The MTI system consists of software for applying alternative methods of discovering MeSH headings for citation titles and abstracts and then combining them into an ordered list of recommended indexing terms. The top portion of the diagram consists of three paths, or methods, for creating a list of recommended indexing terms: MetaMap Indexing, Trigrams and PubMed Related Citations. The first two paths actually compute UMLS Metathesaurus^® concepts which are passed to the Restrict to MeSH process. The results from each path are weighted and combined using the Clustering process. The system is highly parameterized not only by path weights but also by several parameters specific to the Restrict to MeSH and Clustering processes.

A prototype MTI system described below had two additional indexing methods which were removed because their results were subsumed by the three remaining methods.

Please Note:The image below has hot links to the descriptions of the various methods and processes. You can also find these descriptions by selecting the appropriate entry from the "Descriptions" section just to the right.

---

Related Publications:

• The NLM Indexing Initiative's Medical Text Indexer:
  Alan R. Aronson, James G. Mork, Clifford W. Gay, Susanne M. Humphrey, Willie J. Rogers,
  MedInfo 2004     (54kb)
  
  
• Evaluation of French and English MeSH Indexing Systems with a Parallel Corpus, AMIA 2005     (50kb)
  
  
• From Indexing the Biomedical Literature to Coding Clinical Text: Experience with MTI and Machine Learning Approaches, BioNLP 2007     (158kb)

• Summary of Threshold Studies, July 2006    (665 kb)
  
  
• Medical Text Indexer (MTI) Processing Flow    (503 kb)
  
  
• A MEDLINE Indexing Experiment Using Terms Suggested by MTI, June 2002     (510kb)
  
  
• User-centered Evaluation of the MTI System, 2007     (942kb)

The Indexing Initiative Prototype System consists of software for applying alternative methods of discovering MeSH headings for citation titles and abstracts and then combining them into an ordered list of recommended indexing terms. The top portion of the diagram consists of five paths, or methods, for creating a list of recommended indexing terms: the INQUERY method, MetaMap Indexing, Barrier Words with Approximate Matching, Trigrams and PubMed Related Citations. The middle three paths actually compute UMLS Metathesaurus^® concepts which are passed to the Restrict to MeSH process, and the outer two paths compute MeSH headings directly. The results from each path are weighted and combined using the Clustering process. The system is highly parameterized not only by path weights but also by several parameters specific to the Restrict to MeSH and Clustering processes.

Please Note:The image below has hot links to the descriptions of the various methods and processes. You can also find these descriptions by selecting the appropriate entry from the "Descriptions" section just to the right.