SNOMED CT Codes Research Articles

Map-Assisted Generation of Procedure and Intervention Encoding (Magpie): An Innovative Approach for ICD-10-PCS Coding.

ICD-10-PCS coding is challenging because of the large number of codes, non-intuitive terms and paucity of the ICD-10-PCS index. We previously repurposed the richer ICD-9-CM procedure index for ICD-10-PCS coding. We have developed the MAGPIE tool based on the repurposed ICD-9-CM index with other lexical and mapping resources. MAGPIE helps the user to identify SNOMED CT and ICD-10-PCS codes for medical procedures. MAGPIE uses three innovative search approaches: cascading search (SNOMED CT to ICD-9-CM to ICD-10-PCS), hybrid lexical and map-assisted matching, and semantic filtering of ICD-10-PCS codes. Our evaluation showed that MAGPIE found the correct SNOMED CT code and ICD-10-PCS table in 70% and 85% of cases respectively, without any user intervention. MAGPIE is available online from the NLM website: magpie.nlm.nih.gov.

Using Syndromic Surveillance and Climatic Data to Detect High Intensity HFMD Seasons

Using Syndromic Surveillance and Climatic Data to Detect High Intensity HFMD Seasons

Electronic case reporting of STIs: Are non-existent codes the reason for missing information?

Objective: Previous research identified data gaps between traditional paper-based STI notifiable condition reporting and pilot electronic initial case reporting (eICR) relying on Continuity of Care Documents (CCDs) exported from our clinical partner’s electronic health record (EHR) software.1 Structured data capture is needed for automatic processing of eICR data imported into public health repositories and surveillance systems, similar to electronic laboratory reporting (ELR). Coding data gaps (between paper and electronic case reports) using standardized vocabularies will allow integration of additional questions into EHR or other data collection systems and may allow creation of standard Clinical Data Architecture (CDA) templates, Logical Observation Identifiers Names and Codes (LOINC) panels, or Fast Healthcare Interoperability Resources (FHIR) resources. Furthermore, identifying data gaps can inform improvements to other standards including nationwide standardization efforts for notifiable conditions.Introduction: Under the CDC STD Surveillance Network (SSuN) Part B grant, WA DOH is testing eICR of sexually transmitted infections (STI) with a clinical partner. Existing standard vocabulary codes were identified to represent previously-identified information gaps, or the need for new codes or concepts was identified.Methods: In prior work, CCDs were securely received from our clinical partner and then analyzed for gaps compared to the existing paper-based STI case reporting form.1 Now, codes associated with gap concepts were identified in standard vocabularies such as LOINC and SNOMED CT. Standards were searched using online browsers offered by the standards development organizations (SDO) to identify potential codes, which were reviewed with public health epidemiologists and clinicians. Gaps were listed, and wording and intent was compared to standard codes including accessory information found in the SDO browsers and a final table of recommended codes was produced.Results: Acceptable congruity between currently used case reporting questions and coded vocabularies was found for the majority of data gaps previously identified. Where data need was incongruous with standard coded vocabularies, new codes or concepts could be proposed to the SDO.Pregnancy status is often missing from CDA documents but is well-conceptualized in both LOINC and SNOMED CT systems under several codes, including any current laboratory tests for pregnancy. HIV status is similarly well-conceptualized in both LOINC and SNOMED CT both as a problem list item well as thru a variety of laboratory tests. However, problem list EHR models lack standard inclusion of date of last HIV test or dates of current pregnancy as an associated coded data element which is desirable for public health.Information about the case patient’s sexual partners, need for partner STI treatment, and partner treatment completed is lacking in standard CCD documents.1 Number of current sexual partners [requiring treatment] – has a SNOMED-CT code, but lacks a match in LOINC coding system. This gap identified the need for exploration of how information about sexual partners can best be represented in interoperability artifacts, including the most useful division of information content between the information model and the standard terminology. Needed concept could resemble ‘record target’ found in HL7 version 3.0 and would allow data to be provided without specifying additional codes. Exploration of information model options or new codes is recommended.Many codes are possible for site of infection and specific symptoms but the overall concepts of ‘symptomatic infection’ and ‘site of infection’ as coded elements would need to be added.Conclusions: This coded element gap analysis found that most information requested in an STI case report can be found in a CCD. Gaps can be addressed by using existing standard terms except for concepts about sexual partners that might be better addressed by exploring the information model rather than through the addition of standard codes. Standards use will facilitate complete case reporting using CDA or FIHR, for example, within a ‘blue button’ or other system with functionality for exchanging additional information about notifiable condition case patients. Collaboration with clinicians, public health practitioners, informaticians, and EHR vendors in will help determine how these concepts might best be modeled. Understanding data gaps involves working closely with a broad range of stakeholders, to understand why gaps exist and how well proposed solutions will meet stakeholder needs.

