MARS and Medical Text Indexer (MTI) Test Bed

Home

---

The purpose of this Test Bed was to develop a test environment where the Indexing Initiative team could test out "real-time" processing and handling of the Office of Computer and Communications Systems (OCCS) XML (eXtensible Markup Language) formatted data files. The idea was to use the existing Medical Article Record System (MARS) automated data flow to OCCS as a platform to simulate the interaction with OCCS and allow the Indexing Initiative team to finalize development of a system that will eventually interface directly with OCCS.

Goals of the Test Bed:

The system must be able to handle the test bed flow without hesitation, be able to run without human monitoring, provide near 100% uptime, and provide 100% accuracy integrating our recommendations into the existing data file without injecting inconsistencies in the data file.

The Test Bed:

The test bed involved the following:

1. Transmittal of final validated XML based file from MARS to MTI at approximately the same time as they are transmitted to OCCS.
   
   
2. Automatic detection and validation of the MARS transmitted file by the MTI.
   
   
3. Processing and final recommendations made by the MTI and reintegrated into the MARS file.
   
   
4. MTI Validation prior to transmittal back to MARS.
   
   
5. MTI transmittal of the file back to MARS.
   
   
6. MARS validation of the file from MTI - offline from production system. Batch processed with email every couple of days -- more frequently at beginning, tapering off towards the end of the experiment.
   1. Verification of receipt
   2. Validation of file format to ensure that no inconsistencies were added to the file.
      
      
7. Transmittal of MARS validation report back to MTI denoting any deficiencies found.

Results of the Test:

Overall, the MTI worked as planned. We were able to identify batch files sent from MARS, validate the input files, process all of the citations from the batch files, identify and integrate our recommendations, validate our reintegrated file, and transfer the batch files (now with MTI recommendations) back to MARS on average in less than five (5) minutes time.

The Indexing Initiative team has also developed the following as a result of the test bed creation:

• A working XML (eXtensible Markup Language) DTD (Document Type Definition) that is 100% compatible with the current NLM DTD.
• An integrated XML/DTD validator.

Valuable information was also garnered as to "normal" operating procedures to expect in a production environment. We were able to identify typical batch sizes, beginning and ending of processing day, and that jobs are sporadic throughout the day versus all showing up at the end of day.

MARS and the Medical Text Indexer (MTI) Test Bed Results Summary     (195kb)

Last Modified: October 09, 2007							ii-public
Links to Our Sites MetaMap Public Release NEW: Distributable version of the actual MetaMap program. Indexing Initiative (II) Investigating computer-assisted and fully automatic methodologies for indexing biomedical text. Includes the NLM Medical Text Indexer (MTI). Semantic Knowledge Representation (SKR) Develop programs to provide usable semantic representation of biomedical text. Includes the MetaMap and SemRep programs. MetaMap Transfer (MMTx) Java-Based distributable version of the MetaMap program. Word Sense Disambiguation (WSD) Test collection of manually curated MetaMap ambiguity resolution in support of word sense disambiguation research. Medline Baseline Repository (MBR) Static MEDLINE Baselines for use in research involving biomedical citations. Allows for query searches and test collection creation.
	Lister Hill National Center for Biomedical Communications			U.S. National Library of Medicine			National Institutes of Health
							Department of Health and Human Services
Contact Us    |   Copyright    |   Privacy    |   Accessibility    |   Freedom of Information Act    |   USA.gov