Bmc Med Res Methodol
-
Following visible successes on a wide range of predictive tasks, machine learning techniques are attracting substantial interest from medical researchers and clinicians. We address the need for capacity development in this area by providing a conceptual introduction to machine learning alongside a practical guide to developing and evaluating predictive algorithms using freely-available open source software and public domain data. ⋯ We use a straightforward example to demonstrate the theory and practice of machine learning for clinicians and medical researchers. The principals which we demonstrate here can be readily applied to other complex tasks including natural language processing and image recognition.
-
Bmc Med Res Methodol · Mar 2019
A descriptive analysis of the characteristics and the peer review process of systematic review protocols published in an open peer review journal from 2012 to 2017.
An a priori design is essential to reduce the risk of bias in systematic reviews (SRs). To this end, authors can register their SR with PROSPERO, and/or publish a SR protocol in an academic journal. The latter has the advantage that the manuscript for the SR protocol is usually peer-reviewed. However, since authors ought not to begin/continue the SR before their protocol has been accepted for publication, it is crucial that SR protocols are processed in a timely manner. Our main aim was to descriptively analyse the peer review process of SR protocols published in 'BMC Systematic Reviews' from 2012 to 2017. ⋯ The number of published SR protocols increased over the years, but so did the processing time. In 2017, it took several months from submission to acceptance, which is critical from an author's perspective. New models of peer review such as post publication peer review for SR protocols should be investigated. This could probably be realized with PROSPERO.