Artificial Intelligence for Nursing Practice and Management

KEY POINTS With the advancement of available clinical and health data as well as the growth of big data in different healthcare disciplines, artificial intelligence is becoming a prevalent emerging technology to predict disease risks, disease diagnoses, courses of illness, and treatments. A simplified meaning of artificial intelligence, machine learning, and deep learning methods is illustrated for future nursing informatics research. Current use ofmachine learning and deep learning in nursing education is described and research and recommendations for future use are presented. ARTIFICIAL INTELLIGENCE Artificial intelligence (AI) has been defined as an area of study in computer science concerned with the ability to make computers do things that would require intelligence if done by humans. Artificial intelligence is a new-old science. Artificial intelligence concepts were presented in the 1950s; however, due to the scarcity of electronic data, at that time, its use for further discovery was still immature. Nowadays, with the growth of electronic data, AI is growing in importance in many disciplines. In healthcare and nursing science, with widespread implementation of electronic health records and electronic documentation, big data in terms of large volume, variety, velocity, and veracity of data aremore available. Large warehouses of structured and unstructured nursing data will enhance the use of AI technology to create more meanings that can be used in research to improve nursing practice and management. Artificial intelligence is the ability to use machine learning to imitate humans' cognitive abilities by using numerous statistical and algorithmic calculations in understanding, problem solving, and decision making. Artificial intelligence is a broad concept under which are machine learning and deep learning (Figure 1). Machine learning (Table 1) has three subfields; each uses different assumptions and mathematical frameworks for how data are ingested and how learning occurs within the algorithm. The subfields of machine learning are (1) supervised learning; (2) unsupervised learning; and (3) reinforcement learning (semisupervised learning). Supervised learning requires labeled data sets, which is the process of attaching meaning to different types of digital data such as text, audio files, images, videos and more. This environment includes a known data domain and known response (labeled) set. Therefore, a supervised learning model and an algorithm deal with an environment where the given