Identifying Medical Concepts in Free Text Chief Complaint Data

77 Results of a Novel National Emergency Department Chief Complaint Database

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.

Automated Analysis and Codification of Free Text Pathology Reports

In January 2003, the Westchester County Department of Health (WCDH) began conducting electronic syndromic surveillance of hospital emergency department (ED) chief complaints. Although methods for data collection and analysis used in syndromic surveillance have been described previously, minimal information exists regarding the responses to and investigations of signals detected by such systems. This paper describes WCDH's experience in responding to syndromic surveillance signals during the first 9 months after the system was implemented.The objectives of this analysis were to examine WCDH's responses to signals detected by the county's syndromic surveillance system. Specific goals were to 1) review the actual complaints reported by hospital EDs to determine whether complaint data were accurately identified and classified into syndrome categories, and provide feedback from this review to data collection and analysis staff to refine text terms or filters used to identify and classify chief complaints; 2) develop procedures and response algorithms for investigating signals; 3) determine whether signals correlated with reportable communicable diseases or other incidents of public health significance requiring investigation and intervention; and 4) quantify the staffing resources and time required to investigate signals.During January 27-October 31, 2003, electronic files containing chief-complaint data from seven of the county's 13 EDs were collected daily. Complaints were classified into syndrome categories and analyzed for statistically significant increases. A line listing of each complaint comprising each signal detected was reviewed for exact complaint, number, location, patient demographics, and requirement for hospital admission.A total of 59 signals were detected in eight syndrome categories: fever/influenza (11), respiratory (6), vomiting (11), gastrointestinal illness/diarrhea (8), sepsis (7), rash (7), hemorrhagic events (3), and neurologic (6). Line-listing review indicated that complaints routinely were incorrectly identified and included in syndrome categories and that as few as three complaints could produce a signal. On the basis of hospital, geographic, age, or sex clustering of complaints, whether the complaint indicated a reportable condition (e.g., meningitis) or potentially represented an unusual medical event, and whether rates of hospital admission were consistent with medical conditions, 34 of 59 signals were determined to require further investigation (i.e., obtaining additional information from ED staff or medical providers). Investigation did not identify any reportable communicable disease or other incidents of public health significance that would have been missed by existing traditional surveillance systems. Nine staff members spent 3 hours/week collectively investigating signals detected by syndromic surveillance.Standardized sets of text terms used to identify and classify hospital ED chief complaints into syndrome categories might require modification on the basis of hospital idiosyncrasies in recording chief complaints. Signal investigations could be reasonably conducted by using local health department resources. Although no communicable disease events were identified, the system provided baseline and timely objective data for hospital visits and improved communication among county health department and hospital ED staff.

BackgroundThe Unified Medical Language System (UMLS) has been a critical tool in biomedical and health informatics, and the year 2021 marks its 30th anniversary. The UMLS brings together many broadly used vocabularies and standards in the biomedical field to facilitate interoperability among different computer systems and applications.ObjectiveDespite its longevity, there is no comprehensive publication analysis of the use of the UMLS. Thus, this review and analysis is conducted to provide an overview of the UMLS and its use in English-language peer-reviewed publications, with the objective of providing a comprehensive understanding of how the UMLS has been used in English-language peer-reviewed publications over the last 30 years.MethodsPubMed, ACM Digital Library, and the Nursing & Allied Health Database were used to search for studies. The primary search strategy was as follows: UMLS was used as a Medical Subject Headings term or a keyword or appeared in the title or abstract. Only English-language publications were considered. The publications were screened first, then coded and categorized iteratively, following the grounded theory. The review process followed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines.ResultsA total of 943 publications were included in the final analysis. Moreover, 32 publications were categorized into 2 categories; hence the total number of publications before duplicates are removed is 975. After analysis and categorization of the publications, UMLS was found to be used in the following emerging themes or areas (the number of publications and their respective percentages are given in parentheses): natural language processing (230/975, 23.6%), information retrieval (125/975, 12.8%), terminology study (90/975, 9.2%), ontology and modeling (80/975, 8.2%), medical subdomains (76/975, 7.8%), other language studies (53/975, 5.4%), artificial intelligence tools and applications (46/975, 4.7%), patient care (35/975, 3.6%), data mining and knowledge discovery (25/975, 2.6%), medical education (20/975, 2.1%), degree-related theses (13/975, 1.3%), digital library (5/975, 0.5%), and the UMLS itself (150/975, 15.4%), as well as the UMLS for other purposes (27/975, 2.8%).ConclusionsThe UMLS has been used successfully in patient care, medical education, digital libraries, and software development, as originally planned, as well as in degree-related theses, the building of artificial intelligence tools, data mining and knowledge discovery, foundational work in methodology, and middle layers that may lead to advanced products. Natural language processing, the UMLS itself, and information retrieval are the 3 most common themes that emerged among the included publications. The results, although largely related to academia, demonstrate that UMLS achieves its intended uses successfully, in addition to achieving uses broadly beyond its original intentions.

