A case report: using SNOMED CT for grouping Adverse Drug Reactions Terms

Ontological and Non-Ontological Resources for Associating Medical Dictionary for Regulatory Activities Terms to SNOMED Clinical Terms With Semantic Properties

Background: Formal definitions allow selecting terms (e.g., identifying all terms related to “Infectious disease” using the query “has causative agent organism”) and terminological reasoning (e.g., “hepatitis B” is a “hepatitis” and is an “infectious disease”). However, the standard international terminology Medical Dictionary for Regulatory Activities (MedDRA) used for coding adverse drug reactions in pharmacovigilance databases does not beneficiate from such formal definitions. Our objective was to evaluate the potential of reuse of ontological and non-ontological resources for generating such definitions for MedDRA.

Methods: We developed several methods that collectively allow a semiautomatic semantic enrichment of MedDRA: 1) using MedDRA-to-SNOMED Clinical Terms (SNOMED CT) mappings (available in the Unified Medical Language System metathesaurus or other mapping resources, e.g., the MedDRA preferred term “hepatitis B” is associated to the SNOMED CT concept “type B viral hepatitis”) to extract term definitions (e.g., “hepatitis B” is associated with the following properties: has finding site liver structure, has associated morphology inflammation morphology, and has causative agent hepatitis B virus); 2) using MedDRA labels and lexical/syntactic methods for automatic decomposition of complex MedDRA terms (e.g., the MedDRA systems organ class “blood and lymphatic system disorders” is decomposed in blood system disorders and lymphatic system disorders) or automatic suggestions of properties (e.g., the string “cyclic” in preferred term “cyclic neutropenia” leads to the property has clinical course cyclic).

Results: The Unified Medical Language System metathesaurus was the main ontological resource reusable for generating formal definitions for MedDRA terms. The non-ontological resources (another mapping resource provided by Nadkarni and Darer in 2010 and MedDRA labels) allowed defining few additional preferred terms. While the Ci4SeR tool helped the curator to define 1,935 terms by suggesting potential supplemental relations based on the parents’ and siblings’ semantic definition, defining manually all MedDRA terms remains expensive in time.

Discussion: Several ontological and non-ontological resources are available for associating MedDRA terms to SNOMED CT concepts with semantic properties, but providing manual definitions is still necessary. The ontology of adverse events is a possible alternative but does not cover all MedDRA terms either. Perspectives are to implement more efficient techniques to find more logical relations between SNOMED CT and MedDRA in an automated way.

Computational Advances in Drug Safety: Systematic and Mapping Review of Knowledge Engineering Based Approaches

Drug Safety (DS) is a domain with significant public health and social impact. Knowledge Engineering (KE) is the Computer Science discipline elaborating on methods and tools for developing “knowledge-intensive” systems, depending on a conceptual “knowledge” schema and some kind of “reasoning” process. The present systematic and mapping review aims to investigate KE-based approaches employed for DS and highlight the introduced added value as well as trends and possible gaps in the domain. Journal articles published between 2006 and 2017 were retrieved from PubMed/MEDLINE and Web of Science® (873 in total) and filtered based on a comprehensive set of inclusion/exclusion criteria. The 80 finally selected articles were reviewed on full-text, while the mapping process relied on a set of concrete criteria (concerning specific KE and DS core activities, special DS topics, employed data sources, reference ontologies/terminologies, and computational methods, etc.). The analysis results are publicly available as online interactive analytics graphs. The review clearly depicted increased use of KE approaches for DS. The collected data illustrate the use of KE for various DS aspects, such as Adverse Drug Event (ADE) information collection, detection, and assessment. Moreover, the quantified analysis of using KE for the respective DS core activities highlighted room for intensifying research on KE for ADE monitoring, prevention and reporting. Finally, the assessed use of the various data sources for DS special topics demonstrated extensive use of dominant data sources for DS surveillance, i.e., Spontaneous Reporting Systems, but also increasing interest in the use of emerging data sources, e.g., observational healthcare databases, biochemical/genetic databases, and social media. Various exemplar applications were identified with promising results, e.g., improvement in Adverse Drug Reaction (ADR) prediction, detection of drug interactions, and novel ADE profiles related with specific mechanisms of action, etc. Nevertheless, since the reviewed studies mostly concerned proof-of-concept implementations, more intense research is required to increase the maturity level that is necessary for KE approaches to reach routine DS practice. In conclusion, we argue that efficiently addressing DS data analytics and management challenges requires the introduction of high-throughput KE-based methods for effective knowledge discovery and management, resulting ultimately, in the establishment of a continuous learning DS system.

