Download presentation
Presentation is loading. Please wait.
1
PolyAnalyst Data and Text Mining tool
2
Megaputer Intelligence
Knowledge discovery tools for business users Easy-to-understand actionable results Data Overload Useful Knowledge
3
PolyAnalyst capabilities
4
Two types of PolyAnalyst users
Decision Maker Interactive up-to-date reports Data Analyst Visual data analysis scenarios
5
Text Mining in Pharma Industry
Post-marketing: Call Center and other VOC data analysis Drug safety reports analysis Doctor detailing notes analysis Pre-clinical and clinical: Research literature analysis Clinical studies reports analysis IP documents analysis General Survey analysis Competitive intelligence Compliance analysis
6
Visual creation of data analysis scenarios
Drag&Drop; Configure; Execute
7
Handled Data Sources Use ODBC and OLE DB protocols to connect to any
Popular databases (Oracle, MS SQL Server) Statistical systems (SAS, SPSS) Spreadsheets (MS Excel, Lotus) Documents in a file system: PDF, HTML, RTF, TXT, ZIP PubMed External Internet sources RSS feeds Visually integrate data from disparate data sources
8
External or user-built thesauri
PolyAnalyst Dictionary Manager supports and exploits standard medical thesauri: MedDRA MeSH SNOMED CT
9
Dictionary Editor The user can view and edit lists of synonyms and other semantic relationships
10
Pattern Definition Language
Facilitates defining patterns in terms of: Proximity (N terms, sentences, paragraphs) Sequence Negations Sentiment Synonyms Hierarchical thesaurus relations Phonetics Regular expressions Morphology Pattern Definition Language functions
11
Advanced search engine
Supports PDL-based searching
12
Sentiment Analysis Reveals positive or negative tonality of text
13
Negation Detection Detects when negation changes text meaning
14
Keyword extraction Frequently encountered terms and phrases
15
Link Analysis Correlations of terms on the document, paragraph or sentence level
16
Term cluster layout Isolation of clusters of correlated terms
17
Document clustering - statistics
Distribution of documents by discovered clusters
18
Document clustering - results
Automatically discovers groups of similar documents
19
Document clustering - results
Shows distribution of automatically discovered topics
20
Taxonomy building Hierarchical clustering helps build a tentative taxonomy the user can edit
21
Taxonomy categorization
Monitoring data for known issues of importance
22
Multi-dimensional analysis
Displays distribution of articles across multiple dimensions
23
Drill-down on text dimensions
Drill-down: Immune Diseases => Cytoxan => Globulin (3 cases)
24
OLAP matrix Distribution of problems by product
25
Report Editor summarizes results
Add results of performed analysis on report canvas
26
Interactive Dashboard for executives
Decision makers see and manipulate up-to-date key results
27
Interactive Dashboard for executives
Drill down to specific issues
28
Interactive Dashboard for executives
View correlations between Drugs and Medical Conditions
29
Benefits Dramatic cost reduction
Increase in quality and speed of the analysis Objective and uniform data-driven analysis Discovery of even unexpected issues suggested by data Automated monitoring of known problems Timely discovery of newly developing issues Utilization of 100% of available data: structured and text Up-to-date reports for executives Easy to use and maintain solution
30
Select Customers Government Insurance Financial High Tech
Pharmaceutical Marketing Manufacturing
31
1600 W Bloomfield Road, Suite E
Contacting Megaputer Call (812) or 1600 W Bloomfield Road, Suite E Bloomington, IN USA
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.