with legacy ICD data must address the issue of codes created by non-taxonomist users. The NLM core subset possibly needs augmentation with concepts from certain SNOMED hierarchies, notably qualifiers, body structures, substances/products and organisms. Concept-matching software needs to utilize query expansion strategies, but these may be effective in production settings only if a large but non-redundant SNOMED subset that minimizes the proportion of extensively pre-coordinated concepts is also available.     

Using SNOMED CT to Represent Two Interface Terminologies

Objective

Interface terminologies are designed to support interactions between humans and structured medical information. In particular, many interface terminologies have been developed for structured computer based documentation systems. Experts and policy-makers have recommended that interface terminologies be mapped to reference terminologies. The goal of the current study was to evaluate how well the reference terminology SNOMED CT could map to and represent two interface terminologies, MEDCIN and the Categorical Health Information Structured Lexicon (CHISL).

Design

Automated mappings between SNOMED CT and 500 terms from each of the two interface terminologies were evaluated by human reviewers, who also searched SNOMED CT to identify better mappings when this was judged to be necessary. Reviewers judged whether they believed the interface terms to be clinically appropriate, whether the terms were covered by SNOMED CT concepts and whether the terms' implied semantic structure could be represented by SNOMED CT.

Measurements

Outcomes included concept coverage by SNOMED CT for study terms and their implied semantics. Agreement statistics and compositionality measures were calculated.

Results

The SNOMED CT terminology contained concepts to represent 92.4% of MEDCIN and 95.9% of CHISL terms. Semantic structures implied by study terms were less well covered, with some complex compositional expressions requiring semantics not present in SNOMED CT. Among sampled terms, those from MEDCIN were more complex than those from CHISL, containing an average 3.8 versus 1.8 atomic concepts respectively, p<0.001.

Conclusion

Our findings support using SNOMED CT to provide standardized representations of information created using these two terminologies, but suggest that enriching SNOMED CT semantics would improve representation of the external terms.     

2018年版SNOMED CT国际药物模型体系简介

目的对新版医学系统命名法-临床术语(Systematized Nomenclature of Medicine-Clinical Terms,SNOMEDCT)中的国际药物模型进行介绍,为我国药物模型的构建提供参考。方法对2018年7月更新的SNOMEDCT国际药物模型的设计理念、药物分类体系进行介绍,并以含氨氯地平和阿托伐他汀的口服药片为例,将其在模型中的结构进行演示。结果新版国际药物模型中,提供了更加完整的临床药物信息,包括药物充分和完整的描述,新增和调整了强度、强度物质基础、单位属性,使得产品层次结构可以完全由描述逻辑分类器推算出来。结论 SNOMEDCT国际药物模型将药物进行汇总,便于相关行业进行查询、参考,对于我国药物模型的构建有很大启发,对公共突发事件、药物警戒、药物研发等有一定帮助。     

Research and applications: Semantic analysis of SNOMED CT for a post-coordinated database of histopathology findings

Objective

This research investigated the use of SNOMED CT to represent diagnostic tissue morphologies and notable tissue architectures typically found within a pathologist''s microscopic examination report to identify gaps in expressivity of SNOMED CT for use in anatomic pathology.

Methods

24 breast biopsy cases were reviewed by two board certified surgical pathologists who independently described the diagnostically important tissue architectures and diagnostic morphologies observed by microscopic examination. In addition, diagnostic comments and details were extracted from the original diagnostic pathology report. 95 unique clinical statements were extracted from 13 malignant and 11 benign breast needle biopsy cases.

Results

75% of the inventoried diagnostic terms and statements could be represented by valid SNOMED CT expressions. The expressions included one pre-coordinated expression and 73 post-coordinated expressions. No valid SNOMED CT expressions could be identified or developed to unambiguously assert the meaning of 21 statements (ie, 25% of inventoried clinical statements). Evaluation of the findings indicated that SNOMED CT lacked sufficient definitional expressions or the SNOMED CT concept model prohibited use of certain defined concepts needed to describe the numerous, diagnostically important tissue architectures and morphologic changes found within a surgical pathology microscopic examination.

Conclusions

Because information gathered during microscopic histopathology examination provides the basis of pathology diagnoses, additional concept definitions for tissue morphometries and modifications to the SNOMED CT concept model are needed and suggested to represent detailed histopathologic findings in computable fashion for purposes of patient information exchange and research.

Trial registration number

UNMC Institutional Review Board ID# 342-11-EP.     

