ABSTRACT
In response to the lack of readily available multimedia rich medical knowledge sources to support medical education and patient care, we designed and implemented a web-based video publishing platform. In order to promote the development of high-quality, up-to-date educational content, we have devised a scalable structure that allows online submissions and continuous updating of video and accompanying textual descriptions. Our goal is to enable experts in varied medical domains to collaborate in the construction of a video library using an intuitive web-based interface. Neurologists at Stanford built a well-annotated neurology video collection that initially emphasized childhood and adult movement disorders. The collection may be accessed either as a stand-alone resource or as part of the Stanford Skolar MD, an integrated online medical knowledge provider. This manuscript discusses the design framework and implementation details of structured media content development. We present examples illustrating media data collection, content indexing using UMLS concepts, media storage, and web presentation.
Subject(s)
Archives , Information Storage and Retrieval/methods , Video Recording , Abstracting and Indexing , Humans , Hypermedia , Internet , Movement Disorders , Multimedia , Neurology , Software , Unified Medical Language SystemABSTRACT
INTRODUCTION: We did formative evaluations of several variations to the computation of related articles for non-bibliographic resources in the medical domain. METHODS: A binary model and several variations of the vector space model were used to measure similarity between documents. Two corpora were studied, using a human expert as the gold standard. RESULTS: Variations in term weights and stopword choices made little difference to performance. Performance was worse when documents were characterized by title words alone or by MeSH terms extracted from document references. DISCUSSION: Further studies are needed to evaluate these methods in medical information retrieval systems.
Subject(s)
Information Storage and Retrieval/methods , Algorithms , Subject HeadingsABSTRACT
One of the obstacles for a successful search in the biomedical field is that different vocabularies are used by different databases but more than one database is usually needed to respond adequately to a healthcare professional's query. A typical searcher usually is unfamiliar with these vocabularies and the sophisticated measures to narrow or broaden a search. As a result, a failed search is often due to using "inappropriate" search terms. We have developed a highly interactive and versatile user interface, SHINE Refined Search (SHINE RS). It uses medical concepts from the UMLS Metathesaurus as the building block to help searchers find "appropriate" search terms for their queries. The results of our preliminary usability assessment are promising and demonstrate the potential to improve retrieval results.
Subject(s)
Information Storage and Retrieval/methods , Unified Medical Language System , User-Computer Interface , Diabetes Mellitus , Humans , Information Systems , Kidney Diseases , MEDLINE , Vocabulary, ControlledABSTRACT
OBJECTIVE: To examine the information needs of users of the Stanford Health Information Network for Education (SHINE), an integrated information retrieval (IR) system. METHODS: A subset of queries from the SHINE log were categorized into one or more of 33 categories. RESULTS: Drugs and infectious disease accounted for 25% of categorizations, and otherwise the distribution of categorizations was quite broad. CONCLUSIONS: Attention should be paid to the selection of drug information resources in medical knowledge information retrieval systems. The distribution of query categorizations also suggests that IR systems include a wide range of knowledge resources.
Subject(s)
Information Storage and Retrieval/statistics & numerical data , Information Systems/statistics & numerical data , Primary Health Care , California , Drug Therapy , Faculty, Medical , Humans , Information Services/statistics & numerical data , Internet , Medical Staff , Schools, Medical , Students, MedicalABSTRACT
OBJECTIVE: To determine the needs of community family physicians regarding electronic patient records (EPRs). DESIGN: A comprehensive survey was sent to 101 community family physicians in Hamilton, Ontario, who had expressed an interest in EPRs. RESULTS: 46 physicians responded (46%). 87% felt that an EPR would result in their providing better patient care. A wide variety of items were deemed to be important to be included on the EPR "front page". Desired functionality emphasized labs, medications, consultation, hospital follow-up and health maintenance. Family physicians tended to prefer templates to other data entry methods such as typing and dictating. Respondents were more willing to view information from the hospital than to let the hospital view information from their own offices. CONCLUSION: This survey provided useful information on the perceived EPR needs of community-based family physicians. It will be repeated post-computerization.