SNOMED Clinical Terms Research Articles

Integrating and Adopting AI in the Radiology Workflow: A Primer for Standards and Integrating the Healthcare Enterprise (IHE) Profiles.

The deployment of artificial intelligence (AI) solutions in radiology practice creates new demands on existing imaging workflow. Accommodating custom integrations creates a substantial operational and maintenance burden. These custom integrations also increase the likelihood of unanticipated problems. Standards-based interoperability facilitates AI integration with systems from different vendors into a single environment by enabling seamless exchange between information systems in the radiology workflow. Integrating the Healthcare Enterprise (IHE) is an initiative to improve how computer systems share information across health care domains, including radiology. IHE integrates existing standards-such as Digital Imaging and Communications in Medicine, Health Level Seven, and health care lexicons and ontologies (ie, LOINC, RadLex, SNOMED Clinical Terms)-by mapping data elements from one standard to another. IHE Radiology manages profiles (standards-based implementation guides) for departmental workflow and information sharing across care sites, including profiles for scaling AI processing traffic and integrating AI results. This review focuses on the need for standards-based interoperability to scale AI integration in radiology, including a brief review of recent IHE profiles that provide a framework for AI integration. This review also discusses challenges and additional considerations for AI integration, including technical, clinical, and policy perspectives.

Transforming Estonian health data to the Observational Medical Outcomes Partnership (OMOP) Common Data Model: lessons learned.

To describe the reusable transformation process of electronic health records (EHR), claims, and prescriptions data into Observational Medical Outcome Partnership (OMOP) Common Data Model (CDM), together with challenges faced and solutions implemented. We used Estonian national health databases that store almost all residents' claims, prescriptions, and EHR records. To develop and demonstrate the transformation process of Estonian health data to OMOP CDM, we used a 10% random sample of the Estonian population (n = 150824 patients) from 2012 to 2019 (MAITT dataset). For the sample, complete information from all 3 databases was converted to OMOP CDM version 5.3. The validation was performed using open-source tools. In total, we transformed over 100 million entries to standard concepts using standard OMOP vocabularies with the average mapping rate 95%. For conditions, observations, drugs, and measurements, the mapping rate was over 90%. In most cases, SNOMED Clinical Terms were used as the target vocabulary. During the transformation process, we encountered several challenges, which are described in detail with concrete examples and solutions. For a representative 10% random sample, we successfully transferred complete records from 3 national health databases to OMOP CDM and created a reusable transformation process. Our work helps future researchers to transform linked databases into OMOP CDM more efficiently, ultimately leading to better real-world evidence.

