Automatic Concept Indexing and Classification

1
Automatic Concept Indexing and Classification

• for Improved Retrieval in the
• Hazardous Substances Data Bank
• Doszkocs, Tamas Chang, Hua Florence Aronson,
  Alan Thomas, Phillip,
• National Library of Medicine 
• Wilder, Dean, MSD, Inc. 
• Zamora, Antonio, Consultant 

2
Hazardous Substances Data Bank Search
3

4
HSDB radon record for query small-cell
carcinomas
5
HSDB Automatic MeSH Indexing
6
HSDB MeSH Indexing and Search Prototype
7
small-cell carcinomas query result
8
Focus Results by MeSH Headings
9
View Results by MeSH headings
10
Narrow Search by air pollutants, radioactive
11
View Results by Semantic Types (MeSH)
12
Radon and Air pollution, indoor
13
Radon HSDB Record
14
Future Plans

• Scale HSDB Automatic UMLS/MeSH Indexing
  Experiment
• Refine MetaMap Selection Algorithm
• Utilize Noun Phrase Parser(s) for non-UMLS/MeSH
  Concepts
• Incorporate AI Algorithms
• Test/Evaluate
• Integrate into TOXNET Production System

15
Automatic Concept Indexing and Classification

• for Improved Retrieval in the
• Hazardous Substances Data Bank
• Doszkocs, Tamas Chang, Hua Florence Aronson,
  Alan Thomas, Phillip,
• National Library of Medicine 
• Wilder, Dean, MSD, Inc. 
• Zamora, Antonio, Consultant