AUTHOR=Al-Hindawi Ahmed , Abdulaal Ahmed , Rawson Timothy M. , Alqahtani Saleh A. , Mughal Nabeela , Moore Luke S. P. TITLE=COVID-19 Prognostic Models: A Pro-con Debate for Machine Learning vs. Traditional Statistics JOURNAL=Frontiers in Digital Health VOLUME=Volume 3 - 2021 YEAR=2021 URL=https://www.frontiersin.org/journals/digital-health/articles/10.3389/fdgth.2021.637944 DOI=10.3389/fdgth.2021.637944 ISSN=2673-253X ABSTRACT=The SARS-CoV-2 virus causing the COVID-19 pandemic has had an unprecedented impact on healthcare requiring multi-disciplinary innovation and novel thinking to minimise impact and improve outcomes. Wide ranging disciplines have collaborated including diverse clinicians (radiology, microbiology, critical care) working increasingly closely with data-science. This has been leveraged through the democratisation of data-science with increasing availability of easy to access open datasets, tutorials, programming languages and hardware it is significantly easier to create mathematical models. To address the COVID-19 pandemic, such data-science has enabled modelling of the impact of the virus on the population and on individuals for diagnostic, prognostic, and epidemiological ends. This has led to two large systematic reviews on this topic that have highlighted the two different ways in which this feat has been attempted: one using classical statistics and the other using more novel machine learning techniques. In this review, we debate the relative strengths and weaknesses of each method towards the specific task of predicting COVID-19 outcomes.