JMIR Publications

ABSTRACT

Background:

Burn automated diagnosis may be instrumental to accurate and timely decision-making at point-of-care, helping to ensure that the right patients are triaged to burns centres. This is particularly important in resource poor settings.

Objective:

We studied the intention of non-specialized clinicians to engage in automated diagnosis in burn care as well as their perceptions towards clinical risks.

Methods:

A self-administered survey was used among a purposive sample of first contact clinicians (n=56) and burns specialists (n=35). The survey had two main parts: one measuring the intention to use automated diagnosis as per seven constructs of the Automation Acceptance Model (AAM, yielding eight hypotheses) and one on clinical risk perceptions (likelihood and severity of seven risks). Structural Equation Modelling was used to test the hypotheses among first contact clinicians, and Mann-Whitney U test to measure differences in risk perceptions between the two clinical groups.

Results:

Many first contact clinicians would intend to use automated diagnosis for burns should the technology be made available in their departments (73%). The AAM concepts contributed moderately to explain what the intention to use automated diagnosis rests on (R2=0.432) with five out of eight hypotheses being supported. The intention to use automated diagnosis was associated with perceived usefulness but not with the attitudes towards using it. Of the seven risks studied, the one which was most often considered as high risk of occurring was that of complex burns not being recognized (29%). The two groups differed significantly in their concern regarding both the likelihood to happen and the severity of two risks: the under-management of severe burns and the over-management of minor burns. Specifically, a larger proportion of first contact clinicians were concerned than burns specialists (27% versus 6% and 23% versus 6% for under-management and over-management respectively).

Conclusions:

Almost three quarters of first contact clinicians were inclined to seek automated advice for burn diagnosis. The proposed model contributes to explain the intention to use with five hypotheses supported. When seeking for additional determinants, clinical risk perception is a dimension that should be considered in any artificial intelligence implementation process, to help ensure sustainability.