Answer for NURS 8210 Week 7 Blog Innovative Informatics Tools and Applications to Clinical Practice From the five topics: AI, Machine Learning, Genomics, Precision Health, and Robotics, assess the applications of the technology, noting the potential benefits and potential challenges of the innovations. Be specific. Appraise the potential of the innovations to improve healthcare practice and related outcomes.

Artificial Intelligence

AI is developed by training computers to do human tasks (SAS, n.d.). It includes a range of processes and behaviors generated by models and algorithms (Chen & Decary, 2020).  AI integrates big data when it is used in conjunction with these models and algorithms. AI is most frequently used in healthcare for clinical decision support processes in the form of alerts, guidelines, order sets, reports, templates, and workflow tools (Sutton et al, 2020. It is also used in natural language processing to extract information from notes, voice technology to simplify documentation, and robotics in surgical procedures (Chen & Decary, 2020). There are several challenges associated with AI. These challenges include an overarching lack of understanding about what AI is in healthcare, how to integrate it, a shortage of individuals who understand how to implement it, an incompatible healthcare technology infrastructure, and not enough good data in healthcare to support AI methods (Chen & Decary, 2020). It is also very costly to set up and maintain (Sutton et al, 2020). AI is used as a tool and when partnered with clinicians supports the delivery of safe quality care (Sutton et al, 2020). AI also has the potential to improve the triple aim (Chen & Decary, 2020).

Machine Learning

Machine Learning is a subset of AI which is used to look for patterns in big data and draw conclusions (SAS, n.d.) while learning from performance and improving over time (Bini, 2018). Machine learning incorporates seven steps which include the use of big data when developing predictive models or algorithms. These steps include asking a question and gathering data, prepping the data, choosing a model, and then splitting the data to train. Approximately 80% is used to train a model/algorithm and the other 20% is used to evaluate and test the model through hyperparameter tuning or feedback (Google Cloud Tech, 2017; SAS, n.d.). Machine learning has the ability to sift through large amounts of complex data, such as the data being produced by wearables, and transform the data into usable information which can be used to develop individualized care (Kwon et al, 2019). Integrated machine learning models are rare in healthcare because they are challenging to develop, prioritize, and implement (Sendak et al, 2019). Most frequently they are developed as knowledge-based decision support programs used to improve safety, clinical management, cost containment, automated administrative functions, diagnostic support, decision support, better documentation, and workflow improvements (Sutton et al, 2020).

Genomics

Genomics is the study of the interrelationship of all genes (Taylor & Barcelona de Mendoza,2017). Genomics uses technology and big data analytics to develop better precision in patient assessment, intervention, and evaluation processes (Corwin et al, 2019). Genomics integrates big data sets in the form of biospecimens, environment, and behavior in an attempt to determine their effects on health (Taylor & Barcelona de Mendoza, 2017). There are several challenges associated with using genomics in healthcare. There is a lack of understanding in nursing concerning genomics (Newcomb et al, 2019) and a need to apply ethical considerations at both individual and population levels (Williams & Anderson, 2018). These challenges are compounded by privacy, reproducibility, and translation issues (Corwin et al, 2019). GP testing has the potential to improve practice because it is an inexpensive and fast method used to prevent, diagnose, treat, and maintain patient care while transforming healthcare outcomes (Genomic Education Program, n.d.).

Precision Health

Precision health is an emerging field using big data to focus on the interplay of genomics, physiology, psychology, environment, and ethics which are used to improve health (Hacker et al, 2019; Hickey et al, 2019). The goal of precision health is to keep people from getting sick in the first place (Minor, 2016). Precision health is driving the development of therapies tailored to treat individual diseases (Minor, 2016) as well as to reduce the current racial and ethnic disparities in healthcare practice (Hacker et al, 2019; Taylor et al, 2017). There are currently challenges to obtaining funding and publishing the papers needed to share knowledge on this topic (Hacker et al, 2019). Partnerships between researchers at NINR Centers are currently needed to leverage experience and address gaps in the evolving science (Hickey et al. 2020) and this appears to be occurring in the form of yearly NINR boot camps.

Robotics

Robotics is the culmination of all artificial intelligence technology to date (Chen & Decary, 2020). Medical robots are currently being used to