Knowledge Discovery from Posts in Online Health Communities Using Unified Medical Language System

Patient-reported posts in Online Health Communities (OHCs) contain various valuable information that can help establish knowledge-based online support for online patients. However, utilizing these reports to improve online patient services in the absence of appropriate medical and healthcare expert knowledge is difficult. Thus, we propose a comprehensive knowledge discovery method that is based on the Unified Medical Language System for the analysis of narrative posts in OHCs. First, we propose a domain-knowledge support framework for OHCs to provide a basis for post analysis. Second, we develop a Knowledge-Involved Topic Modeling (KI-TM) method to extract and expand explicit knowledge within the text. We propose four metrics, namely, explicit knowledge rate, latent knowledge rate, knowledge correlation rate, and perplexity, for the evaluation of the KI-TM method. Our experimental results indicate that our proposed method outperforms existing methods in terms of providing knowledge support. Our method enhances knowledge support for online patients and can help develop intelligent OHCs in the future.

[Automated grouping of terms associated to cardiac valve fibrosis in MedDRA]

AIM

To propose an alternative approach for building custom groupings of terms that complements the usual approach based on both hierarchical method (selection of reference groupings in medical dictionary for regulatory activities [MedDRA]) and/or textual method (string search), for case reports extraction from a pharmacovigilance database in response to a safety problem. Here we take cardiac valve fibrosis as an example.

METHODS

The list of terms obtained by an automated approach, based on querying ontology of adverse drug reactions (OntoADR), a knowledge base defining MedDRA terms through relationships with systematized nomenclature of medicine-clinical terms (SNOMED CT) concepts, was compared with the reference list consisting of 53 preferred terms obtained by hierarchical and textual method. Two queries were performed on OntoADR by using a dedicated software: OntoADR query tools. Both queries excluded congenital diseases, and included a procedure or an auscultation method performed on cardiac valve structures. Query 1 also considered MedDRA terms related to fibrosis, narrowing or calcification of heart valves, and query 2 MedDRA terms described according to one of these four SNOMED CT terms: "Insufficiency", "Valvular sclerosis", "Heart valve calcification" or "Heart valve stenosis".

RESULTS

The reference grouping consisted of 53 MedDRA preferred terms. Our automated method achieved recall of 79% and precision of 100% for query 1 privileging morphological abnormalities, and recall of 100% and precision of 96% for query 2 privileging functional abnormalities.

CONCLUSION

An alternative approach to MedDRA reference groupings for building custom groupings is feasible for cardiac valve fibrosis. OntoADR is still in development. Its application to other adverse reactions would require significant work for a knowledge engineer to define every MedDRA term, but such definitions could then be queried as many times as necessary by pharmacovigilance professionals.

Exploitation of semantic methods to cluster pharmacovigilance terms

Pharmacovigilance is the activity related to the collection, analysis and prevention of adverse drug reactions (ADRs) induced by drugs. This activity is usually performed within dedicated databases (national, European, international...), in which the ADRs declared for patients are usually coded with a specific controlled terminology MedDRA (Medical Dictionary for Drug Regulatory Activities). Traditionally, the detection of adverse drug reactions is performed with data mining algorithms, while more recently the groupings of close ADR terms are also being exploited. The Standardized MedDRA Queries (SMQs) have become a standard in pharmacovigilance. They are created manually by international boards of experts with the objective to group together the MedDRA terms related to a given safety topic. Within the MedDRA version 13, 84 SMQs exist, although several important safety topics are not yet covered. The objective of our work is to propose an automatic method for assisting the creation of SMQs using the clustering of semantically close MedDRA terms. The experimented method relies on semantic approaches: semantic distance and similarity algorithms, terminology structuring methods and term clustering. The obtained results indicate that the proposed unsupervised methods appear to be complementary for this task, they can generate subsets of the existing SMQs and make this process systematic and less time consuming.