MP17-09 DEVELOPMENT OF A LONGITUDINAL PROSTATE CANCER TRANSCRIPTOMIC AND REAL-WORLD CLINICAL DATA LINKAGE

You have accessJournal of UrologyCME1 Apr 2023MP17-09 DEVELOPMENT OF A LONGITUDINAL PROSTATE CANCER TRANSCRIPTOMIC AND REAL-WORLD CLINICAL DATA LINKAGE Michael Leapman, Julian Ho, Yang Liu, Xin Zhao, Alexander Hakansson, James Proudfoot, Elai Davicioni, Darryl Martin, Yi An, Tyler Seibert, Daniel Spratt, Matthew Cooperberg, Ashley Ross, and Preston Sprenkle Michael LeapmanMichael Leapman More articles by this author , Julian HoJulian Ho More articles by this author , Yang LiuYang Liu More articles by this author , Xin ZhaoXin Zhao More articles by this author , Alexander HakanssonAlexander Hakansson More articles by this author , James ProudfootJames Proudfoot More articles by this author , Elai DavicioniElai Davicioni More articles by this author , Darryl MartinDarryl Martin More articles by this author , Yi AnYi An More articles by this author , Tyler SeibertTyler Seibert More articles by this author , Daniel SprattDaniel Spratt More articles by this author , Matthew CooperbergMatthew Cooperberg More articles by this author , Ashley RossAshley Ross More articles by this author , and Preston SprenklePreston Sprenkle More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003237.09AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: We developed a novel linkage between the Decipher prostate genomic classifier (GC) and real-world patient data in the United States across payors and sites of care. METHODS: Clinical and transcriptomic data from clinical use of the Decipher prostate GC between 2013-2022 (Veracyte Inc., San Diego, CA) were linked with real-world data aggregated from insurance claims, pharmacy records, and electronic health record (EHR) data (Clarivate, Chandler, AZ). Patients were anonymously linked between datasets by deterministic methods through a de-identification engine using encrypted tokens (Datavant, San Francisco, CA), Figure 1. The objective of this study was to develop algorithms for identifying prostate cancer diagnoses, treatment timing, and clinical outcomes (biochemical recurrence, BCR, and prostate cancer metastases) in RWD using diagnosis, common procedural terminology (CPT) codes, pharmacy codes, SNOMED clinical terms and unstructured text in the electronic health record (EHR). We compared the accuracy of RWD algorithms using clinical information obtained during Decipher testing as the reference standard. RESULTS: A total of 92,976 of 95,578 (97.2%) patients with Decipher prostate GC were successfully linked to RWD, including 53,871 from biopsy and 39,105 from radical prostatectomy (RP) tests. The median age at Decipher testing was 66.4 years [IQR 61.0, 71.0]. The concordance of prostate cancer diagnoses was 85.0%, including 80.8% for biopsy and 90.7% for RP. Year of treatment was concordant in 98.6% of patients undergoing GC testing at RP, and 87.4% in patients with biopsy GC tests. BCR was identified based on diagnosis code (R 97.21 of ICD-10) (96.3%), unstructured text (0.05%) and both in (3.65%). Similarly, metastases were identified based on diagnosis codes (94.9%), unstructured text (1.38%) and both (3.73%). CONCLUSIONS: We established the first national-scale linkage of transcriptomic and longitudinal clinical data yielding high accuracy for identifying key clinical junctures including diagnosis, treatment, and early cancer outcome. This resource can be leveraged to enhance understandings of disease biology, patterns of care and treatment effectiveness. Source of Funding: Veracyte Inc © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e216 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Michael Leapman More articles by this author Julian Ho More articles by this author Yang Liu More articles by this author Xin Zhao More articles by this author Alexander Hakansson More articles by this author James Proudfoot More articles by this author Elai Davicioni More articles by this author Darryl Martin More articles by this author Yi An More articles by this author Tyler Seibert More articles by this author Daniel Spratt More articles by this author Matthew Cooperberg More articles by this author Ashley Ross More articles by this author Preston Sprenkle More articles by this author Expand All Advertisement PDF downloadLoading ...

S1544 Celiac Disease Is Associated With Idiopathic Inflammatory Myopathies

Introduction: Celiac disease (CD) is a chronic systemic immune-mediated disorder that occurs in genetically predisposed people upon ingestion of gluten. The complications and associations of CD are wide-ranging, with notable associations with other autoimmune diseases. Few studies have described the association of CD with inflammatory myopathies, such as polymyositis (PM), dermatomyositis (DM), and inclusion body myositis (IBM). However, there have been no studies interrogating the association in large cohorts. We investigated these relationships using a large nation-wide patient dataset. Methods: Utilizing IBM Explorys (Cleveland, OH), a database encompassing over 80 million patients in the United States and spanning the last 2 decades, we defined groups of patients identified with 3 idiopathic inflammatory myopathies using SNOMED Clinical Terms. We collected age, gender, and race-based demographics, in addition to comorbidities including hypothyroidism, alcohol use disorder, tobacco use, and CD, and subsequently performed binary logistic regression using IBM SPSS Statistics v26 (Chicago, IL) to determine significant associations. Results: In the database, which contained 80,920,060 patients at the time of querying, there were 143,330 CD patients (0.18%). 18,270 (0.02%) of the total patients met the definition of dermatomyositis, with 160 (0.88%) of these carrying the diagnosis of CD, while there were 8,970 (0.01%) polymyositis patients (of which there were 70 / 0.78% with CD) and 1,520 (0.002%) IBM patients (30 / 2% with CD). Following logistic regression that incorporated demographics and several comorbidities, CD was significantly associated with all inflammatory myopathies: the OR for CD in dermatomyositis was 3.55 (95%CI 3.11 — 4.04, P< 0.001), 3.23 in polymyositis (95%CI 2.89 — 3.60, P< 0.001) and 11.60 in IBM (95%CI 9.02 — 14.92, P< 0.001) (Table). Conclusion: In this very large aggregate of patients across the United States, CD was significantly associated with the idiopathic inflammatory myopathies of polymyositis, dermatomyositis, and IBM after accounting for a number of possible confounders. Clinicians should be aware of this relationship when assessing myalgia in celiac disease patients. Table 1. - Results of the multivariate regression analysis with odds ratios (OR), confidence intervals, and P-values (significant if <0.05) for each inflammatory myopathy Risk Factor OR for PM P-value OR for DM P-value OR for IBM P-value Celiac Disease 3.23 [2.89-3.60] < 0.001 3.55 [3.11-4.04] < 0.001 11.60 [9.02-14.92] < 0.001 Female gender 1.34 [1.31-1.38] < 0.001 1.36 [1.32-1.40] < 0.001 0.47 [0.43-0.52] < 0.001 Age ≥65 2.51 [2.45-2.57] < 0.001 2.26 [2.20-2.33] < 0.001 9.16 [8.20-10.25] < 0.001 White race 1.49 [1.45-1.53] < 0.001 1.71 [1.65-1.76] < 0.001 1.88 [1.69-2.09] < 0.001 Hypothyroidism 3.59 [3.49-3.69] < 0.001 3.33 [3.21-3.45] < 0.001 3.08 [2.76-3.43] < 0.001 Alcohol use 1.64 [1.53-1.76] < 0.001 1.76 [1.61-1.93] < 0.001 3.01 [2.47-3.67] < 0.001 Tobacco use 1.93 [1.86-2.00] < 0.001 1.93 [1.84-2.02] < 0.001 1.45 [1.25-1.68] < 0.001

