Biostats discipline needs fostering in big data era

08/11/19

Australian medical research is at risk of punching below its weight unless more attention is paid to the discipline of biostatistics, according to a paper recently published in the Medical Journal of Australia and co-authored by the CTC’s Prof Ian Marschner.

The risk to $800 million invested annually in Australian research was first raised at the International Society for Clinical Biostatistics conference in Melbourne in August 2018, the largest gathering of biostatisticians ever in Australia.

“The entire Australian medical research enterprise is at considerable risk of ‘drowning in data but starving for knowledge’,” wrote the paper’s authors, led by Associate Professor Katherine Lee and Professor John Carlin of the Clinical Epidemiology and Biostatistics Unit at the Murdoch Children’s Research Institute.

Big data challenges

Big data has increased the amount of complex and messy data, placing greater emphasis on fundamental statistical concepts and methods to extract valuable evidence, the authors argued.

“Biostatistical research develops and evaluates rigorous methods for drawing conclusions from new study designs and data types. This involves mathematical derivations and conceptualisations, simulation studies, detailed case studies, and translation of the newly developed methods for use by other researchers.

“Superficial understanding of statistics can easily lead to unscientific practice (recently characterised as ‘cargo-cult statistics’) and may be seen as responsible in large part for the current ‘crisis of reproducibility’ in research.”

Australia falling behind international standards

In the US, many major universities have departments of biostatistics. The Medical Research Council in the United Kingdom funds a national centre in biostatistics (the Medical Research Council's Biostatistics Unit), and a number of methodology hubs. Europe also has substantial streams of funding for methodological research.

In Australia, however, “there has never been systematic investment in the development of biostatistics … either in universities or via national funding schemes”, the authors wrote.

“For example, all of the Group of Eight (Go8) universities have structures that link statistics with mathematics or business, which inhibits the linkage between biostatistical and medical research that is critical for achieving excellence in the planning, conduct and analyses of medical research studies. None of the major universities has a department of biostatistics.”

Prof Marschner also noted the unfortunate trend towards non-Go8 universities mimicking these structures, such as the recent loss of an independent statistics department at Macquarie University.

What is needed

The authors acknowledge there is no quick solution, but they suggest three potential steps to take:

• Universities and research institutes need to foster the development of organisational structures with a critical mass of academic biostatisticians working both in methodology and collaborating with health researchers, as well as training opportunities and career development for biostatisticians;
• Biostatistical teaching and advanced training must keep pace with the dramatic changes in the data science landscape, to ensure that graduates have the necessary breadth of skills to support medical research in the modern era; and
• Funding bodies need to invest in biostatistical research; for example, by the creation and support of graduate and postdoctoral methodological training programs.

Read the MJA paper.