Roger Watson, Editor-in-Chief
I have long had an interest in artificial neural networks (ANNs) but I must admit my interest was mainly in what they were, what they did and what possible use they could be. On a visit to Italy many months ago I met a research team at the University of Genoa who were using ANNs to study communication in emergency care. I encouraged them to publish the work and worked very closely with them and that work is now published in JAN by Bagnasco et al. (2015) in their article titled: 'Applying artificial neural networks to predict communication risks in the emergency department'.
My understanding of ANNs has increased in the process and I am very happy to publish this paper so that others may also learn about them and see their potential in nursing research. In the words of the authors: 'ANNs are mathematical models that try to imitate the functional processes of the human brain. ANNs involve non-linear relationships among different data sets that cannot always be fully identified through the use of conventional linear analyses. ANNs are extensively used in technology and science with applications in chemistry, physics, biology and medicine.' I will not pretend that this concept or the operation of ANNs is easy to grasp; however, Bagnasco et al. explain it as clearly as anyone and central to the method, which is computer based, is the 'back propagation algorithm' which allows a system to 'learn' about the data that are being entered into it.
You can also listen to this entry as a podcast.
Bagnasco, Siri A, Aleo G, Rocco G, Sasso L (2015) Applying artificial neural networks to predict communication risks in the emergency department Journal of Advanced Nursing doi: 10.1111/jan.12691