Objectives: To provide typical examples of biomedical ontologies in action, emphasizing the role played by biomedical ontologies in knowledge management, data integration and decision support. Methods: Biomedical ontologies selected for their practical impact are examined from a functional perspective. Examples of applications are taken from operational systems and the biomedical literature, with a bias towards recent journal articles. Results: The ontologies under investigation in this survey include SNOMED CT, the Logical Observation Identifiers, Names, and Codes (LOINC), the Foundational Model of Anatomy, the Gene Ontology, RxNorm, the National Cancer Institute Thesaurus, the International Classification of Diseases, the Medical Subject Headings (MeSH) and the Unified Medical Language System (UMLS). The roles played by biomedical ontologies are classified into three major categories: knowledge management (indexing and retrieval of data and information, access to information, mapping among ontologies); data integration, exchange and semantic interoperability; and decision support and reasoning (data selection and aggregation, decision support, natural language processing applications, knowledge discovery). Conclusions: Ontologies play an important role in biomedical research through a variety of applications. While ontologies are used primarily as a source of vocabulary for standardization and integration purposes, many applications also use them as a source of computable knowledge. Barriers to the use of ontologies in biomedical applications are discussed.s in

/pdf/biomedical-ontologies-in-action-role-in-knowledge-management-1ii4slhzbc.pdf

Biomedical ontologies in action: role in knowledge management, data integration and decision support.

Previous reviews of research on electronic health record (EHR) data quality have not focused on the needs of quality measurement The authors reviewed empirical studies of EHR data quality, published from January 2004, with an emphasis on data attributes relevant to quality measurement Many of the 35 studies reviewed examined multiple aspects of data quality Sixty-six percent evaluated data accuracy, 57% data completeness, and 23% data comparability The diversity in data element, study setting, population, health condition, and EHR system studied within this body of literature made drawing specific conclusions regarding EHR data quality challenging Future research should focus on the quality of data from specific EHR components and important data attributes for quality measurement such as granularity, timeliness, and comparability Finally, factors associated with poor or variability in data quality need to be better understood and effective interventions developed

Review: Electronic Health Records and the Reliability and Validity of Quality Measures: A Review of the Literature

In the "Internet Age," physicians and patients have unique technological resources available to improve the patient physician relationship. How they both utilize online medical information will influence the course of their relationship and possibly influence health outcomes. The decision-making process may improve if efforts are made to share the burden of responsibility for knowledge. Further benefits may arise from physicians who assist patients in the information-gathering process. However, further research is necessary to understand these differences in the patient physician relationship along with their corresponding effects on patient and physician satisfaction as well as clinical outcomes.

The Patient-Physician Relationship in the Internet Age: Future Prospects and the Research Agenda

Patient clustering improves efficiency of federated machine learning to predict mortality and hospital stay time using distributed electronic medical records

A data processing system and method for automatically performing prioritized nursing diagnoses from patient assessment data stores a diagnosis table containing relations between nursing diagnoses and patient characteristics, with each such relation having a corresponding probability measure. A priority table containing at least one relation between a diagnosis from a diagnosis table and a corresponding priority measure is also stored. The data processing system receives assessment data, matches assessment data with relations in the diagnosis table and constructs a potential diagnosis list including the matched diagnoses and the corresponding probability measures. The probability measure of each diagnosis in the potential diagnosis list is weighted with the priority measure corresponding to the diagnosis from the priority table. When more than one relation is provided for a diagnosis in the diagnosis table, probability measures are combined when the potential diagnosis list is constructed. The probability measures are preferably added together to combine them, and are preferably limited to a maximum value, for example, equivalent to 99%. The diagnosis table may be divided into primary and secondary diagnoses tables. Each relation in the primary diagnosis table has the same probability measure. The tables and lists of the data processing system and method preferably implemented in a relational database.

