Mapping of Wound Infection Concepts

Wound infection is a serious health care complication. Standardized clinical terminologies could be leveraged to support the early identification of wound infection. The purpose of this study was to evaluate the representation of wound infection assessment and diagnosis concepts (N=26) in SNOMED CT and ICNP, using a synthesized procedural framework. A total of 13/26 (50%) assessment and diagnosis concepts had exact matches in SNOMED CT and 2/7 (29%) diagnosis concepts had exact matches in ICNP. This study demonstrated that the source concepts were moderately well represented in SNOMED CT and ICNP; however, further work is necessary to increase the representation of diagnostic infection types. The use of the framework facilitated a systematic, transparent, and repeatable mapping process, with opportunity to extend.

The SPHN Ecosystem Towards FAIR Data

Health-related data originating from diverse sources are commonly stored in manifold databases and formats, making it difficult to find, access and gather data for research purposes. In addition, so-called secondary use scenarios for health data are usually hindered by local data codes, missing dictionaries and the lack of metadata and context descriptions. Following the FAIR principles (Findable, Accessible, Interoperable and Reusable), we developed a decentralized infrastructure to overcome these hurdles and enable collaborative research by making the meaning of health-related data understandable to both, humans and machines. This infrastructure is currently being implemented in the realm of the Swiss Personalized Health Network (SPHN), a research infrastructure initiative for enabling the use and exchange of health-related data for research in Switzerland. The SPHN ecosystem for FAIR data consists of the SPHN Dataset (semantic definitions), the SPHN RDF Schema (linkage and transport of the semantics in a machine-readable format), a project RDF template, extensive guidelines and conventions on how to generate SPHN RDF schema, a Terminology Service (converter of clinical terminologies in RDF), and a Quality Assurance Framework (automated data validation with SHACLs and SPARQLs). The SPHN ecosystem has been built in a way that it can easily be adapted and extended by any SPHN project to fit individual needs. By providing such a national ecosystem, SPHN supports researchers in generating, processing and sharing FAIR data.

Clinical Term Normalization Using Learned Edit Patterns and Subconcept Matching (Preprint)

BACKGROUND Clinical terms mentioned in clinical text are often not in their standardized forms as listed in clinical terminologies due to linguistic and stylistic variations. However, many downstream automated applications require clinical terms mapped to their corresponding concepts in clinical terminologies thus necessitating the task of clinical term normalization. OBJECTIVE In this paper, a system for clinical term normalization is presented which utilizes edit patterns to convert clinical terms into their normalized forms. METHODS The edit patterns are automatically learned from UMLS as well as from the given training data. The edit patterns are generalized sequences of edits which are derived from edit distance computations. The edit patterns are both character-based as well as word-based and are learned separately for different semantic types. Besides these edit patterns, the system also normalizes clinical terms through the subconcepts mentioned in them. RESULTS The system was evaluated on the MCN corpus as part of the 2019 n2c2 Track 3 shared task of clinical term normalization. It obtained 80.79% accuracy on the standard test data. The paper includes ablation studies to evaluate contributions of different components of the system. A challenging part of the task was disambiguation when a clinical term could be normalized to multiple concepts. CONCLUSIONS The learned edit patterns led the system to perform well on the normalization task. Given that the system is based on patterns, it is human-interpretable and is also capable of giving insights about common variations of clinical terms mentioned in clinical text that are different from their standardized forms. CLINICALTRIAL

Analyzing the heterogeneity of rule-based EHR phenotyping algorithms in CALIBER and the UK Biobank

