Carroll, W. (July, 2018). Artificial Intelligence, Nurses and the Quadruple Aim. Online Journal of Nursing Informatics (OJNI), 22(2). Available at http://www.himss.org/ojni
AI Enters the Nursing Arena
Artificial intelligence (AI) is a relatively new concept in healthcare, particularly in nursing practice. Other once revolutionary technologies developed for high quality, safe patient care are now commonplace in care delivery and education, ranging from electronic health record (EHR) to mobile health (mHealth), telehealth and sensors for remote patient monitoring and simulation. New data-driven, intelligent innovations in the healthcare space bring capabilities and the hope of adding value to nursing care delivery. Big tech companies entering the healthcare AI arena including IBM Watson, Microsoft, and Intel join other prominent industry players such as Google and Amazon to use Big Data-enabled AI solutions for more accurate image recognition, amplified web searching and to enhance the e-commerce experience. AI in healthcare is gaining traction, and nurses can harness its power to enhance standard patient care processes and workflows to improve quality of care, impact cost and optimize the patient and provider experience.
Better Decision Making with Prediction
Artificial Intelligence is recognized as the aptitude exhibited by smart machines through perceiving, thinking, planning, learning, and the ability to manipulate objects (NITI Aayog, 2018). The concept and development of AI, defined as computer systems able to perform tasks that usually require human intelligence (English Oxford, 2018) can enhance and expedite a critical component of nursing care delivery, namely decision making.
Historically and still today, decision making in clinical practice and operations is made based on little or no data. Data tends to be used retrospectively in its descriptive form, devoid of prescription. Guessing and using heuristic methods have become the standard for determining impending patients’ health deterioration and disease progression, interpreting complex radiology results, and matching patient demand for appropriate nurse staffing. Also, events that impact the quality of care, such as patient length of stay, hospital readmissions, and patients leaving without being seen in Emergency Departments are difficult to forecast accurately. Existing nursing technologies collect and consume healthcare data that are enabled to foretell future events that could hinder care delivery. However, available data is often incomplete, unclean and lives in disparate systems within organizations. Big Data has arrived and is available readily from multiple sources in vast amounts. Difficult to aggregate and analyze, nurses have yet to grasp and use data to its full potential and reap its many benefits. With a greater comprehension of AI, nurses can be at the forefront of embracing and encouraging its use in clinical practice.
Enter predictive analytics, which falls under the umbrella of AI. This type of advanced analytics allows nurses to discover previously unknown patterns in multiple sources of clinical and operational data that can guide better decision making. Through the use of predictive data, nurses can gain actionable insights that enable greater accuracy, timely, and appropriate interventions in a prescriptive way for both patient and nurses. For instance, prediction can help nurses determine the appropriate number of days a patient should stay in the hospital. With this information, nurses can implement seamless care planning and management to prevent complications, improve patient satisfaction and patient flow, and reduce costly readmissions.
While automated and intelligent, AI and predictive analytics nevertheless require, in tandem, strong nursing judgment to make the proper decisions for enabling the right nurse to provide the right care, at the right time for the right patient. Clinical decision support system (CDSS) functionality offers nurses a means to promote and enhance care delivery by using rules-based tools. AI extends CDSS used in nursing care. The difference is that AI, particularly predictive analytics, adds breadth and precision to decision making for healthier care experiences for those giving and receiving care.
AI and Predictive Analytics Impact on the Quadruple Aim
The newest arm of the Quadruple Aim, which addresses the wellbeing of nurses, physicians and other care providers (Bodheimer & Sinsky, 2014), is enhanced by predictive analytics to alleviate untoward effects of taxing patient care that cause nurse dissatisfaction and burnout. Innovations in technology, including predictive analytics applications, can increase nurse satisfaction and improve this facet of the Quadruple Aim. Intelligent computer systems also assist the nursing process, and critical and organized thinking to expedite decision making by synthesizing valuable nursing skills and knowledge.
Why should nurses care about these innovations? Artificial Intelligence and predictive analytics can evolve nurses’ thinking about care delivery and operational tasks in functionally disruptive ways to serve the Quadruple Aim. With this shift, nurses can begin to advocate for the adoption and use of AI in patient care delivery. Leveraging AI and prediction will further the healthcare industry’s movement towards the development of data-driven solutions. It will also enhance the quality of nursing care more cost-effectively, to improve population outcomes and optimize patient and nurse satisfaction in the transforming healthcare landscape.
Bodenheimer, T., Sinsky, C. (2014). From triple to Quadruple Aim: Care of the patient requires care of the provider. Annuals of Family Medicine, 12(6), 573-576. DOI: 10.1370/afm.171
English Oxford Living Dictionary. 2018. Definition: Artificial Intelligence. Retrieved from https://en.oxforddictionaries.com/definition/artificial_intelligence
National Institution for Transforming India (NITI) Aayog. 2018. National Strategy for Artificial Intelligence. Retrieved from: http://niti.gov.in/writereaddata/files/document_publication/NationalStrategy-for-AI-Discussion-Paper.pdf