INTRODUCTION: YouTube, the online multimedia platform, remains an untapped resource for surgical procedure content for education and research. Recent efforts to identify this content have lacked the diversity, volume and depth of the expanding corpus of surgical content on the site. We leverage computer vision (CV) and natural language processing (NLP) techniques to index and characterize the vast amount of open, non-minimally invasive surgical content on YouTube. METHODS: Twenty-three surgical procedure terms were used to programmatically query and collect videos, resulting in 9,197 results. Video-level metadata from YouTube were collected. Using a CV model and a NLP tool developed by our group, each video was analyzed for detailed scene understanding (e.g., action, tool, and hand detection) and medical and procedure tags from the Unified Medical Language System (UMLS) were generated. RESULTS: We identified 477, 270, and 556 videos related to head and neck, breast, and gastrointestinal surgery, respectively. 10.1 million frames were analyzed, and 11.9, 3.9, and 5.6 million, hands, surgical tools, and instances of surgical activity, respectively, were detected. 59,776 UMLS tags were also generated from video metadata. UMLS tags and temporal, “surgical signatures” were generated for each type and category of surgical procedures (Fig. 1).Figure 1CONCLUSION: Using novel CV and NLP techniques, we efficiently identified and characterized a large amount of open surgical videos in an automated way that exceeds previous efforts in scope, volume and depth. This technique enables the creation of a continuously expanding and comprehensive, surgical video repository to enhance surgical education and research.

Positive predictive value of an elevated cardiac troponin for type I myocardial infarction in ED patients based on the chief complaint

To describe a new chief-complaint categorization schema, the development of a computer text-parsing algorithm to automatically classify free-text chief complaints into this schema, and use of these coded chief complaints to describe the case mix of a community emergency department (ED). Coded Chief Complaints for Emergency Department Systems (CCC-EDS) is a new and untested schema of 228 chief complaints, grouped within dimensions of type and system. A computerized text-parsing algorithm for automatically reading and classifying free-text chief complaints into 1 of these 228 coded chief complaints was developed by using a consecutive derivation sample of 46,602 patients who presented to a community teaching-hospital ED in 2004. Descriptive statistics included frequency of patients presenting with the 228 coded chief complaints; percentage of free-text complaints not categorizable by the CCC-EDS; and admission rate, age, and gender differences by chief complaint. In the derivation sample, the text-parsing algorithm classified 87.5% of 45,329 ED visits with non-null free-text chief complaints into 1 of 194 coded chief complaints. The text-parsing algorithm successfully classified 87.3% of the free-text chief complaints in a validation sample. The five most common coded chief complaints were Abdominal Pain (3,734 visits), Fever (2,234), Chest Pain (2,183), Breathing Difficulty (2,030), and Cuts-Lacerations (2,028). The CCC-EDS is a new comprehensive, granular, and useful classification schema for categorizing chief complaints in an ED. A CCC-EDS text-parsing algorithm successfully classified the majority of free-text chief complaints from an ED computer log. These coded chief complaints were used to describe the case mix of a community teaching-hospital ED.

