Development of Predictive Metrics that Allow Early Detection of Poor Laboratory Performance Via Machine-Learning Algorithms to Improve Patient Outcomes and Save Health Resource - Pilot Study and Systematic Review

This page provides information related to the completed project.

Page last updated: 09 May 2017

The project was a pilot study to investigate the empirically meaningful integration of the National Association of Testing Authorities (NATA) and Quality Assurance Programmes (QAP/EQA) data, to enhance the capacity via the combined quality data sources to detect poor laboratory performance earlier and accurately. This was with the view of improving patient outcomes and effective use of health resources. This was done through a systematic review of current literature and the validation through machine learning algorithms on NATA and QAP/EQA data subsets.

Development of Predictive Metrics that Allow Early Detection of Poor Laboratory Performance Via Machine-Learning Algorithms to Improve Patient Outcomes and Save Health Resource - Pilot Study and Systematic Review (PDF 1756 KB)

Development of Predictive Metrics that Allow Early Detection of Poor Laboratory Performance Via Machine-Learning Algorithms to Improve Patient Outcomes and Save Health Resource - Pilot Study and Systematic Review (Word 3752 KB)