Sonya Reid, Vikram Niranjan
Abstract: Artificial Intelligence is increasingly being used in medical research and certain clinical practice areas. This article examines selected literature to identify common themes with an idea to understanding the impact, concerns and opportunities afforded by such technology. Such research is markedly different from established research methodologies and so is challenging to assess and evaluate. The complexity of the analytics and applied statistics makes it difficult for many to understand and yet conclusions drawn can have a significant impact on clinical practice and policy, funding and recording practices. The key themes identified are those of accuracy, population bias, database limitations, cost- and time-savings, and the ability to use artificial intelligence to predict future events or outcomes. In addition, certain dangers are highlighted and a few recommendations made.
Keywords: Artificial intelligence, Machine learning, Delivery of health care, Deep learning