We have recently mapped the Gene Ontology (GO), developed by the Gene OntologyConsortium, into the National Library of Medicine's Unified Medical LanguageSystem (UMLS). GO has been developed for the purpose of annotating gene productsin genome databases, and the UMLS has been developed as a framework forintegrating large numbers of disparate terminologies, primarily for the purpose ofproviding better access to biomedical information sources. The mapping of GO toUMLS highlighted issues in both terminology systems. After some initial explorationsand discussions between the UMLS and GO teams, the GO was integrated with theUMLS. Overall, a total of 23% of the GO terms either matched directly (3%) orlinked (20%) to existing UMLS concepts. All GO terms now have a corresponding,official UMLS concept, and the entire vocabulary is available through the web-basedUMLS Knowledge Source Server. The mapping of the Gene Ontology, with its focuson structures, processes and functions at the molecular level, to the existing broadcoverage UMLS should contribute to linking the language and practices of clinicalmedicine to the language and practices of genomics.

This study evaluated whether emergency department (ED) patient presentations for problems related to mental and substance use disorders could be validly monitored by a syndromic surveillance system that uses chief complaints to identify mental disorders. The study used syndromic surveillance data on 146,315 ED visits to participating Fresno County, California, hospitals between January 1 and December 31, 2013. Free-text patient chief complaints are automatically classified into syndromes based on the developer's algorithms. Agreement was assessed between the algorithm's syndrome classification of mental health and substance abuse (MHSA) disorders and ICD-9-CM discharge diagnostic codes. Diagnosis and ED utilization patterns among patients with at least one visit with an MHSA syndrome classification were also examined. Approximately 8% of ED visits during the study period received an MHSA syndrome classification. Overall agreement between MHSA syndrome classification and psychiatric- or substance use-related ICD-9 discharge diagnoses was high (κ=.92, 95% confidence interval=.91-.92). Sensitivity (100%) and specificity (98.6%) of the MHSA syndrome classification were also very high. MHSA syndrome-classified patients exhibited high levels of health care and morbidity burden compared with other patients. ED chief complaints can be utilized to reliably and validly ascertain the incidence of patient presentations for mental and substance use disorders in contexts in which discharge diagnoses are not routinely available. Wider adoption of MHSA-related syndrome algorithms by syndromic surveillance systems could be valuable for public mental health surveillance, service delivery, and resource planning efforts.

Significance. Early detection of axial spondyloarthritis (axSpA) is a complex clinical task. Quality improvement of axSpA diagnostics in primary care settings is possible with the help of decision-making information systems based on the ontological approach application. The key stage of the decision-making system development consists of the elaboration of a set of clinical terms. This set should fully describe clinical area or sub-area under study. One of the essential requirements is compliance of the clinical terms used with the existing clinical nomenclatures. Currently, the largest set of clinical terms is the Unified Medical Language System (UMLS) metathesaurus. The majority of UMLS terms is presented in English only. The development of tools for the analysis of unstructured texts and recognition of clinically relevant UMLS entities make it possible to elaborate a set of terms describing axSpA diagnostic aspects. This will also help to compile a list of UMLS terminology nomenclatures for their priority adaptation and expert translation into Russian. The purpose of this study is to develop an automated system for recognizing clinically relevant UMLS terms in texts of the English-language articles. Material and methods. The research material has included English terms (11.2 million) aggregated from 76 nome6nclatures of the current UMLS (2022AB) version. In addition, the study has used texts of PubMed clinical abstracts in English. Queries to the UMLS graph model, semantic algorithms for unstructured texts and machine-learning methods have been applied for data collection and analysis. Results. The study has elaborated a set of high-accuracy regular expressions (F1-score=98%) for metadata elimination from the text corpus. Then the authors have identified patterns for searching clinically relevant terms in the aggregated set of UMLS concepts. Using a logistic regression algorithm, the authors have trained a binary classification model. Input data for the created classificatory are information about an UMLS term. Output data are a label indicating the presence or absence of clinical relevance. Conclusion. The binary classification model has been validated individually and double-tested on different data samples. Values of the accuracy, sensitivity and specificity of metrics equal to 91%, 90% and 91%, respectively, for the validation sample (a number of axSpA terms). In addition, this model has been tested on the sets of terms aggregated for any two diseases. Values of the accuracy metric equal to 91% and 90%, respectively. With the help of the developed machine-learning model, the study has estimated that UMLS contains 1.5 million unique terms applicable to describing a clinical picture. In addition, lists of priority UMLS data sources and thematic groups have been compiled. These clinically relevant UMLS terms should be adapted and translated into Russian as soon as possible.

