Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

MScanner: a classifier for retrieving Medline citations.

Graham L Poulter1, Daniel L Rubin, Russ B Altman

  • 1UCT NBN Node, Department of Molecular and Cell Biology, University of Cape Town, Cape Town, South Africa. graham.poulter@gmail.com

BMC Bioinformatics
|February 21, 2008
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Prediction of hospitalisation in young children with pneumonia in Malawi: A machine learning-based approach.

PLoS medicine·2026
Same author

An Integrative Network Analysis Framework for Identifying Altered Glycosylation Pathways Associated with Autism Spectrum Disorder.

Genes·2026
Same author

Extraction of distant recurrence sites for breast cancer patients from free-text clinical notes using large language models.

Journal of biomedical informatics·2026
Same author

Intratumoral heterogeneity in microsatellite instability status at single-cell resolution.

iScience·2026
Same author

Creation of Radiology Teaching Content with STELLA-A STandardized Electronic Learning Library and Application Platform.

Academic radiology·2025
Same author

Individuals with intellectual disability have an increased burden of <i>de novo</i> variants in <i>cis</i>-regulatory elements of glutamatergic neurons.

medRxiv : the preprint server for health sciences·2025
Same journal

OpenIMC: an open-source platform for analyzing single-cell and spatial proteomics by imaging mass cytometry.

BMC bioinformatics·2026
Same journal

NAP: an open source pipeline for cross-domain microbiome profiling using Nanopore sequencing-derived amplicon data.

BMC bioinformatics·2026
Same journal

SurvGME: an R package for survival analysis with graphical and measurement error models.

BMC bioinformatics·2026
Same journal

SimMapNet: a Bayesian framework for gene regulatory network inference using gene ontology similarities as external hint.

BMC bioinformatics·2026
Same journal

Dual channel drug-drug interactions extraction based on cross attention.

BMC bioinformatics·2026
Same journal

FeSseqdb: a curated sequence-level database and interpretable machine learning framework for identifying iron-sulfur proteins.

BMC bioinformatics·2026
See all related articles

MScanner offers a fast, non-domain-specific Bayesian classifier for Medline, improving information retrieval for complex topics. It efficiently ranks relevant articles using Medical Subject Headings (MeSH) and publication journal, achieving high precision.

Area of Science:

  • Biomedical Informatics
  • Computational Biology
  • Information Retrieval

Background:

  • Traditional keyword searching in Medline has limitations for complex topics and literature curation.
  • Existing supervised learning methods for Medline classification often lack speed, generalizability, or performance evaluation metrics.
  • There is a need for efficient, non-domain-specific tools to classify Medline records across the entire database.

Purpose of the Study:

  • To develop and evaluate MScanner, a Bayesian classifier for efficient and non-domain-specific Medline record classification.
  • To provide a user-friendly web interface for submitting training data and retrieving ranked search results.
  • To assess the performance of MScanner in classifying relevant articles for complex topics.

Main Methods:

Related Experiment Videos

  • Implemented a Bayesian classifier utilizing Medical Subject Headings (MeSH) and journal of publication for concise document representation.
  • Developed a web interface for users to submit PubMed IDs as training examples.
  • Ranked Medline records by decreasing probability of relevance and performed cross-validation against random subsets.

Main Results:

  • MScanner processed 16 million Medline records in approximately 90 seconds.
  • Cross-validation on three topics showed excellent separation of relevant and irrelevant articles, with ROC areas between 0.97 and 0.99.
  • Achieved an average precision ranging from 0.69 to 0.92, outperforming expert PubMed queries for a complex topic.

Conclusions:

  • MScanner is an effective, non-domain-specific classifier for the entire Medline database, suitable for retrieving topics with numerous relevance indicators.
  • The web interface simplifies Medline citation classification compared to topic-specific pre-filters and classifiers.
  • Open-source code and datasets are available, with the web interface accessible online.