Datafish Multiphase Data Mining Technique to Match Multiple Mutually Inclusive Independent Variables in Large PACS Databases

Brendan P. Kelley*, Chad Klochko, Safwan Halabi, Daniel Siegal

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

Retrospective data mining has tremendous potential in research but is time and labor intensive. Current data mining software contains many advanced search features but is limited in its ability to identify patients who meet multiple complex independent search criteria. Simple keyword and Boolean search techniques are ineffective when more complex searches are required, or when a search for multiple mutually inclusive variables becomes important. This is particularly true when trying to identify patients with a set of specific radiologic findings or proximity in time across multiple different imaging modalities. Another challenge that arises in retrospective data mining is that much variation still exists in how image findings are described in radiology reports. We present an algorithmic approach to solve this problem and describe a specific use case scenario in which we applied our technique to a real-world data set in order to identify patients who matched several independent variables in our institution’s picture archiving and communication systems (PACS) database.

Original languageEnglish (US)
Pages (from-to)331-336
Number of pages6
JournalJournal of Digital Imaging
Volume29
Issue number3
DOIs
StatePublished - Jun 1 2016
Externally publishedYes

Keywords

  • Data mining
  • Databases
  • Image database
  • Imaging informatics
  • PACS
  • Software design
  • User interface

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Datafish Multiphase Data Mining Technique to Match Multiple Mutually Inclusive Independent Variables in Large PACS Databases'. Together they form a unique fingerprint.

Cite this