Artificial intelligence for clinical decision support in neurology

Abstract

Artificial intelligence is one of the most exciting methodological shifts in our era. It holds the potential to transform healthcare as we know it, to a system where humans and machines work together to provide better treatment for our patients. It is now clear that cutting edge artificial intelligence models in conjunction with high-quality clinical data will lead to improved prognostic and diagnostic models in neurological disease, facilitating expert-level clinical decision tools across healthcare settings. Despite the clinical promise of artificial intelligence, machine and deep-learning algorithms are not a one-size-fits-all solution for all types of clinical data and questions. In this article, we provide an overview of the core concepts of artificial intelligence, particularly contemporary deep-learning methods, to give clinician and neuroscience researchers an appreciation of how artificial intelligence can be harnessed to support clinical decisions. We clarify and emphasize the data quality and the human expertise needed to build robust clinical artificial intelligence models in neurology. As artificial intelligence is a rapidly evolving field, we take the opportunity to iterate important ethical principles to guide the field of medicine is it moves into an artificial intelligence enhanced future.

Keywords: artificial intelligence; augmented intelligence; deep learning; ethics; neurology.

Graphical Abstract

Figure 1

Definitions of AI: AI encompasses both ‘traditional’ machine learning and ‘contemporary’ deep-learning concepts.

Figure 2

Biological and artificial neuron: on the left side of the figure is a biological neuron (reused under the terms of Creative Commons Attribution Licence—CC BY-SA 3.0—allowing for reproduction https://commons.wikimedia.org/wiki/ File: Neuron.svg), and on the right side of the figure is a model of an artificial neuron [reprinted from Agatonovic-Kustrin and Beresford (2000) with permission from Elsevier].

Figure 3

An Artificial Neural Network example: here is a schematic overview of how high-dimensional genetics and brain imaging is used in a deep-learning model to make a probabilistic estimate (p) whether people are likely to develop epilepsy (red node) or not (green node). The lines between layers represent connections, each associated with a weight-adjusted during feed-forward training and updated during back-propagation until the optimal model performance.

Figure 4

Importance of labels in AI: AI can answer difficult clinical questions in neurology.