Effectiveness of the Use of Standardized Vocabularies on Epilepsy Patient Cohort Generation.

ObjectivesThis study investigated the effectiveness of using standardized vocabularies to generate epilepsy patient cohorts with local medical codes, SNOMED Clinical Terms (SNOMED CT), and International Classification of Diseases tenth revision (ICD-10)/Korean Classification of Diseases-7 (KCD-7).MethodsWe compared the granularity between SNOMED CT and ICD-10 for epilepsy by counting the number of SNOMED CT concepts mapped to one ICD-10 code. Next, we created epilepsy patient cohorts by selecting all patients who had at least one code included in the concept sets defined using each vocabulary. We set patient cohorts generated by local codes as the reference to evaluate the patient cohorts generated using SNOMED CT and ICD-10/KCD-7. We compared the number of patients, the prevalence of epilepsy, and the age distribution between patient cohorts by year.ResultsIn terms of the cohort size, the match rate with the reference cohort was approximately 99.2% for SNOMED CT and 94.0% for ICD-10/KDC7. From 2010 to 2019, the mean prevalence of epilepsy defined using the local codes, SNOMED CT, and ICD-10/KCD-7 was 0.889%, 0.891% and 0.923%, respectively. The age distribution of epilepsy patients showed no significant difference between the cohorts defined using local codes or SNOMED CT, but the ICD-9/KCD-7-generated cohort showed a substantial gap in the age distribution of patients with epilepsy compared to the cohort generated using the local codes.ConclusionsThe number and age distribution of patients were substantially different from the reference when we used ICD-10/KCD-7 codes, but not when we used SNOMED CT concepts. Therefore, SNOMED CT is more suitable for representing clinical ideas and conducting clinical studies than ICD-10/KCD-7.

Artificial Intelligence DENTOMO: Opportunities and Prospects for analysis of CBCT in Dentistry

Analysis of artificial intelligence DENTOMO application efficiency, its opportunities and prospects for Interpretation of Cone Beam CT in Dentistry and developing model for automatic analysis cone beam computed tomography in Dentistry. The presented model is based on two convolutional neural networks, includes a database and knowledge base, harmonized with SNOMED Clinical Terms is a systematically organized computer processable collection of medical terms providing codes, terms, synonyms and definitions used in clinical documentation and reporting. The accuracy of AI model was assessed by calculating the ratio of false identifications to the true ones in each case. The model of artificial intelligence DENTOMO, which allows automated deciphering the CT in maxillofacial area, was developed and implemented in practical dentistry. The developed model automatically decodes cone beam CT images, identifies, and classifies the anatomical structures of the human dental system, and reveals the pathological processes and their dynamics in dentistry system. The developed model rather accurately identified the natural teeth in the frontal group as well in the group of premolars and molars. The recognition accuracy surpassed 90%. It should be noted that the developed model includes the possibility of “training”, which can improve the quality of evaluation of diagnostic features and related parameters. Moreover, it can add the current diagnostic potencies with novel features. Testing of DENTOMO model demonstrated a reasonable effectiveness in deciphering the CT of dental system. The developed technology allows computerizing and objectifying interpretation of CT of the dental system.

