Sorting out symptoms: design and evaluation of the 'babylon check' automated triage system

By Katherine Middleton, Mobasher Butt, Nils Y. Hammerla, Steven Hamblin, Karan Mehta, Ali Parsa. 2016

34 citations recorded by the source corpus.

Prior to seeking professional medical care it is increasingly common for patients to use online resources such as automated symptom checkers. Many such systems attempt to provide a differential diagnosis based on the symptoms elucidated from the user, which may lead to anxiety if life or limb-threatening conditions are part of the list, a phenomenon termed 'cyberchondria' [1]. Systems that provide advice on where to seek help, rather than a diagnosis, are equally popular, and in our view provide the most useful information. In this technical report we describe how such a triage system can be modelled computationally, how medical insights can be translated into triage flows, and how such systems can be validated and tested. We present babylon check, our commercially deployed automated triage system, as a case study, and illustrate its performance in a large, semi-naturalistic deployment study.

Subfields: Psychiatry and Mental health

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Conversational Agents in Health Care: Scoping Review and Conceptual Analysis (2020, background): “The conversational agents in the included studies were health care professional like [57,58,62,66,71,73,74,86], informal [46,52,53,56,61,65,81,85], coach like [47,49,52,64,66,70,80], knowledgeable [56,60,68,72,89], human like [48,78,79,88], culture specific [47,48,53], factual [68,76], gender…”
A comparative study of artificial intelligence and human doctors for the purpose of triage and diagnosis (2018, methodology): “We opted to use GPs to play the patients instead of professional actors as in a previous study [Middleton et al., 2016], to prioritise the accuracy of interpreting the information on the vignette over the realism of a layperson.”