Speaker:
Natalie landry. clinical biochemistry fellow. university of manitoba.
Natalie Landry is in the final year of her fellowship in Clinical Biochemistry in the Post-Graduate Medical Education Program at the University of Manitoba. She has been actively engaged in undergraduate medical education about the clinical laboratory, including the Choosing Wisely Students & Trainees Advocating for Resource Stewardship (STARS) program. She has also been involved in laboratory informatics and process improvements at Shared Health Manitoba, where she has leveraged her background in bioinformatics and computer science to improve laboratory pre-analytics and utilization
Overview:
Machine Learning is a type of Artifical Intelligence (Al) which enables computer programs to learn and infer from data inputs without continuous human programming. This powerful tool can be used to predict, classify, and estimate outcomes from large datasets which would otherwise be too unwieldy to analyze. As demand for laboratory services continues to increase, and the data generated follows suit, the potential for Machine Learning in the clinical laboratory is certainly appealing. This presentation will serve as a broad review of the types of Machine Learning algorithms and their potential application to improve clinical, analytical, and operational processes in the laboratory.
Objectives:
At the end of this activity, participants will be able to:
- Define and identify sources of “Big Data”
- Compare and contrast the 4 main categories of Machine Learning algorithms.
- Recognize the types of problems in the clinical laboratory that can be addressed using Machine Learning.