Artificial Intelligence DENTOMO: Opportunities and Prospects for Interpretation of Cone Beam CT in Dentistry.

The model of artificial intelligence DENTOMO, which allows automated deciphering the CT in maxillofacial area, was developed and implemented in practical dentistry. The presented model is based on two convolutional neural networks, includes a database and knowledge base, harmonized with SNOMED Clinical Terms is a systematically organized computer processable collection of medical terms providing codes, terms, synonyms and definitions used in clinical documentation and reporting. The developed model automatically decodes cone beam CT images, identifies and classifies the anatomical structures of the human dental system, and reveals the pathological processes and their dynamics in dentistry system. This model generates the medical reports automatically. Testing of DENTOMO model demonstrated a reasonable effectiveness in deciphering the CT of dental system. The developed technology allows computerizing and objectifying interpretation of CT of the dental system.

Искусственный интеллект DENTOMO — возможности и перспективы интерпретации конусно-лучевых компьютерных томограмм в стоматологии

The model of artificial intelligence DENTOMO, which allows automated deciphering the CT in maxillofacial area, was developed and implemented in practical dentistry. The presented model is based on two convolutional neural networks, includes a database and knowledge base, harmonized with SNOMED Clinical Terms is a systematically organized computer processable collection of medical terms providing codes, terms, synonyms and definitions used in clinical documentation and reporting. The developed model automatically decodes cone beam CT images, identifies and classifies the anatomical structures of the human dental system, and reveals the pathological processes and their dynamics in dentistry system. This model generates the medical reports automatically. Testing of DENTOMO model demonstrated a reasonable effectiveness in deciphering the CT of dental system. The developed technology allows computerizing and objectifying interpretation of CT of the dental system.

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.

SNOMEDtxt: Natural Language Generation from SNOMED Ontology.

SNOMED Clinical Terms (SNOMED CT) defines over 70,000 diseases, including many rare ones. Meanwhile, descriptions of rare conditions are missing from online educational resources. SNOMEDtxt converts ontological concept definitions and relations contained in SNOMED CT into narrative disease descriptions using Natural Language Generation techniques. Generated text is evaluated using both computational methods and clinician and lay user feedback. User evaluations indicate that lay people prefer generated text to the original SNOMED content, find it more informative, and understand it significantly better. This method promises to improve access to clinical knowledge for patients and the medical community and to assist in ontology auditing through natural language descriptions.

NPU, LOINC, and SNOMED CT: a comparison of terminologies for laboratory results reveals individual advantages and a lack of possibilities to encode interpretive comments

AbstractBackgroundTerminologies facilitate data exchange and enable laboratories to assist in patient care even if complex treatment pathways involve multiple stakeholders. This paper examines the three common terminologiesNomenclature for Properties and Units(NPU),Logical Observation Identifiers Names and Codes(LOINC), andSNOMED Clinical Terms(SNOMED CT).MethodsThe potential of each terminology to encode five exemplary laboratory results is assessed. The terminologies are evaluated according to scope, correctness, formal representations, and ease of use.ResultsNPU is based on metrological concepts with strict rules regarding the coding of the measurand and the result value. Clinically equivalent results are regularly mapped to the same code but there is little support to differentiate results from non-standardized measurements. LOINC encodes analyses as offered by the laboratory. Its large number of entries allows different mappings for the same analysis. SNOMED CT contains few analyses natively, but its formal composition mechanism allows representing measurements by post-coordinated expressions that are equivalent to LOINC codes. SNOMED CT’s strength lies in its support of many non-numerical result values. Implicit code hierarchies exist in NPU and LOINC. SNOMED CT has explicit, elaborate axioms that elucidate the meaning of its content. Its complexity and its license conditions, however, impede a more widespread use. Interpretive comments, a crucial part of laboratory results, are still difficult to encode with any of the terminologies.ConclusionsAll three terminologies have distinct potentials and limitations, but the approximation of SNOMED CT and LOINC suggests using them together. Terminologies need to be expanded to also cover interpretive comments.

