Information retrieval at the millenium.

W Hersh

Home/Archive/PubMed

PubMed · 9929180

Information retrieval at the millenium.

W Hersh

View original source ↗Export metadata ↓

Abstract

Information retrieval systems were among the first medical informatics applications, yet their use has changed substantially in this decade with the growth of end-user computers and the Internet. While early challenges revolved around how to increase the amount of information available in electronic form, more recent challenges center on how to manage the growing volume. Traditional information retrieval issues--such as how to organize and index information to make it more retrievable as well as how to evaluate the effectiveness of systems--are still as pertinent as ever.

Explore related subjects

Abstracting and Indexing Information Storage and Retrieval Internet Research Vocabulary, Controlled Journal Article Review

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

W Hersh. 1998. Information retrieval at the millenium.. https://pubmed.ncbi.nlm.nih.gov/9929180/

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2003

PRECIS: protein reports engineered from concise information in SWISS-PROT.

MOTIVATION: There have been several endeavours to address the problem of annotating sequence data computationally, but the task is non-trivial and few tools have emerged that gather useful information on a given sequence, or set of sequences, in a simple and convenient manner. As more genome projects bear fruit, the mass of uncharacterized sequence data accumulating in public repositories grows ever larger. There is thus a pressing need for tools to support the process of automatic analysis and annotation of newly determined sequences. With this in mind, we have developed PRECIS, which automatically creates protein reports from sets of SWISS-PROT entries, collating results into structured reports, detailing known biological and medical information, literature and database cross-references, and relevant keywords.

Abstracting and Indexing↗

PubMed2003

MedScan, a natural language processing engine for MEDLINE abstracts.

MOTIVATION: The importance of extracting biomedical information from scientific publications is well recognized. A number of information extraction systems for the biomedical domain have been reported, but none of them have become widely used in practical applications. Most proposals to date make rather simplistic assumptions about the syntactic aspect of natural language. There is an urgent need for a system that has broad coverage and performs well in real-text applications. RESULTS: We present a general biomedical domain-oriented NLP engine called MedScan that efficiently processes sentences from MEDLINE abstracts and produces a set of regularized logical structures representing the meaning of each sentence. The engine utilizes a specially developed context-free grammar and lexicon. Preliminary evaluation of the system's performance, accuracy, and coverage exhibited encouraging results. Further approaches for increasing the coverage and reducing parsing ambiguity of the engine, as well as its application for information extraction are discussed.

Abstracting and Indexing↗

PubMed2003

A pilot study of contextual UMLS indexing to improve the precision of concept-based representation in XML-structured clinical radiology reports.

OBJECTIVE: Despite the advantages of structured data entry, much of the patient record is still stored as unstructured or semistructured narrative text. The issue of representing clinical document content remains problematic. The authors' prior work using an automated UMLS document indexing system has been encouraging but has been affected by the generally low indexing precision of such systems. In an effort to improve precision, the authors have developed a context-sensitive document indexing model to calculate the optimal subset of UMLS source vocabularies used to index each document section. This pilot study was performed to evaluate the utility of this indexing approach on a set of clinical radiology reports. DESIGN: A set of clinical radiology reports that had been indexed manually using UMLS concept descriptors was indexed automatically by the SAPHIRE indexing engine. Using the data generated by this process the authors developed a system that simulated indexing, at the document section level, of the same document set using many permutations of a subset of the UMLS constituent vocabularies. MEASUREMENTS: The precision and recall scores generated by simulated indexing for each permutation of two or three UMLS constituent vocabularies were determined. RESULTS: While there was considerable variation in precision and recall values across the different subtypes of radiology reports, the overall effect of this indexing strategy using the best combination of two or three UMLS constituent vocabularies was an improvement in precision without significant impact of recall. CONCLUSION: In this pilot study a contextual indexing strategy improved overall precision in a set of clinical radiology reports.

Abstracting and Indexing↗