Electronic Health Records (EHR) are data generated during routine interactions across healthcare settings and contain rich, longitudinal information on diagnoses, symptoms, medications, investigations and tests. A primary use-case for EHR is the creation of phenotyping algorithms used to identify disease status, onset and progression or extraction of information on risk factors or biomarkers. Phenotyping however is challenging since EHR are collected for different purposes, have variable data quality and often require significant harmonization. While considerable effort goes into the phenotyping process, no consistent methodology for representing algorithms exists in the UK. Creating a national repository of curated algorithms can potentially enable algorithm dissemination and reuse by the wider community. A critical first step is the creation of a robust minimum information standard for phenotyping algorithm components (metadata, implementation logic, validation evidence) which involves identifying and reviewing the complexity and heterogeneity of current UK EHR algorithms. In this study, we analyzed all available EHR phenotyping algorithms (n=70) from two large-scale contemporary EHR resources in the UK (CALIBER and UK Biobank). We documented EHR sources, controlled clinical terminologies, evidence of algorithm validation, representation and implementation logic patterns. Understanding the heterogeneity of UK EHR algorithms and identifying common implementation patterns will facilitate the design of a minimum information standard for representing and curating algorithms nationally and internationally.

USE OF COMPUTATIONAL TOOLS AS SUPPORT TO THE CROSS-MAPPING METHOD BETWEEN CLINICAL TERMINOLOGIES

ABSTRACT Objective: to reflect on the use of computational tools in the cross-mapping method between clinical terminologies. Method: reflection study. Results: the cross-mapping method consists of obtaining a list of terms through extraction and normalization; the connection between the terms of the list and those of the reference base, by means of predefined rules; and grouping of the terms into categories: exact or partial combination or, in more detail, similar term, more comprehensive term, more restricted term and non-agreeing term. Performed manually in many studies, it can be automated with the use of the Unified Medical Language System (UMLS). Obtaining the terms list can occur automatically by natural language processing algorithms, being that the use of rules to identify information in texts allows the expert's knowledge to be coupled to the algorithm, and it can be performed by techniques based on Machine Learning. When it comes to mapping terms using the 7-Axis model of the International Classification for Nursing Practice (ICNP®), the process can also be automated through natural language processing algorithms such as POS-tagger and the syntactic parser. Conclusion: the cross-mapping method can be intensified by the use of natural language processing algorithms. However, even in cases of automatic mapping, the validation of the results by specialists should not be discarded.

Recent Developments in Clinical Terminologies — SNOMED CT, LOINC, and RxNorm

Objective: To discuss recent developments in clinical terminologies. SNOMED CT (Systematized Nomenclature of Medicine Clinical Terms) is the world's largest clinical terminology, developed by an international consortium. LOINC (Logical Observation Identifiers, Names, and Codes) is an international terminology widely used for clinical and laboratory observations. RxNorm is the standard drug terminology in the U.S. Methods and results: We present a brief review of the history, current state, and future development of SNOMED CT, LOINC and RxNorm. We also analyze their similarities and differences, and outline areas for greater interoperability among them. Conclusions: With different starting points, representation formalisms, funding sources, and evolutionary paths, SNOMED CT, LOINC, and RxNorm have evolved over the past few decades into three major clinical terminologies supporting key use cases in clinical practice. Despite their differences, partnerships have been created among their development teams to facilitate interoperability and minimize duplication of effort.

Smashing the strict hierarchy: three cases of clinical decision support malfunctions involving carvedilol

Clinical vocabularies allow for standard representation of clinical concepts, and can also contain knowledge structures, such as hierarchy, that facilitate the creation of maintainable and accurate clinical decision support (CDS). A key architectural feature of clinical hierarchies is how they handle parent-child relationships — specifically whether hierarchies are strict hierarchies (allowing a single parent per concept) or polyhierarchies (allowing multiple parents per concept). These structures handle subsumption relationships (ie, ancestor and descendant relationships) differently. In this paper, we describe three real-world malfunctions of clinical decision support related to incorrect assumptions about subsumption checking for β-blocker, specifically carvedilol, a non-selective β-blocker that also has α-blocker activity. We recommend that 1) CDS implementers should learn about the limitations of terminologies, hierarchies, and classification, 2) CDS implementers should thoroughly test CDS, with a focus on special or unusual cases, 3) CDS implementers should monitor feedback from users, and 4) electronic health record (EHR) and clinical content developers should offer and support polyhierarchical clinical terminologies, especially for medications.