Enhanced Laboratory Diagnosis of Human Chlamydia Pneumoniae Infection through Patter Recognition Derived from Pathology Database Analysis

Alice Richardson, Simon Hawkins, Fariba Shadabi, Dharmendra Sharma, John Fulcher, Brett Lidbury

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

Abstract

This study focuses on pattern recognition in pathology data collected from patients tested for Chlamydia pneumoniae (Cp) infection, with co-infection by Mycoplasma pneumoniae (Myco) also considered. Both Cp and Myco are microbes that cause respiratory disease in some infected people. As well as the immunoassay results revealing whether the patient had been infected, or not, an extensive range of other routine pathology data was also available for each patient, allowing the analysis of associations between a positive immunoassay laboratory result for Cp or Myco, and a range of tests for biochemical and cellular markers (e.g. liver enzymes, electrolyte balance, haematological indices such as red/white cell counts). Decision trees and logistic regression were used to enhance laboratory diagnosis of these respiratory infections via the formulation of association rules derived from immunoassay results and associated pathology data.
Original languageEnglish
Title of host publicationSupplementary Proceedings of the Third IAPR International Conference on Pattern Recognition in Bioinformatics (PRIB 2008)
EditorsMadhu Chetty, Shandar Ahmad, Alioune Ngom, Shyh Wei Teng
Place of PublicationAustralia
PublisherThird IAPR International Conference on Pattern Recognition in Bioinformatics
Pages227-234
Number of pages8
ISBN (Print)978073262268
Publication statusPublished - 2008
EventPRIB 2008 - Melbourne, Australia
Duration: 15 Oct 200817 Oct 2008

Conference

ConferencePRIB 2008
Country/TerritoryAustralia
CityMelbourne
Period15/10/0817/10/08

Fingerprint

Dive into the research topics of 'Enhanced Laboratory Diagnosis of Human Chlamydia Pneumoniae Infection through Patter Recognition Derived from Pathology Database Analysis'. Together they form a unique fingerprint.

Cite this