Scalable Methodologies for Distributed Development of Logic-Based Convergent Medical Terminology

Natural Language Processing methods and systems for biomedical ontology learning

While the biomedical informatics community widely acknowledges the utility of domain ontologies, there remain many barriers to their effective use. One important requirement of domain ontologies is that they must achieve a high degree of coverage of the domain concepts and concept relationships. However, the development of these ontologies is typically a manual, time-consuming, and often error-prone process. Limited resources result in missing concepts and relationships as well as difficulty in updating the ontology as knowledge changes. Methodologies developed in the fields of Natural Language Processing, information extraction, information retrieval and machine learning provide techniques for automating the enrichment of an ontology from free-text documents. In this article, we review existing methodologies and developed systems, and discuss how existing methods can benefit the development of biomedical ontologies.

Overview and utilization of the NCI thesaurus

The NCI Thesaurus is a reference terminology covering areas of basic and clinical science, built with the goal of facilitating translational research in cancer. It contains nearly 110 000 terms in approximately 36000 concepts, partitioned in 20 subdomains, which include diseases, drugs, anatomy, genes, gene products, techniques, and biological processes, among others, all with a cancer-centric focus in content, and originally designed to support coding activities across the National Cancer Institute. Each concept represents a unit of meaning and contains a number of annotations, such as synonyms and preferred name, as well as annotations such as textual definitions and optional references to external authorities. In addition, concepts are modelled with description logic (DL) and defined by their relationships to other concepts; there are currently approximately 90 types of named relations declared in the terminology. The NCI Thesaurus is produced by the Enterprise Vocabulary Services project, a collaborative effort between the NCI Center for Bioinformatics and the NCI Office of Communications, and is part of the caCORE infrastructure stack (http://ncicb.nci.nih.gov/NCICB/core). It can be accessed programmatically through the open caBIO API and browsed via the web (http://nciterms.nci.nih.gov). A history of editing changes is also accessible through the API. In addition, the Thesaurus is available for download in various file formats, including OWL, the web ontology language, to facilitate its utilization by others.

AIM: a personal view of where I have been and where we might be going

My own career in medical informatics and AI in medicine has oscillated between concerns with medical records and concerns with knowledge representation with decision support as a pivotal integrating issue. It has focused on using AI to organise information and reduce 'muddle' and improve the user interfaces to produce 'useful and usable systems' to help doctors with a 'humanly impossible task'. Increasingly knowledge representation and ontologies have become the fulcrum for orchestrating re-use of information and integration of systems. Encouragingly, the dilemma between computational tractability and expressiveness is lessening, and ontologies and description logics are joining the mainstream both in AI in Medicine and in Intelligent Information Management generally. It has been shown possible to scale up ontologies to meet medical needs, and increasingly ontologies are playing a key role in meeting the requirements to scale up the complexity of clinical systems to meet the ever increasing demands brought about by new emphasis on reduction of errors, clinical accountability, and the explosion of knowledge on the Web.

Accessing heterogeneous sources of evidence to answer clinical questions

The large and rapidly growing number of information sources relevant to health care, and the increasing amounts of new evidence produced by researchers, are improving the access of professionals and students to valuable information. However, seeking and filtering useful, valid information can be still very difficult. An online information system that conducts searches based on individual patient data can have a beneficial influence on the particular patient's outcome and educate the healthcare worker. In this paper, we describe the underlying model for a system that aims to facilitate the search for evidence based on clinicians' needs. This paper reviews studies of information needs of clinicians, describes principles of information retrieval, and examines the role that standardized terminologies can play in the integration between a clinical system and literature resources, as well as in the information retrieval process. The paper also describes a model for a digital library system that supports the integration of clinical systems with online information sources, making use of information available in the electronic medical record to enhance searches and information retrieval. The model builds on several different, previously developed techniques to identify information themes that are relevant to specific clinical data. Using a framework of evidence-based practice, the system generates well-structured questions with the intent of enhancing information retrieval. We believe that by helping clinicians to pose well-structured clinical queries and including in them relevant information from individual patients' medical records, we can enhance information retrieval and thus can improve patient-care.

Evaluation of the clinical LOINC (Logical Observation Identifiers, Names, and Codes) semantic structure as a terminology model for standardized assessment measures

OBJECTIVE

The purpose of this study was to test the adequacy of the Clinical LOINC (Logical Observation Identifiers, Names, and Codes) semantic structure as a terminology model for standardized assessment measures.

METHODS

After extension of the definitions, 1, 096 items from 35 standardized assessment instruments were dissected into the elements of the Clinical LOINC semantic structure. An additional coder dissected at least one randomly selected item from each instrument. When multiple scale types occurred in a single instrument, a second coder dissected one randomly selected item representative of each scale type.

RESULTS

The results support the adequacy of the Clinical LOINC semantic structure as a terminology model for standardized assessments. Using the revised definitions, the coders were able to dissect into the elements of Clinical LOINC all the standardized assessment items in the sample instruments. Percentage agreement for each element was as follows: component, 100 percent; property, 87.8 percent; timing, 82.9 percent; system/sample, 100 percent; scale, 92.6 percent; and method, 97.6 percent.

DISCUSSION

This evaluation was an initial step toward the representation of standardized assessment items in a manner that facilitates data sharing and re-use. Further clarification of the definitions, especially those related to time and property, is required to improve inter-rater reliability and to harmonize the representations with similar items already in LOINC.