NPU, LOINC, and SNOMED CT: a comparison of terminologies for laboratory results reveals individual advantages and a lack of possibilities to encode interpretive comments

Background Terminologies facilitate data exchange and enable laboratories to assist in patient care even if complex treatment pathways involve multiple stakeholders. This paper examines the three common terminologies Nomenclature for Properties and Units (NPU), Logical Observation Identifiers Names and Codes (LOINC), and SNOMED Clinical Terms (SNOMED CT). Methods The potential of each terminology to encode five exemplary laboratory results is assessed. The terminologies are evaluated according to scope, correctness, formal representations, and ease of use. Results NPU is based on metrological concepts with strict rules regarding the coding of the measurand and the result value. Clinically equivalent results are regularly mapped to the same code but there is little support to differentiate results from non-standardized measurements. LOINC encodes analyses as offered by the laboratory. Its large number of entries allows different mappings for the same analysis. SNOMED CT contains few analyses natively, but its formal composition mechanism allows representing measurements by post-coordinated expressions that are equivalent to LOINC codes. SNOMED CT’s strength lies in its support of many non-numerical result values. Implicit code hierarchies exist in NPU and LOINC. SNOMED CT has explicit, elaborate axioms that elucidate the meaning of its content. Its complexity and its license conditions, however, impede a more widespread use. Interpretive comments, a crucial part of laboratory results, are still difficult to encode with any of the terminologies. Conclusions All three terminologies have distinct potentials and limitations, but the approximation of SNOMED CT and LOINC suggests using them together. Terminologies need to be expanded to also cover interpretive comments.

Consumers' Use of UMLS Concepts on Social Media: Diabetes-Related Textual Data Analysis in Blog and Social Q&A Sites.

BackgroundThe widely known terminology gap between health professionals and health consumers hinders effective information seeking for consumers.ObjectiveThe aim of this study was to better understand consumers’ usage of medical concepts by evaluating the coverage of concepts and semantic types of the Unified Medical Language System (UMLS) on diabetes-related postings in 2 types of social media: blogs and social question and answer (Q&A).MethodsWe collected 2 types of social media data: (1) a total of 3711 blogs tagged with “diabetes” on Tumblr posted between February and October 2015; and (2) a total of 58,422 questions and associated answers posted between 2009 and 2014 in the diabetes category of Yahoo! Answers. We analyzed the datasets using a widely adopted biomedical text processing framework Apache cTAKES and its extension YTEX. First, we applied the named entity recognition (NER) method implemented in YTEX to identify UMLS concepts in the datasets. We then analyzed the coverage and the popularity of concepts in the UMLS source vocabularies across the 2 datasets (ie, blogs and social Q&A). Further, we conducted a concept-level comparative coverage analysis between SNOMED Clinical Terms (SNOMED CT) and Open-Access Collaborative Consumer Health Vocabulary (OAC CHV)—the top 2 UMLS source vocabularies that have the most coverage on our datasets. We also analyzed the UMLS semantic types that were frequently observed in our datasets.ResultsWe identified 2415 UMLS concepts from blog postings, 6452 UMLS concepts from social Q&A questions, and 10,378 UMLS concepts from the answers. The medical concepts identified in the blogs can be covered by 56 source vocabularies in the UMLS, while those in questions and answers can be covered by 58 source vocabularies. SNOMED CT was the dominant vocabulary in terms of coverage across all the datasets, ranging from 84.9% to 95.9%. It was followed by OAC CHV (between 73.5% and 80.0%) and Metathesaurus Names (MTH) (between 55.7% and 73.5%). All of the social media datasets shared frequent semantic types such as “Amino Acid, Peptide, or Protein,” “Body Part, Organ, or Organ Component,” and “Disease or Syndrome.”ConclusionsAlthough the 3 social media datasets vary greatly in size, they exhibited similar conceptual coverage among UMLS source vocabularies and the identified concepts showed similar semantic type distributions. As such, concepts that are both frequently used by consumers and also found in professional vocabularies such as SNOMED CT can be suggested to OAC CHV to improve its coverage.

