Managing the evidence infodemic: Automation approaches used for developing NICE COVID-19 living guidelines

Background and Objectives The National Institute for Health and Care Excellence (NICE) produces evidence-based guidance and advice for health, public health and social care practitioners in England and Wales. Between March 2020 and March 2022, NICE produced 24 COVID-19 guidelines to support healthcare workers during the COVID-19 pandemic. This article outlines three automation strategies NICE utilised to facilitate faster processing of evidence on COVID-19 and describes the value of those approaches when there is an increasing volume of evidence and demand on resources. Study Design and Setting Text classification using machine learning, and regular expression-based pattern matching were used to automate screening of literature search results. Relevant clinical trials were tracked by automated monitoring of clinical trial databases and Pubmed. Results The strategies discussed here brought considerable efficiencies in the processing time without impacting on quality compared to equivalent manual efforts. Additionally, the paper illustrates how to incorporate automation into established processes of the evidence management pipeline. Conclusions We have demonstrated through testing and use in live guideline development and surveillance that these are effective and low risk approaches at managing high volumes of evidence. Highlights ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement The authors received no specific funding for this work. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable. Yes All data referred to in the manuscript are available upon reasonable request to the authors * NLP : Natural language processing ML : Machine learning API : Application programming interface