Machine learning for COVID-19 diagnosis and prognostication: lessons for amplifying the signal whilst reducing the noise
Since the emergence of Coronavirus Disease 2019 (COVID-19), researchers in machine learning and radiology have rushed to develop algorithms that could assist with diagnosis, triage and management of the disease (1). As a result, thousands of diagnostic and prognostic models using chest radiographs and computed tomography (CT) have been developed. However, with no standardised approach to development or evaluation, it is difficult, even for experts, to determine which models may be of most clinical benefit. In this work, we share our main concerns and present some possible solutions. ; NIHR Cambridge Biomedical Research Centre; the EPSRC; the BHF; CRUK National Cancer Imaging Translational Accelerator (NCITA) [C22479/A28667]; Intel Corporation; the DRAGON consortium, which received funding from the Innovative Medicines Initiative 2 Joint Undertaking (JU) under grant agreement No 101005122, and the Cambridge Mathematics of Information in Healthcare (CMIH) Hub EP/T017961/1. The Philip Leverhulme Prize, the Royal Society Wolfson Fellowship, the EPSRC grants EP/S026045/1 and EP/T003553/1, EP/N014588/1, the Wellcome Innovator Award RG98755, European Union Horizon 2020 research and innovation programme under the Marie Skodowska- Curie grant agreement No. 777826 NoMADS, the Cantab Capital Institute for the Mathematics of Information and the Alan Turing Institute.