Harmonising ICNP and SNOMED CT: A Model for Effective Collaboration.

The purpose of this panel was to demonstrate an approach to collaborative working within nursing and health informatics. The panel took as an example an initiative to harmonise between two large-scale terminologies, namely the International Classification for Nursing Practice (ICNP) and SNOMED Clinical Terms (SNOMED CT). A number of practical topics were framed within a context of collaboration, including semi-automated and manual approaches to mapping, consensus working, clinical validation, formal concept modelling, etc. Those attending the panel, nurses and informatics professional alike, came away with an increased understanding of a range of approaches to collaborative working within nursing and health informatics.

A structured approach to recording AIDS-defining illnesses in Kenya: A SNOMED CT based solution

IntroductionSeveral studies conducted in sub-Saharan Africa (SSA) have shown that routine clinical data in HIV clinics often have errors. Lack of structured and coded documentation of diagnosis of AIDS defining illnesses (ADIs) can compromise data quality and decisions made on clinical care. MethodsWe used a structured framework to derive a reference set of concepts and terms used to describe ADIs. The four sources used were: (i) CDC/Accenture list of opportunistic infections, (ii) SNOMED Clinical Terms (SNOMED CT), (iii) Focus Group Discussion (FGD) among clinicians and nurses attending to patients at a referral provincial hospital in western Kenya, and (iv) chart abstraction from the Maternal Child Health (MCH) and HIV clinics at the same hospital. Using the January 2014 release of SNOMED CT, concepts were retrieved that matched terms abstracted from approach iii & iv, and the content coverage assessed. Post-coordination matching was applied when needed. ResultsThe final reference set had 1054 unique ADI concepts which were described by 1860 unique terms. Content coverage of SNOMED CT was high (99.9% with pre-coordinated concepts; 100% with post-coordination). The resulting reference set for ADIs was implemented as the interface terminology on OpenMRS data entry forms. ConclusionDifferent sources demonstrate complementarity in the collection of concepts and terms for an interface terminology. SNOMED CT provides a high coverage in the domain of ADIs. Further work is needed to evaluate the effect of the interface terminology on data quality and quality of care.

Cadec: A corpus of adverse drug event annotations

CSIRO Adverse Drug Event Corpus (Cadec) is a new rich annotated corpus of medical forum posts on patient-reported Adverse Drug Events (ADEs). The corpus is sourced from posts on social media, and contains text that is largely written in colloquial language and often deviates from formal English grammar and punctuation rules. Annotations contain mentions of concepts such as drugs, adverse effects, symptoms, and diseases linked to their corresponding concepts in controlled vocabularies, i.e., SNOMED Clinical Terms and MedDRA. The quality of the annotations is ensured by annotation guidelines, multi-stage annotations, measuring inter-annotator agreement, and final review of the annotations by a clinical terminologist. This corpus is useful for studies in the area of information extraction, or more generally text mining, from social media to detect possible adverse drug reactions from direct patient reports. The corpus is publicly available at https://data.csiro.au.1The data can be used for research purposes only, under the CSIRO data licence.1

SORTA: a system for ontology-based re-coding and technical annotation of biomedical phenotype data.