Identifying inconsistencies in SNOMED CT problem lists using structural indicators

The National Library of Medicine has published the CORE and the VA/KP problem lists to facilitate the usage of SNOMED CT for encoding diagnoses and clinical data of patients in electronic health records. Therefore, it is essential for the content of the problem lists to be as accurate and consistent as possible. This study assesses the effectiveness of using a concept's word length and number of parents, two structural indicators for measuring concept complexity, to identify inconsistencies with high probability. The method is able to isolate concepts with over 40% expected of being erroneous. A structural indicator for concepts which is able to identify 52% of the examined concepts as having errors in synonyms is also presented. The results demonstrate that the concepts in problem lists are not free of inconsistencies and further quality assurance is needed to improve the quality of these concepts.

Mining FDA drug labels for medical conditions

Background

Cincinnati Children’s Hospital Medical Center (CCHMC) has built the initial Natural Language Processing (NLP) component to extract medications with their corresponding medical conditions (Indications, Contraindications, Overdosage, and Adverse Reactions) as triples of medication-related information ([(1) drug name]-[(2) medical condition]-[(3) LOINC section header]) for an intelligent database system, in order to improve patient safety and the quality of health care. The Food and Drug Administration’s (FDA) drug labels are used to demonstrate the feasibility of building the triples as an intelligent database system task.

Methods

This paper discusses a hybrid NLP system, called AutoMCExtractor, to collect medical conditions (including disease/disorder and sign/symptom) from drug labels published by the FDA. Altogether, 6,611 medical conditions in a manually-annotated gold standard were used for the system evaluation. The pre-processing step extracted the plain text from XML file and detected eight related LOINC sections (e.g. Adverse Reactions, Warnings and Precautions) for medical condition extraction. Conditional Random Fields (CRF) classifiers, trained on token, linguistic, and semantic features, were then used for medical condition extraction. Lastly, dictionary-based post-processing corrected boundary-detection errors of the CRF step. We evaluated the AutoMCExtractor on manually-annotated FDA drug labels and report the results on both token and span levels.

Results

Precision, recall, and F-measure were 0.90, 0.81, and 0.85, respectively, for the span level exact match; for the token-level evaluation, precision, recall, and F-measure were 0.92, 0.73, and 0.82, respectively.

Conclusions

The results demonstrate that (1) medical conditions can be extracted from FDA drug labels with high performance; and (2) it is feasible to develop a framework for an intelligent database system.

The readiness of SNOMED problem list concepts for meaningful use of electronic health records

OBJECTIVE

By 2015, SNOMED CT (SCT) will become the USA's standard for encoding diagnoses and problem lists in electronic health records (EHRs). To facilitate this effort, the National Library of Medicine has published the "SCT Clinical Observations Recording and Encoding" and the "Veterans Health Administration and Kaiser Permanente" problem lists (collectively, the "PL"). The PL is studied in regard to its readiness to support meaningful use of EHRs. In particular, we wish to determine if inconsistencies appearing in SCT, in general, occur as frequently in the PL, and whether further quality-assurance (QA) efforts on the PL are required.

METHODS AND MATERIALS

A study is conducted where two random samples of SCT concepts are compared. The first consists of concepts strictly from the PL and the second contains general SCT concepts distributed proportionally to the PL's in terms of their hierarchies. Each sample is analyzed for its percentage of primitive concepts and for frequency of modeling errors of various severity levels as quality measures. A simple structural indicator, namely, the number of parents, is suggested to locate high likelihood inconsistencies in hierarchical relationships. The effectiveness of this indicator is evaluated.

RESULTS

PL concepts are found to be slightly better than other concepts in the respective SCT hierarchies with regards to the quality measure of the percentage of primitive concepts and the frequency of modeling errors. There were 58% primitive concepts in the PL sample versus 62% in the control sample. The structural indicator of number of parents is shown to be statistically significant in its ability to identify concepts having a higher likelihood of inconsistencies in their hierarchical relationships. The absolute number of errors in the group of concepts having 1-3 parents was shown to be significantly lower than that for concepts with 4-6 parents and those with 7 or more parents based on Chi-squared analyses.

CONCLUSION

PL concepts suffer from the same issues as general SCT concepts, although to a slightly lesser extent, and do require further QA efforts to promote meaningful use of EHRs. To support such efforts, a structural indicator is shown to effectively ferret out potentially problematic concepts where those QA efforts should be focused.