Biomedical Informatics Investigator

The BMI Investigator is a computer human interface built in .Net which allows simultaneous query of structured data such as demographics, administrative codes, medications (coded in RxNorm), laboratory test results (coded in LOINC) and formerly unstructured data in clinical notes (coded in SNOMED CT). The ontology terms identified using SNOMED are all coded as either positive, negative or uncertain assertions. They are then where applicable built into compositional expressions and stored in both a graph database and a triple store. The SNOMED CT codes are stored in a NOSQL database, Berkley DB, and the structured data is stored in SQL using the OMOP/OHDSI format. The BMI investigator also lets you develop models for cohort selection (data driven recruitment to clinical trials) and automated retrospective research using genomic criteria and we are adding image feature data currently to the system. We performed a usability experiment and the users identified some usability flaws which were used to improve the software. Overall, the BMI Investigator was felt to be usable by subject matter experts. Next steps for the software are to integrate genomic criteria and image features into the query engine.

2327

2327

Coding of Electronic Laboratory Reports for Biosurveillance, Selected United States Hospitals, 2011.

ObjectiveElectronic laboratory reporting has been promoted as a public health priority. The Office of the U.S. National Coordinator for Health Information Technology has endorsed two coding systems: Logical Observation Identifiers Names and Codes (LOINC) for laboratory test orders and Systemized Nomenclature of Medicine-Clinical Terms (SNOMED CT) for test results.Materials and MethodsWe examined LOINC and SNOMED CT code use in electronic laboratory data reported in 2011 by 63 non-federal hospitals to BioSense electronic syndromic surveillance system. We analyzed the frequencies, characteristics, and code concepts of test orders and results.ResultsA total of 14,028,774 laboratory test orders or results were reported. No test orders used SNOMED CT codes. To describe test orders, 77% used a LOINC code, 17% had no value, and 6% had a non-informative value, “OTH”. Thirty-three percent (33%) of test results had missing or non-informative codes. For test results with at least one informative value, 91.8% had only LOINC codes, 0.7% had only SNOMED codes, and 7.4% had both. Of 108 SNOMED CT codes reported without LOINC codes, 45% could be matched to at least one LOINC code.ConclusionMissing or non-informative codes comprised almost a quarter of laboratory test orders and a third of test results reported to BioSense by non-federal hospitals. Use of LOINC codes for laboratory test results was more common than use of SNOMED CT. Complete and standardized coding could improve the usefulness of laboratory data for public health surveillance and response.

Pharmacy HIT Collaborative releases documents for practitioners

Seven documents released Integrating Pharmacists into Health Information Exchanges. “In order for pharmacists to exchange what they are documenting clinically, they have to be able to exchange the information with hospitals, other health care providers, and even patients through health information exchanges [HIEs],” said Shelly Spiro, BSPharm, FASCP, Executive Director of the Pharmacy HIT Collaborative. HIEs make health information available to all health professionals, including pharmacists, who are critical in coordinating medication management, especially during points of transitional care. This document informs pharmacists about HIEs and provides best practices to help them electronically exchange health information through state-run HIEs. Documenting Comprehensive Medication Management in Team-Based Models Using SNOMED CT Codes. SNOMED CT Codes are comprehensive codes used to document clinical encounters by pharmacists and other health care providers. This document provides examples of how SNOMED CT Codes are used by pharmacists in various care delivery models, including patient-centered medical homes (PCMHs). The guide is especially helpful for pharmacists who provide medication therapy management (MTM) services or comprehensive medication management (CMM) in PCMHs or other teambased care models. The codes can be embedded into an HIE or EHR and sent to other health care providers or even payers. “In coordination with other health care providers, the pharmacist needs to be able to consistently document the care delivered to patients in exchange-

Leveraging the NLM map from SNOMED CT to ICD-10-CM to facilitate adoption of ICD-10-CM.

Develop and test web services to retrieve and identify the most precise ICD-10-CM code(s) for a given clinical encounter. Facilitate creation of user interfaces that 1) provide an initial shortlist of candidate codes, ideally visible on a single screen; and 2) enable code refinement. To satisfy our high-level use cases, the analysis and design process involved reviewing available maps and crosswalks, designing the rule adjudication framework, determining necessary metadata, retrieving related codes, and iteratively improving the code refinement algorithm. The Partners ICD-10-CM Search and Mapping Services (PI-10 Services) are SOAP web services written using Microsoft's.NET 4.0 Framework, Windows Communications Framework, and SQL Server 2012. The services cover 96% of the Partners problem list subset of SNOMED CT codes that map to ICD-10-CM codes and can return up to 76% of the 69,823 billable ICD-10-CM codes prior to creation of custom mapping rules. We consider ways to increase 1) the coverage ratio of the Partners problem list subset of SNOMED CT codes and 2) the upper bound of returnable ICD-10-CM codes by creating custom mapping rules. Future work will investigate the utility of the transitive closure of SNOMED CT codes and other methods to assist in custom rule creation and, ultimately, to provide more complete coverage of ICD-10-CM codes. ICD-10-CM will be easier for clinicians to manage if applications display short lists of candidate codes from which clinicians can subsequently select a code for further refinement. The PI-10 Services support ICD-10 migration by implementing this paradigm and enabling users to consistently and accurately find the best ICD-10-CM code(s) without translation from ICD-9-CM.