There is an urgent need to standardize the semantics of biomedical data values, such as phenotypes, to enable comparative and integrative analyses. However, it is unlikely that all studies will use the same data collection protocols. As a result, retrospective standardization is often required, which involves matching of original (unstructured or locally coded) data to widely used coding or ontology systems such as SNOMED CT (clinical terms), ICD-10 (International Classification of Disease) and HPO (Human Phenotype Ontology). This data curation process is usually a time-consuming process performed by a human expert. To help mechanize this process, we have developed SORTA, a computer-aided system for rapidly encoding free text or locally coded values to a formal coding system or ontology. SORTA matches original data values (uploaded in semicolon delimited format) to a target coding system (uploaded in Excel spreadsheet, OWL ontology web language or OBO open biomedical ontologies format). It then semi- automatically shortlists candidate codes for each data value using Lucene and n-gram based matching algorithms, and can also learn from matches chosen by human experts. We evaluated SORTA’s applicability in two use cases. For the LifeLines biobank, we used SORTA to recode 90 000 free text values (including 5211 unique values) about physical exercise to MET (Metabolic Equivalent of Task) codes. For the CINEAS clinical symptom coding system, we used SORTA to map to HPO, enriching HPO when necessary (315 terms matched so far). Out of the shortlists at rank 1, we found a precision/recall of 0.97/0.98 in LifeLines and of 0.58/0.45 in CINEAS. More importantly, users found the tool both a major time saver and a quality improvement because SORTA reduced the chances of human mistakes. Thus, SORTA can dramatically ease data (re)coding tasks and we believe it will prove useful for many more projects.Database URL: http://molgenis.org/sorta or as an open source download from http://www.molgenis.org/wiki/SORTA

New primary renal diagnosis codes for the ERA-EDTA

The European Renal Association-European Dialysis and Transplant Association (ERA-EDTA) Registry has produced a new set of primary renal diagnosis (PRD) codes that are intended for use by affiliated registries. It is designed specifically for use in renal centres and registries but is aligned with international coding standards supported by the WHO (International Classification of Diseases) and the International Health Terminology Standards Development Organization (SNOMED Clinical Terms). It is available as supplementary material to this paper and free on the internet for non-commercial, clinical, quality improvement and research use, and by agreement with the ERA-EDTA Registry for use by commercial organizations. Conversion between the old and the new PRD codes is possible. The new codes are very flexible and will be actively managed to keep them up-to-date and to ensure that renal medicine can remain at the forefront of the electronic revolution in medicine, epidemiology research and the use of decision support systems to improve the care of patients.

Mapping OpenSDE Domain Models to SNOMED CT

To explore the strengths and pitfalls of mapping structured EPR (electronic patient record) terms (OpenSDE) to SNOMED codes. The OpenSDE model was developed for cardiovascular diseases in the context of the I4C project. We employed 35 patient records as references to adjust the model. We then performed automated and manual matches following the design of matching terms in the thesaurus of the resulting OpenSDE domain model to SNOMED concepts. Subsequently, we assessed what number of OpenSDE terms within the domain model can be matched to SNOMED concepts. The OpenSDE domain tree contains 3230 nodes, involving 689 unique terms (terms can be associated with more than one node in different parts of a domain model tree). After final manual work for the 689 tree terms, 616 resulted in a good match, 31 in a partial match, and 42 in no match. Of the good matches, 23 produced multiple matches. The matches were used to represent the mapping of each node in the domain tree by concatenation of the matching terms. Mapping predefined terms in OpenSDE domain models to SNOMED Clinical Terms (CT) concepts eliminates laborious mapping for each individual patient record. The assignment of SNOMED codes to OpenSDE tree nodes facilitates exchange, aggregation, and research involving patient data. The mapping will serve the construction of queries at higher semantic levels than explicitly modeled in an OpenSDE domain model. However, the usefulness of the mapping result depends on the completeness of the mapping to SNOMED CT, for which there is no gold standard.

An evaluation of the usefulness of two terminology models for integrating nursing diagnosis concepts into SNOMED Clinical Terms ®

Objectives: We evaluated the usefulness of two models for integrating nursing diagnosis concepts into SNOMED Clinical Terms (CT). Methods: First, we dissected nursing diagnosis term phrases from two source terminologies (North American Nursing Diagnosis Association Taxonomy 1 (NANDA) and Omaha System) into the semantic categories of the European Committee for Standardization (CEN) categorical structure and ISO reference terminology model (RTM). Second, we critically analyzed the similarities between the semantic links in the CEN and ISO models and the semantic links used to formally define diagnostic concepts in SNOMED CT. Results: Our findings demonstrated that focus, bearer/subject of information, and judgment were present in 100% of the NANDA and Omaha term phrases. The Omaha term phrases contained no additional descriptors beyond those considered mandatory in the CEN and ISO models. The comparison among the semantic links showed that SNOMED CT currently contains all but one of the semantic links needed to model the two source terminologies for integration. In conclusion, our findings support the potential utility of the CEN and ISO models for integrating nursing diagnostic concepts into SNOMED CT.