For several decades there have been concerns that there may be a connection between workplace interruptions and an increased chance of errors in worker performance. The possibility of such a connection is of particular concern in the healthcare workplace, where surgical or medication errors, for example, can have grave consequences. Most researchers recognise that interruptions and distractions are part of the nature of healthcare work, particularly in high-tempo critical and acute care environments, and they recognise that many interruptions have a positive effect by conveying timely information, providing guidance, and offering warnings. However, there is a body of evidence that interruptions can have a deleterious effect on cognitive and decision processes, leading to errors in performance. As a result, many healthcare organisations have taken steps to reduce interruptions and distractions in the working environment, or to mitigate their impact, but sometimes these effects have led to unintended consequences. As a result, in the last few years there has been a switch of focus to a more nuanced and balanced understanding of interruptions and distractions, including a broader view of how healthcare practitioners manage the multithreaded nature of their work. In this talk I will survey the evidence for the impact of interruptions and distractions on healthcare work, drawing on field research and simulator-based research, and including research done at The University of Queensland, amongst many other locations. I will outline the outcomes of attempts at the management of interruptions and distractions and highlight recent contributions to our understanding. 

Artificial intelligence (AI) is an incredibly powerful tool for building computer vision systems that support the work of radiologists. Over the last several years, artificial intelligence methods have revolutionized the analysis of digital images, leading to high interest and explosive growth in the use of “deep” machine learning and other AI methods to analyze clinical images. These promising techniques create computer vision systems that perform some image interpretation tasks at the level of expert radiologists. Deep learning methods are now being developed for image reconstruction, imaging quality assurance, imaging triage, computer-aided detection, computer-aided classification, radiogenomics, and other new imaging insights. The resulting computer vision systems have the potential to provide real-time assistance to imaging professionals, thereby reducing diagnostic errors, improving patient outcomes, and reducing costs. We will review the origins of AI and its applications to medical imaging, define key terms, and show examples of real-world applications that suggest how AI may change the practice of radiology. We will also review key shortcomings and challenges that may limit the application of AI to radiology.