Binding SNOMED CT terms to archetype elements. Establishing a baseline of results.

This article is part of the Focus Theme of METHODS of Information in Medicine on "Managing Interoperability and Complexity in Health Systems". The proliferation of archetypes as a means to represent information of Electronic Health Records has raised the need of binding terminological codes - such as SNOMED CT codes - to their elements, in order to identify them univocally. However, the large size of the terminologies makes it difficult to perform this task manually. To establish a baseline of results for the aforementioned problem by using off-the-shelf string comparison-based techniques against which results from more complex techniques could be evaluated. Nine Typed Comparison METHODS were evaluated for binding using a set of 487 archetype elements. Their recall was calculated and Friedman and Nemenyi tests were applied in order to assess whether any of the methods outperformed the others. Using the qGrams method along with the 'Text' information piece of archetype elements outperforms the other methods if a level of confidence of 90% is considered. A recall of 25.26% is obtained if just one SNOMED CT term is retrieved for each archetype element. This recall rises to 50.51% and 75.56% if 10 and 100 elements are retrieved respectively, that being a reduction of more than 99.99% on the SNOMED CT code set. The baseline has been established following the above-mentioned results. Moreover, it has been observed that although string comparison-based methods do not outperform more sophisticated techniques, they still can be an alternative for providing a reduced set of candidate terms for each archetype element from which the ultimate term can be chosen later in the more-than-likely manual supervision task.

Evaluating the impact of pre-annotation on annotation speed and potential bias: natural language processing gold standard development for clinical named entity recognition in clinical trial announcements

ObjectiveTo present a series of experiments: (1) to evaluate the impact of pre-annotation on the speed of manual annotation of clinical trial announcements; and (2) to test for potential bias, if pre-annotation is utilized.MethodsTo build the gold standard, 1400 clinical trial announcements from the clinicaltrials.gov website were randomly selected and double annotated for diagnoses, signs, symptoms, Unified Medical Language System (UMLS) Concept Unique Identifiers, and SNOMED CT codes. We used two dictionary-based methods to pre-annotate the text. We evaluated the annotation time and potential bias through F-measures and ANOVA tests and implemented Bonferroni correction.ResultsTime savings ranged from 13.85% to 21.5% per entity. Inter-annotator agreement (IAA) ranged from 93.4% to 95.5%. There was no statistically significant difference for IAA and annotator performance in pre-annotations.ConclusionsOn every experiment pair, the annotator with the pre-annotated text needed less time to annotate than the annotator with non-labeled text. The time savings were statistically significant. Moreover, the pre-annotation did not reduce the IAA or annotator performance. Dictionary-based pre-annotation is a feasible and practical method to reduce the cost of annotation of clinical named entity recognition in the eligibility sections of clinical trial announcements without introducing bias in the annotation process.

Can we improve the negative predictive value of faecal calprotectin for the diagnosis of IBS in primary care?

IntroductionRecent data has established faecal calprotectin (FC) as a highly sensitive and specific test for detecting inflammatory bowel disease (IBD) in patients referred to secondary care.1 Computer modelling has shown...

Semantic Tagging of Medical Narratives with Top Level Concepts from SNOMED CT Healthcare Data Standard

Medical narratives written by clinicians constitute critical information in healthcare domain and are required to be correct with respect to contextual meaning. SNOMED CT (Systematized Nomenclature of Medicine -- Clinical Terms) is a standardized reference terminology that consists of 390023 SNOMED CT concepts with SNOMED CT codes. This paper describes the extraction of SNOMED CT concepts from free text discharge summary reports. For the evaluation of the medical concepts, we used 300 discharge summaries corpus provided by University of Pittsburgh Medical Centre, and compared it with the SNOMED CT concept file which is a preprocessed and cleaned file listing SNOMED CT concepts. In this paper we present the ongoing research on SNOMED CT concept extraction from discharge summaries using natural language processing and introducing SNOMED CT core concepts as a single gazetteer list for concept extraction. Out of 390023 concepts, 21563 concepts were found in the test set of discharge summaries from the SNOMED CT core concepts gazetteer list. A modified approach extracted the 23 top level concept tags which will be useful for linguist analysis research.