Quality assessment of clinical trials with artificial intelligence based chatbots in healthcare: points to consider in the protocol development for a systematic literature review

Abstract

Artificial intelligence (AI) based chatbots are used in healthcare either as therapeutic agents or tools to support different healthcare functions. Evidence behind their effectiveness and safety have to be proved by scientifically sound clinical trials. Systematic literature review (SLR) is a scientific method that allows to identify, select and critically apprise available empirical evidence. Development of the research protocol for an SLR is a challenging task in which research goals are defined and translated into a literature search and analysis plan via an iterative work. In this paper we present the main steps of the development of our research protocol for an SLR focusing on the reporting quality of clinical trials involving AI based chatbots in healthcare. We introduce how the specific goal and protocol of our SLR work was developed. We draw attention to some methods and sources that deserve consideration in SLRs dealing with AI based health technologies.