Identification of fever and vaccine-associated gene interaction networks using ontology-based literature mining

Background

Fever is one of the most common adverse events of vaccines. The detailed mechanisms of fever and vaccine-associated gene interaction networks are not fully understood. In the present study, we employed a genome-wide, Centrality and Ontology-based Network Discovery using Literature data (CONDL) approach to analyse the genes and gene interaction networks associated with fever or vaccine-related fever responses.

Results

Over 170,000 fever-related articles from PubMed abstracts and titles were retrieved and analysed at the sentence level using natural language processing techniques to identify genes and vaccines (including 186 Vaccine Ontology terms) as well as their interactions. This resulted in a generic fever network consisting of 403 genes and 577 gene interactions. A vaccine-specific fever sub-network consisting of 29 genes and 28 gene interactions was extracted from articles that are related to both fever and vaccines. In addition, gene-vaccine interactions were identified. Vaccines (including 4 specific vaccine names) were found to directly interact with 26 genes. Gene set enrichment analysis was performed using the genes in the generated interaction networks. Moreover, the genes in these networks were prioritized using network centrality metrics. Making scientific discoveries and generating new hypotheses were possible by using network centrality and gene set enrichment analyses. For example, our study found that the genes in the generic fever network were more enriched in cell death and responses to wounding, and the vaccine sub-network had more gene enrichment in leukocyte activation and phosphorylation regulation. The most central genes in the vaccine-specific fever network are predicted to be highly relevant to vaccine-induced fever, whereas genes that are central only in the generic fever network are likely to be highly relevant to generic fever responses. Interestingly, no Toll-like receptors (TLRs) were found in the gene-vaccine interaction network. Since multiple TLRs were found in the generic fever network, it is reasonable to hypothesize that vaccine-TLR interactions may play an important role in inducing fever response, which deserves a further investigation.

Conclusions

This study demonstrated that ontology-based literature mining is a powerful method for analyzing gene interaction networks and generating new scientific hypotheses.

Comparison of Knowledge Levels Required for SNOMED CT Coding of Diagnosis and Operation Names in Clinical Records

Objectives

Coding Systematized Nomenclature of Medicine, Clinical Terms (SNOMED CT) with complex and polysemy clinical terms may ask coder to have a high level of knowledge of clinical domains, but with simpler clinical terms, coding may require only simpler knowledge. However, there are few studies quantitatively showing the relation between domain knowledge and coding ability. So, we tried to show the relationship between those two areas.

Methods

We extracted diagnosis and operation names from electronic medical records of a university hospital for 500 ophthalmology and 500 neurosurgery patients. The coding process involved one ophthalmologist, one neurosurgeon, and one medical record technician who had no experience of SNOMED coding, without limitation to accessing of data for coding. The coding results and domain knowledge were compared.

Results

705 and 576 diagnoses, and 500 and 629 operation names from ophthalmology and neurosurgery, were enrolled, respectively. The physicians showed higher performance in coding than in MRT for all domains; all specialist physicians showed the highest performance in domains of their own departments. All three coders showed statistically better coding rates in diagnosis than in operation names (p < 0.001).

Conclusions

Performance of SNOMED coding with clinical terms is strongly related to the knowledge level of the domain and the complexity of the clinical terms. Physicians who generate clinical data can be the best potential candidates as excellent coders from the aspect of coding performance.

Comparative analysis of the VA/Kaiser and NLM CORE problem subsets: an empirical study based on problem frequency

The problem list is a critical component of the electronic medical record, with implications for clinical care, provider communication, clinical decision support, quality measurement and research. However, many of its benefits depend on the use of coded terminologies. Two standard terminologies (ICD-9 and SNOMED-CT) are available for problem documentation, and two SNOMED-CT subsets (VA/KP and CORE) are available for SNOMED-CT users. We set out to examine these subsets, characterize their overlap and measure their coverage. We applied the subsets to a random sample of 100,000 records from Brigham and Women's Hospital to determine the proportion of problems covered. Though CORE is smaller (5,814 terms vs. 17,761 terms for VA/KP), 94.8% of coded problem entries from BWH were in the CORE subset, while only 84.0% of entries had matches in VA/KP (p<0.001). Though both subsets had reasonable coverage, CORE was superior in our sample, and had fewer clinically significant gaps.