Tracking medical students’ clinical experiences using natural language processing

ObjectivesUrinary tract infection (UTI) is common in home care but not easily captured with standard assessment. This study aimed to examine the value of nursing notes in detecting UTI signs and symptoms in home care. DesignThe study developed a natural language processing (NLP) algorithm to automatically identify UTI-related information in nursing notes. Setting and ParticipantsHome care visit notes (n = 1,149,586) and care coordination notes (n = 1,461,171) for 89,459 patients treated in the largest nonprofit home care agency in the United States during 2014. MeasuresWe generated 6 categories of UTI-related information from literature and used the Unified Medical Language System (UMLS) to identify a preliminary list of terms. The NLP algorithm was tested on a gold standard set of 300 clinical notes annotated by clinical experts. We used structured Outcome and Assessment Information Set data to extract the frequency of UTI-related emergency department (ED) visits or hospitalizations and explored time-patterns in documentation of UTI-related information. ResultsThe NLP system achieved very good overall performance (F measure = 0.9, 95% CI: 0.87-0.93) based on the test results obtained by using the notes for patients admitted to the ED or hospital due to UTI. UTI-related information was significantly more prevalent (P < .01 for all the tests) in home care episodes with UTI-related ED admission or hospitalization vs the general patient population; 81% of home care episodes with UTI-related hospitalization or ED admission had at least 1 category of UTI-related information vs 21.6% among episodes without UTI-related hospitalization or ED admission. Frequency of UTI-related information documentation increased in advance of UTI-related hospitalization or ED admission, peaking within a few days before the event. Conclusions and ImplicationsInformation in nursing notes is often overlooked by stakeholders and not integrated into predictive modeling for decision-making support, but our findings highlight their value in early risk identification and care guidance. Health care administrators should consider using NLP to extract clinical data from nursing notes to improve early detection and treatment, which may lead to quality improvement and cost reduction.

Comprehensive decade-long analysis of point-of-care resources reveals insights into how clinical research makes its way into practice across different medical specialties and through time to enable us to identify potential translational bottlenecks in the pathway from research to practice.

Mapping clinical attributes from hospital information systems to standardized terminologies may allow their scientific reuse for multicenter studies. The Unified Medical Language System (UMLS) defines synonyms in different terminologies, which could be valuable for achieving semantic interoperability between different sites. Here we aim to explore the potential relevance of UMLS concepts and associated semantic relations for widely used clinical terminologies in a German university hospital. To semi-automatically examine a sample of the 200 most frequent codes from Erlangen University Hospital for three relevant terminologies, we implemented a script that queries their UMLS representation and associated mappings via a programming interface. We found that 94% of frequent diagnostic codes were available in UMLS, and that most of these codes could be mapped to other terminologies such as SNOMED CT. We observed that all examined laboratory codes were represented in UMLS, and that various translations to other languages were available for these concepts. The classification that is most widely used in German hospital for documenting clinical procedures was not originally represented in UMLS, but external mappings to SNOMED CT allowed identifying UMLS entries for 90.5% of frequent codes. Future research could extend this investigation to other code sets and terminologies, or study the potential utility of available mappings for specific applications.