Lecturer in Data Science University of York
Lewis is a lecturer in the Hull York Medical School (HYMS) and the Department of Health Sciences. This case study, collected by the Research Data Management and Open Research team at the University of York, discusses how Lewis applied machine learning to help in healthcare research.
https://orcid.org/0000-0002-3328-5634
Applying the principles of open science to maximise the potential impact of machine learning in healthcare research
Summary
Open research promotes practice whereby all elements of the research process are transparently reported, with advances in this area including code-sharing, reporting standards, and lay-researcher involvement. However, there is a theory-practice gap in the field of health research using non-experimental (observational) data; machine learning is increasingly applied to such data, but it is often unclear how results are generated, and their replication is impossible, leading to questionable data practices and publication bias. Researchers in HYMS addressed this issue by developing an accessible, interactive website, hosting and signposting resources on open research. They also delivered workshops focusing on different aspects of open research and have embedded these principles and practical resources into postgraduate teaching, conferences, and journal editorial board practices.
The University of York has long been committed to the idea that scientific research is at its most valuable when it is ‘open’, meaning that its aims, methods, tools, execution and results are all made as freely accessible as possible. Academics in the university’s medical school were therefore quick to receive a green light when they proposed addressing a growing issue of transparency arising from recent advances in machine learning.
You can read more about this exciting project on the University of York Open Research pages.