Use of SNOMED CT to Represent Clinical Research Data: A Semantic Characterization of Data Items on Case Report Forms in Vasculitis Research

ObjectiveTo estimate the coverage provided by SNOMED CT for clinical research concepts represented by the items on case report forms (CRFs), as well as the semantic nature of those concepts relevant to post-coordination methods.DesignConvenience samples from CRFs developed by rheumatologists conducting several longitudinal, observational studies of vasculitis were selected. A total of 17 CRFs were used as the basis of analysis for this study, from which a total set of 616 (unique) items were identified. Each unique data item was classified as either a clinical finding or procedure. The items were coded by the presence and nature of SNOMED CT coverage and classified into semantic types by 2 coders.MeasurementsBasic frequency analysis was conducted to determine levels of coverage provided by SNOMED CT. Estimates of coverage by various semantic characterizations were estimated.ResultsMost of the core clinical concepts (88%) from these clinical research data items were covered by SNOMED CT; however, far fewer of the concepts were fully covered (that is, where all aspects of the CRF item could be represented completely without post-coordination; 23%). In addition, a large majority of the concepts (83%) required post-coordination, either to clarify context (e.g., time) or to better capture complex clinical concepts (e.g., disease-related findings). For just over one third of the sampled CRF data items, both types of post-coordination were necessary to fully represent the meaning of the item.ConclusionSNOMED CT appears well-suited for representing a variety of clinical concepts, yet is less suited for representing the full amount of information collected on CRFs.     

基于语义的区域医疗信息集成方法研究

区域医疗信息共享能有效促进区域内医学信息平台之间数据的有效互通,提高医护人员的工作效率,提升医疗质量。但由于区域医疗的业务内容繁多,标准和规范复杂,同时涉及的运行机构多,严重限制了区域医疗信息系统之间的信息共享。针对这一问题,引入语义网技术,提出基于物理层、语义层和应用层三层架构模型的区域医疗信息集成框架,采用混合本体方法将分散的数据源发布成关联数据,构建一张计算机能理解的语义数据网络。通过局部本体和上层本体的建立,在不改变原有数据结构的条件下实现区域异构系统之间的无缝连接,进而达到为医护人员、患者等随时随地提供个性化的医疗保健服务目的。     

SNOMED CT与OpenEHR的整合探究

详细介绍SNOMED CT与OpenEHR的发展历史、主要内容、主要架构,通过数据类型转换、原型中的临床术语与SNOMED CT的映射、候选术语集等方法进行SNOMED CT与OpenEHR的整合,从而使原型中的术语更加规范,也为互操作提供可能。     

Reference Standards, Judges, and Comparison Subjects: Roles for Experts in Evaluating System Performance

Medical informatics systems are often designed to perform at the level of human experts. Evaluation of the performance of these systems is often constrained by lack of reference standards, either because the appropriate response is not known or because no simple appropriate response exists. Even when performance can be assessed, it is not always clear whether the performance is sufficient or reasonable. These challenges can be addressed if an evaluator enlists the help of clinical domain experts. 1) The experts can carry out the same tasks as the system, and then their responses can be combined to generate a reference standard. 2)The experts can judge the appropriateness of system output directly. 3) The experts can serve as comparison subjects with which the system can be compared. These are separate roles that have different implications for study design, metrics, and issues of reliability and validity. Diagrams help delineate the roles of experts in complex study designs.Medical informatics systems are often designed to carry out complex tasks and to perform at the level of human experts. For example, diagnostic systems use clinical evidence, such as admission history, clinical signs, and diagnostic results, to produce probabilities of disease or lists of diagnoses. Therapeutic systems suggest interventions tailored to patients. Information retrieval systems produce lists of documents that are relevant to some topic. Image processing systems detect features in a digital image.Evaluating the function of these systems can be difficult.¹ Determining the appropriate responses that a system should have produced, deciding whether the system output matches an appropriate response, and even deciding whether a given level of performance is good enough are all challenges. Clinical domain experts have frequently been enlisted to address these challenges. In this paper, we review the many designs that have incorporated human experts into system evaluation, enumerate the roles that experts may play in evaluation, and provide a framework for describing designs. We draw largely on examples from clinical informatics and from information retrieval, but the framework and issues are more broadly applicable across medical informatics.     

