Supervised machine learning and hematology parameters for blood culture classification

Benjamin Mcfadden

Research output: ThesisMaster's Thesis

26 Downloads (Pure)

Abstract

Bloodstream infections are a significant cause of morbidity and mortality around the world. Identification of bacteria in the blood using blood cultures is the preferred method of laboratory testing. In the clinical setting, many blood cultures are requested, which results in a low positive yield. With the significant damage to patients and the rise of antimicrobial resistance, it is critical that new methods are utilised to identify the presence of pathogenic organisms in the blood. This thesis explores the use of machine learning to predict positive blood culture results from routinely collected blood tests.
Original languageEnglish
QualificationMasters
Awarding Institution
  • The University of Western Australia
Supervisors/Advisors
  • Reynolds, Mark, Supervisor
  • Inglis, Tim, Supervisor
Thesis sponsors
Award date3 Sep 2021
DOIs
Publication statusUnpublished - 2021

Fingerprint

Dive into the research topics of 'Supervised machine learning and hematology parameters for blood culture classification'. Together they form a unique fingerprint.

Cite this