MEDLINE Categorization Algorithm
Author Information
Author(s): Darmoni Stefan J, Névéol Aurelie, Renard Jean-Marie, Gehanno Jean-Francois, Soualmia Lina F, Dahamna Badisse, Thirion Benoit
Primary Institution: CISMeF, Rouen University Hospital
Hypothesis
The objective of this work is to propose a categorization algorithm to classify a set of scientific articles indexed with the MeSH thesaurus.
Conclusion
The MEDLINE categorization algorithm can classify medical specialties in a ranked list from any MEDLINE file.
Supporting Evidence
- The algorithm can categorize scientific production of scientists or entire research laboratories.
- It was tested on 60 articles published in a specific journal.
- The top 3 medical specialties identified were information science, organization and administration, and medical informatics.
Takeaway
This study created a tool that helps organize medical articles by their specialties, making it easier to find relevant information.
Methodology
The algorithm uses semantic links between MeSH terms and metaterms to categorize articles.
Potential Biases
The validity of the semantic links may be questioned, and the contribution of CISMeF experts could introduce bias.
Limitations
No formal evaluation of the MEDLINE categorization algorithm was performed.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website