Systematic reviews
-
Despite existing research on text mining and machine learning for title and abstract screening, the role of machine learning within systematic literature reviews (SLRs) for health technology assessment (HTA) remains unclear given lack of extensive testing and of guidance from HTA agencies. We sought to address two knowledge gaps: to extend ML algorithms to provide a reason for exclusion-to align with current practices-and to determine optimal parameter settings for feature-set generation and ML algorithms. ⋯ ML algorithms can improve the efficiency of the SLR process and the proposed algorithms could reduce the workload of a second reviewer by identifying exclusions with a relevant PICOS reason, thus aligning with HTA guidance. Downsampling can be used to improve study selection, and improvements using full-text exclusions have implications for a learn-as-you-go approach.
-
Critically ill patients receiving invasive ventilation are at risk of sputum retention. Mechanical insufflation-exsufflation (MI-E) is a technique used to mobilise sputum and optimise airway clearance. Recently, interest has increased in the use of mechanical insufflation-exsufflation for invasively ventilated critically ill adults, but evidence for the feasibility, safety and efficacy of this treatment is sparse. The aim of this scoping review is to map current and emerging evidence on the feasibility, safety and efficacy of MI-E for invasively ventilated adult patients with the aim of highlighting knowledge gaps and identifying areas for future research. Specific research questions aim to identify information informing indications and contraindications to the use of MI-E in the invasively ventilated adult, MI-E settings used, outcome measures reported within studies, adverse effects reported and perceived barriers and facilitators to using MI-E reported. ⋯ Open Science Framework submitted on 9 July 2020. https://osf.io/mpksq/ .