China
Africa
Explore chapters and articles related to this topic
Optimizing Medication Use through Health Information Technology
Published in Salvatore Volpe, Health Informatics, 2022
Troy Trygstad, Mary Ann Kliethermes, Anne L. Burns, Mary Roth McClurg, Marie Smith, John Easter
The Unified Medical Language System (UMLS) is sponsored by the National Library of Medicine (NLM) and has focused its efforts of late on enabling interoperability between often disparate proprietary and non-proprietary classification systems embedded within electronic medical and other health records systems. In addition to classifying diseases and procedures, relationships are defined between terms to create ontological structures. The Systematized Nomenclature of Medicine-Clinical Terms (SNOMED-CT), maintained by the International Health Terminology Standards Development Organization (IHTSDO), and RxNorm, produced by the (NLM) itself, are probably the most well-known and widely used ontologies in the US healthcare system, with the latter being used to classify pharmaceuticals to aid interoperable functions such as electronic prescribing and computerized physician order entry systems.
Discussion
Published in Helis Miido, The Integrated Medical Library, 2020
In reviewing the results of this survey, the first impression may be one of disorder and disarray. However, on closer examination, what initially seemed as disorder turns out in fact to be anticipation of future technological improvements, as networks and gateways are developed. Libraries today are not restricted to using their own database if they can communicate with another database that provides functions that theirs lacks. Furthermore, if the communication is such that there is a common language used to access both the internal systems and external databases, then there is no necessity for the internal and external databases to be similar in other aspects. The Unified Medical Language System project at NLM is an attempt to facilitate the retrieval and integration of information from many machine-readable information sources, including descriptions of the biomedical literature, clinical records, factual databanks, and medical knowledge bases. Assuming that diversity will continue to exist in the biomedical community, the project seeks to provide products that can compensate for differences in the vocabularies or coding schemes used in different systems, as well as for differences in the terminology employed by system users without imposing either a single standard vocabulary, a single standard record format, or a single medical knowledge base on the biomedical community.
Intelligent Data Analysis Techniques
Published in Arvind Kumar Bansal, Javed Iqbal Khan, S. Kaisar Alam, Introduction to Computational Health Informatics, 2019
Arvind Kumar Bansal, Javed Iqbal Khan, S. Kaisar Alam
Ontology is concerned about the study of entities, their relationships, and equivalence of the groups of entities and relationships. In health science, it has tremendous application as the same concept may be expressed using multiple phrases by different healthcare providers. Ontology requires word-sense disambiguation in a domain and concepts, and traversing up and down the class-hierarchical relationship to derive if two words or phrases are related. UMLS (Unified Medical Language System) is a dataware house of medical terms and relations. It contains a meta-thesaurus, semantic network of entities, their relationships and specialist lexicons. To derive similarity between two concepts, various similarity-measures are used. Similarity-measures are based upon the distance of the two concepts in the semantic network or the information content. Ontology formation is based upon building the semantic network using the relationships and developing the hierarchical tree using “is-a” relationship.
Treatment characteristics among patients with binge-eating disorder: an electronic health records analysis
Published in Postgraduate Medicine, 2023
William M. Spalding, Monica L. Bertoia, Cynthia M. Bulik, John D. Seeger
An International Classification of Diseases (ICD) code for BED was introduced in 2016 in ICD-10. Without a specific code for BED in ICD-9 (previously under the general ICD-9 code 307.50 [Eating Disorder, Not Otherwise Specified]) during the timeframe that this study was conducted, patients with BED were identified using an algorithm comprised of NLP terms. The NLP system was used to extract and organize concepts, attributes, sentiments, and modifiers related to BED from free text clinical notes. The system was developed using vocabulary from the Unified Medical Language System, which includes multiple medical dictionaries (eg, the Logical Observation Identifiers Names and Codes, the Systematized Nomenclature of Medicine–Clinical Terms, and RxNorm [a listing of generic and branded drugs]). The NLP system is updated regularly and supplemented with new terms and information as refinements are identified. The architecture of the NLP system is based on the OASIS Unstructured Information Management Architecture [27] and is similar to other previously described systems [28]. The types of NLP concepts included medications; clinical measurements; diagnostic and therapeutic procedures; and signs, diseases, and symptoms. Modifiers of the NLP concepts included sentiments (eg, negations, affirmations), descriptive attributes (eg, stage, grade, severity, duration), and the notes section (eg, medical history, history of current illness, assessments, plans).
Prognostic elements extraction from documents to detect prognostic stage
Published in Computer Methods in Biomechanics and Biomedical Engineering, 2022
Pratiksha R. Deshmukh, Rashmi Phalnikar
Dictionary creation is used for the feature selection process. It includes variations in clinical terms, spelling, and negation identification. Variations in representation: Clinical data can be described in distinct forms, distinct in context, and their description vary from institute to institute such as the clinical term ‘grade-I’ can be represented differently like, ‘low grade’, ‘well differentiated’, ‘slow growing grade’, in various reports. Because of this, a dictionary is developed for all cancer-related clinical terminology and has many synonyms. For the development of the dictionary, a unified medical language system and our previous work for contextual identification of clinical terms (Deshmukh and Phalnikar 2018) are also referred.Variations in spelling: It is observed that as there are variations in the spelling of clinical terms, such as the clinical term ER is represented as ‘estrogen receptor’ or ‘oestrogen receptor’ in some reports hence this study includes clinical terms’ spelling variations.Negation identification: This feature identifies negation words from records such as 'no sign of malignancy', 'not identified', 'abnormal', 'free from malignant'. To identify negation, Negex algorithm is proposed by Chapman et al. (2001), but the proposed framework provides a dictionary for that.
Multi-feature fusion method for medical image retrieval using wavelet and bag-of-features
Published in Computer Assisted Surgery, 2019
Liu Shuang, Chen Deyun, Chen Zhifeng, Pang Ming
To improve the performance of CBIR for a medical image, machine learning has been used in pre-filtering image and statistical similarity has been used in the matching of multi-feature between query image and database [9]. UMLS is a successful medical image retrieval system which has a structured learning framework and modular design based on support vector machine. To find out the possible lesion region in brain images, domain knowledge has been used in retrieving the image sequence. A boosting framework has been proposed to improve the performance of medical image retrieval. Evaluation results show that this method has a high retrieval accuracy with a low computational cost [10].