Determining correspondences between high-frequency MedDRA concepts and SNOMED: a case study

BACKGROUND

The Systematic Nomenclature of Medicine Clinical Terms (SNOMED CT) is being advocated as the foundation for encoding clinical documentation. While the electronic medical record is likely to play a critical role in pharmacovigilance - the detection of adverse events due to medications - classification and reporting of Adverse Events is currently based on the Medical Dictionary of Regulatory Activities (MedDRA). Complete and high-quality MedDRA-to-SNOMED CT mappings can therefore facilitate pharmacovigilance. The existing mappings, as determined through the Unified Medical Language System (UMLS), are partial, and record only one-to-one correspondences even though SNOMED CT can be used compositionally. Efforts to map previously unmapped MedDRA concepts would be most productive if focused on concepts that occur frequently in actual adverse event data. We aimed to identify aspects of MedDRA that complicate mapping to SNOMED CT, determine pattern in unmapped high-frequency MedDRA concepts, and to identify types of integration errors in the mapping of MedDRA to UMLS.

METHODS

Using one years' data from the US Federal Drug Administrations Adverse Event Reporting System, we identified MedDRA preferred terms that collectively accounted for 95% of both Adverse Events and Therapeutic Indications records. After eliminating those already mapping to SNOMED CT, we attempted to map the remaining 645 Adverse-Event and 141 Therapeutic-Indications preferred terms with software assistance.

RESULTS

All but 46 Adverse-Event and 7 Therapeutic-Indications preferred terms could be composed using SNOMED CT concepts: none of these required more than 3 SNOMED CT concepts to compose. We describe the common composition patterns in the paper. About 30% of both Adverse-Event and Therapeutic-Indications Preferred Terms corresponded to single SNOMED CT concepts: the correspondence was detectable by human inspection but had been missed during the integration process, which had created duplicated concepts in UMLS.

CONCLUSIONS

Identification of composite mapping patterns, and the types of errors that occur in the MedDRA content within UMLS, can focus larger-scale efforts on improving the quality of such mappings, which may assist in the creation of an adverse-events ontology.

Enriching a primary health care version of ICD-10 using SNOMED CT mapping

BACKGROUND

In order to satisfy different needs, medical terminology systems must have richer structures. This study examines whether a Swedish primary health care version of the mono-hierarchical ICD-10 (KSH97-P) may obtain a richer structure using category and chapter mappings from KSH97-P to SNOMED CT and SNOMED CT's structure. Manually-built mappings from KSH97-P's categories and chapters to SNOMED CT's concepts are used as a starting point.

RESULTS

The mappings are manually evaluated using computer-produced information and a small number of mappings are updated. A new and poly-hierarchical chapter division of KSH97-P's categories has been created using the category and chapter mappings and SNOMED CT's generic structure. In the new chapter division, most categories are included in their original chapters. A considerable number of concepts are included in other chapters than their original chapters. Most of these inclusions can be explained by ICD-10's design. KSH97-P's categories are also extended with attributes using the category mappings and SNOMED CT's defining attribute relationships. About three-fourths of all concepts receive an attribute of type Finding site and about half of all concepts receive an attribute of type Associated morphology. Other types of attributes are less common.

CONCLUSIONS

It is possible to use mappings from KSH97-P to SNOMED CT and SNOMED CT's structure to enrich KSH97-P's mono-hierarchical structure with a poly-hierarchical chapter division and attributes of type Finding site and Associated morphology. The final mappings are available as additional files for this paper.

Using SNOMED CT in combination with MedDRA for reporting signal detection and adverse drug reactions reporting

OBJECTIVE

To investigate the feasibility of using SNOMED CT as an entry point for coding adverse drug reactions and map them automatically to MedDRA for reporting purposes and interoperability with legacy repositories.

METHODS

On the one hand, we attempt to map SNOMED CT concepts to MedDRA concepts through the UMLS, using synonymy and explicit mapping relations. On the other, we compute the set of all fine-grained concepts that can be reached from concepts having a mapping to MedDRA.

RESULTS

58% of the Preferred Terms in MedDRA have a mapping to SNOMED CT. Through the descendants in SNOMED CT, 108,305 additional SNOMED CT concepts can be linked to MedDRA.

CONCLUSIONS

Fine-grained SNOMED CT concepts can be mapped automatically to MedDRA. This approach has the potential to enable the collection of adverse events related to drugs directly from clinical repositories. The quality of the mapping needs to be evaluated.