Medical Text Indexer (MTI)

The Medical Text Indexer (MTI) system was developed as part of the U. S. National Library of Medicine’s (NLM) Indexing Initiative. MTI produces both semi- and fully-automated indexing recommendations based on the Medical Subject Headings (MeSH®) controlled vocabulary and has been in use at NLM since mid-2000. MTI is in daily use to assist Indexers, Catalogers, and NLM’s History of Medicine Division (HMD) in their indexing efforts. Every weeknight MTI provides recommendations for 5,000 to 8,000 new citations for Indexing and processes a mixed file of approximately 9,000 old and new records for both Cataloging and HMD. MTI is also used on a regular basis to provide fully-automated keyword indexing for NLM’s Gateway meeting abstract collection which is not manually indexed. Indexers and Revisers review MTI recommendations for approximately 45% of the articles they are indexing, and the MTI recommendations are tightly integrated into the Cataloging and HMD system. Although mainly used in indexing efforts for processing MEDLINE® formatted citations consisting of identifier, title, and abstract, MTI is also capable of processing arbitrary biomedical text.

Authors

Jim Mork
Alan Aronson

Associated Institutions

U. S. National Library of Medicine

Application Domains
  • Clinical
  • Clinical records
  • Domain independent
  • Literature
Other Resource Type
Software Subtype
  • Data mining/Machine learning
  • Document/information retrieval
  • NLP / information extraction
  • Text mining
Programming Languages
  • C
  • Java
Operating Systems
  • Linux
  • OS X
  • Unix
  • Windows
Included Components
Dataset Subtype
Data Model Subtype
Online Resource Subtype
Knowledge Base Subtype
Intended User Types
  • Clinical researcher
  • Informatics researcher
  • NLP researcher or developer
  • Software developer
Citations

Aronson AR, Mork JG, Gay CW, Humphrey SM, Rogers WJ. The NLM Indexing Initiative's Medical Text Indexer . Medinfo. 2004 Sept.;2004: 268-272.
------------------------------------------------------------------------
Aronson AR, Bodenreider O, Demner-Fushman D, Fung KW, Lee VK, Mork JG, Neveol A, Peters L, Rogers WJ. From Indexing the Biomedical Literature to Coding Clinical Text: Experience with MTI and Machine Learning Approaches. Proc BioNLP Workshop 2007:105-12.
Neveol A, Shooshan SE, Mork JG, Aronson AR. Fine-Grained Indexing of the Biomedical Literature: MeSH Subheading Attachment for a MEDLINE Indexing Tool . AMIA Annu Symp Proc. 2007;:553-7
Neveol A, Shooshan SE, Humphrey SM, Rindflesch TC, Aronson AR. Multiple Approaches to Fine-Grained Indexing of the Biomedical Literature. Pacific Symposium on Biocomputing 2007 12:293-303
Neveol A, Mork JG, Aronson AR, Darmoni SJ. Evaluation of French and English MeSH Indexing Systems with a Parallel Corpus. AMIA Annu Symp Proc. 2005;:565-9.
Gay CW, Kayaalp M, Aronson AR. Semi-Automatic Indexing of Full Text Biomedical Articles. AMIA Annu Symp Proc. 2005;:271-5.
Kim GR , Aronson AR, Mork JG, Cohen BA, Lehmann CU. Application of a Medical Text Indexer to an Online Dermatology Atlas . MedInfo. 2004 Sept.;2004:.

Available Documentation
  • Web page/HTML documentation
Licensing Notes
MTI is currently not available for download. Access is available via our Interactive and Batch facilities found at skr.nlm.nih.gov.
Development Milestones

February 2, 2011 - MTI became the first line indexer for a small set of journals. This means that for these journals, MTI is acting as the indexer and not simply recommending indexing terms. The indexing that MTI provides for these journals is still manually reviewed.

Date of Latest Version