糖尿病领域本体构建与语义推理实现

目的：构建糖尿病领域本体库与糖尿病诊疗规则库,在此基础上实现语义推理,糖尿病领域知识的重用、潜在知识的揭示及共享,为后续糖尿病管理系统研究奠定基础,进而为基层全科医生诊疗糖尿病提供决策支持。方法：以国内糖尿病领域相关临床指南和领域专家知识为依据,抽取其中的概念以及概念之间的关系,借鉴七步法和骨架法,在斯坦福大学Protégé平台构建糖尿病领域本体,编写SWRL诊疗规则库,继而使用JESS推理机实现语义推理。结果：构建了较为完整的糖尿病领域本体库与糖尿病诊疗规则库,包含概念233条、实例205条、实例间关系16条、数值属性18条、SWRL规则28条,并在此基础上实现了语义推理。结论：构建的糖尿病领域本体能够实现语义推理任务,是将本体技术应用于慢病诊疗领域的有益探索。     

QNOTE: an instrument for measuring the quality of EHR clinical notes

Background and objective

The outpatient clinical note documents the clinician''s information collection, problem assessment, and patient management, yet there is currently no validated instrument to measure the quality of the electronic clinical note. This study evaluated the validity of the QNOTE instrument, which assesses 12 elements in the clinical note, for measuring the quality of clinical notes. It also compared its performance with a global instrument that assesses the clinical note as a whole.

Materials and methods

Retrospective multicenter blinded study of the clinical notes of 100 outpatients with type 2 diabetes mellitus who had been seen in clinic on at least three occasions. The 300 notes were rated by eight general internal medicine and eight family medicine practicing physicians. The QNOTE instrument scored the quality of the note as the sum of a set of 12 note element scores, and its inter-rater agreement was measured by the intraclass correlation coefficient. The Global instrument scored the note in its entirety, and its inter-rater agreement was measured by the Fleiss κ.

Results

The overall QNOTE inter-rater agreement was 0.82 (CI 0.80 to 0.84), and its note quality score was 65 (CI 64 to 66). The Global inter-rater agreement was 0.24 (CI 0.19 to 0.29), and its note quality score was 52 (CI 49 to 55). The QNOTE quality scores were consistent, and the overall QNOTE score was significantly higher than the overall Global score (p=0.04).

Conclusions

We found the QNOTE to be a valid instrument for evaluating the quality of electronic clinical notes, and its performance was superior to that of the Global instrument.     

Latent bias and the implementation of artificial intelligence in medicine

Increasing recognition of biases in artificial intelligence (AI) algorithms has motivated the quest to build fair models, free of biases. However, building fair models may be only half the challenge. A seemingly fair model could involve, directly or indirectly, what we call “latent biases.” Just as latent errors are generally described as errors “waiting to happen” in complex systems, latent biases are biases waiting to happen. Here we describe 3 major challenges related to bias in AI algorithms and propose several ways of managing them. There is an urgent need to address latent biases before the widespread implementation of AI algorithms in clinical practice.     

Clinical decision support system,using expert consensus-derived logic and natural language processing,decreased sedation-type order errors for patients undergoing endoscopy

ObjectiveDetermination of appropriate endoscopy sedation strategy is an important preprocedural consideration. To address manual workflow gaps that lead to sedation-type order errors at our institution, we designed and implemented a clinical decision support system (CDSS) to review orders for patients undergoing outpatient endoscopy.Materials and MethodsThe CDSS was developed and implemented by an expert panel using an agile approach. The CDSS queried patient-specific historical endoscopy records and applied expert consensus-derived logic and natural language processing to identify possible sedation order errors for human review. A retrospective analysis was conducted to evaluate impact, comparing 4-month pre-pilot and 12-month pilot periods.Results22 755 endoscopy cases were included (pre-pilot 6434 cases, pilot 16 321 cases). The CDSS decreased the sedation-type order error rate on day of endoscopy (pre-pilot 0.39%, pilot 0.037%, Odds Ratio = 0.094, P-value < 1e-8). There was no difference in background prevalence of erroneous orders (pre-pilot 0.39%, pilot 0.34%, P = .54).DiscussionAt our institution, low prevalence and high volume of cases prevented routine manual review to verify sedation order appropriateness. Using a cohort-enrichment strategy, a CDSS was able to reduce number of chart reviews needed per sedation-order error from 296.7 to 3.5, allowing for integration into the existing workflow to intercept rare but important ordering errors.ConclusionA workflow-integrated CDSS with expert consensus-derived logic rules and natural language processing significantly reduced endoscopy sedation-type order errors on day of endoscopy at our institution.