Data processing system and method for automatically performing prioritized nursing diagnoses from patient assessment data

The usefulness of digital clinical information is limited by difficulty in accessing that information. Information in electronic medical records (EMR) must be entered and stored at the appropriate level of granularity for individual patient care. However, benefits such as outcomes research and decision support require aggregation to clinical data -- "heart disease" as opposed to "S/P MI 1997" for example. The hierarchical relationships in an external reference terminology, such as SNOMED, can facilitate aggregation. This study examines whether by leveraging the knowledge built into SNOMED’s hierarchical structure, one can simplify the query process without degrading the query results.

The Use of SNOMED© CT Simplifies Querying of a Clinical Data Warehouse

A description is given of the design of an interface for QMR-DT, an evolving decision-theoretic version of Quick Medical Reference, which performs diagnostic reasoning about diseases in internal medicine. QMR-DT encompasses the part of QMR's functionality that provides differential diagnoses for a set of patient characteristics, but it uses a different algorithm to compute diagnoses. The work described includes two programs that integrate off-the-shelf speech technology with programs that manipulate medical terminology. The term identifier program uses an isolated-word, speaker-dependent speech product to provide an interface for entering medical findings into QMR-DT. Frame browser is an auxiliary program used by the developers of term identifier to examine frame structures. Frame browser was also used to experiment with a continuous-speech system. >

Building a speech interface to a medical diagnostic system

A method for determining a sufficiency of data entry in an electronic health record includes: receiving a packet of input data from a user, the input data reflecting patient problem, history, or diagnosis information; linking data elements in the packet with interface terminology data elements; mapping the interface terminology data elements corresponding to the codified data elements to data elements in a code set; sending the mapped data elements in the sample code set to a DRG encoder or DRG web service; and receiving zero or more DRGs correspond to the mapped data elements. The results of the receiving step then are conveyed back to the user so that the user may know whether sufficient data has been entered or whether additional details are necessary.

System and Method for Determining a Sufficiency of Data Entry in an Electronic Health Record

Developing automated tools for clinical information management requires an appreciation of user needs and capabilities. To address the reality of practice style variation, and the varying degree of comfort with computers in clinical users, we developed the KnowledgeBank concept. The KnowledgeBank concept includes an end-user authoring tool for clinical content in the EMR, and a web-based repository of content for sharing clinical content. We describe the early experiences of end-users using the KnowledgeBank.

Use of the WWW for distributed knowledge engineering for an EMR: the KnowledgeBank concept.

In the United States and Europe, electronic health records (EHRs) allow information technology and decision-support to facilitate the activities of clinicians and are considered an important component of health care improvement However, actual adoption of EHRs by physicians has been slow and the use of decision support has been minimal Part of the difficulty lies in the challenges that users face in capturing structured clinical information Reference and administrative terminologies have been in use for many years and provide a critical infrastructure to support reimbursement, decision-support and data analysis The problem is that physicians do not think and work using reference terminologies Interface terminologies bridge the gap between information that is in the physician's mind and information that can be interpreted by computer applications The maps from interface terminologies to appropriate reference terminologies enable advanced functionality in clinical information systems The conflict between the need for timely adoption of health information technology and the need for standardization is also relevant to the problems faced by health information technology in Africa The problem of clinicians having to communicate and/or record information in a format that is acceptable to someone else, somewhere else, leaves the true benefits of these systems beyond the reach of most in Africa There is a growing effort in the United States to produce clinically-relevant interface terminologies mapped to standards These interface terminologies can be expanded to incorporate the languages and clinical requirements of clinicians in Africa The adoption of interface terminologies will help bring the value of standard terminology and the resulting benefits of decision-support, data analysis and information retrieval to parts of the world where they are needed most

/pdf/interface-terminologies-bridging-the-gap-between-theory-and-57f9estsuq.pdf

Fred E. Masarie

Papers

The Use of SNOMED© CT Simplifies Querying of a Clinical Data Warehouse

Building a speech interface to a medical diagnostic system

System and Method for Determining a Sufficiency of Data Entry in an Electronic Health Record

Use of the WWW for distributed knowledge engineering for an EMR: the KnowledgeBank concept.

Interface terminologies: bridging the gap between theory and reality for Africa.