Article type
Abstract
Background: There is an evolving discussion about the use of advanced technology to aid the completion of systematic reviews, including the use of machine learning and crowd sourcing. One of the key aims of producing high-quality health evidence is to use it to develop guidelines. Therefore guideline developers are key gatekeepers in the acceptance and use of evidence produced using machine-learning and crowd-sourcing. There has not yet been structured research regarding the attitudes of guideline developers regarding these technologies (machine-learning and crowd-sourcing).
Objectives: This paper will describe the attitudes of guideline developers towards the use of machine learning and crowd sourcing in evidence synthesis for health guidelines. It is intended that these data will inform the design of these automation systems as well as future research regarding validity and reliability.
Methods:Semi-structured interviews are being conducted with guideline developers and others involved with guideline development. Interviews are being transcribed and a thematic analysis will be performed using NVivo.
Results: The results of the above-described thematic analysis will be completed in June 2017 and will be presented.
Conclusions: Results of this study will elucidate guideline developers’ attitudes towards machine learning and automation. This information will be used to guide the design of future experimentation in the accuracy, reliability, and potential benefits of automation technologies and will contribute to the user-centred design of semi-automated evidence systems for use in guideline development.
Objectives: This paper will describe the attitudes of guideline developers towards the use of machine learning and crowd sourcing in evidence synthesis for health guidelines. It is intended that these data will inform the design of these automation systems as well as future research regarding validity and reliability.
Methods:Semi-structured interviews are being conducted with guideline developers and others involved with guideline development. Interviews are being transcribed and a thematic analysis will be performed using NVivo.
Results: The results of the above-described thematic analysis will be completed in June 2017 and will be presented.
Conclusions: Results of this study will elucidate guideline developers’ attitudes towards machine learning and automation. This information will be used to guide the design of future experimentation in the accuracy, reliability, and potential benefits of automation technologies and will contribute to the user-centred design of semi-automated evidence systems for use in guideline development.