Resources for comparing the speed and performance of medical autocoders

Additional File 1:

A tarred and gzip-compressed collection of files used in the manuscript. The files include are: 1. omim18.pl (2,404 bytes), the Perl autocoding script 2. quickout.txt (9,540,442 bytes), the autocoded output for omim18.pl, using OMIM and an unencumbered subset of UMLS 3. goodhit.dir (4,096 bytes) and goodhit.pag (33,554,432 bytes), the database files containing the paired concept codes and terms for the unencumbered subset of UMLS 4. tiecount.pl (1,380 bytes), the perl script that counts the number of concepts and terms included in the autocoder nomenclature 5. countcon.pl (1,649 bytes), the Perl script that counts the concepts in OMIM's autocoded output file 6. finneg2.pl (4,630 bytes), the Perl script that counts the different words contained in Finnegan's Wake (by James Joyce). 7. neocl.xml (4,855,690 bytes), a publicly available taxonomy and classification for neoplasms based on the developmental lineage of tumors. 8. omimcan.pl (3,161 bytes), the Perl script that extracts all names of neoplasms contained in OMIM records matching the neoplasm taxonomy file, neocl.xml. 9. quickcan.txt (517,263), the autocoded output of omimcan.pl, using OMIM and neocl.xml Autocode.tar.gz is (9,509,278 bytes), tarred and gzipped (.tar.gz) compressed distribution file containing all the described archive files. This file can be easily decompressed with freely available software available with complete instructions from many web sites http://www.gzip.org webcite.

Format: GZ Size: 9.3MB Download file