The rapid integration of artificial intelligence (AI) into healthcare delivery has not only provided a glimpse into an enhanced digital future but also raised significant concerns about the social and ethical implications of this evolution. Nursing leaders have a critical role to play in advocating for the just and effective use of AI health solutions. To fulfill this responsibility, nurses need information on the widespread reach of AI and, perhaps more importantly, how the development, deployment and evaluation of these technologies can be influenced.
This article includes the results of a scoping review on the use of AI in healthcare delivery, with a particular focus on aspects of care essential in nursing practice, including systems management and medication administration. The review was conducted using an updated Arskey and O'Malley framework, and the findings are reported in alignment with key nursing leadership functions outlined by the Canadian Nurses Association. This examination of AI in healthcare delivery has revealed very little nursing consultation in relation to the use and potential implications of AI integration. However, nurses are uniquely positioned to aid in the ethical and effective implementation of this technology, as noted in a discussion of current AI strengths and challenges. Several ways in which nursing leaders can amplify the voice of the profession as well as represent patient needs in this technological evolution are also highlighted. The article concludes with a look ahead to a digitally diverse healthcare landscape detailing nursing roles to support a future that delivers on the current promises and aspirations touted in AI science.
Artificial intelligence (AI) in healthcare application is rapidly increasing on numerous fronts, and this technology has the potential to become integrated into several processes and/or products used in the delivery of nursing care. AI is "the ability of a digital computer or computer-controlled robot to perform task commonly associated with intelligent beings. The term is frequently applied to the project of developing systems endowed with the intellectual processes characteristic of humans." (Copeland 2018: para. 1). There are other categorizations of note within the AI lexicon, such as ambient intelligence, typically referring to systems driven by intelligent computing (Acampora et al. 2013), or machine learning (Char et al. 2018), often considered a subset of AI. The foundational element in this science is the use of algorithmic processes to automate and simulate cognitive tasks, including complex analysis and increasingly independent action.
AI is only part of a growing trend of digitization influencing multiple aspects of our personal and professional lives. Increased use of wearable devices, many of which promote the collection of "health" data, is a significant aspect of the consumer health movement. Smartphones and a multitude of sensors contribute to new "intelligent living" or care environments, also delivering an extraordinary amount of data into emerging systems. This explosion of information coalesces into an expansive "big data" entity, which is a key driver in the advancement of AI solutions that endeavour to analyze and direct action from this knowledge. In healthcare, AI is being used for practitioner and patient decision support; the review of diagnostics, particularly in medical imaging; and predicting a host of factors related to patient outcomes and system utilization. Applications are being designed to review reams of patient health record data, as well as to support the presence of robotic devices, including those to support care delivery. However, the complexities of the healthcare environment present real and substantial challenges to the advancement of "automated" care solutions. In addition, there are serious ethical challenges regarding the advancement of this technology, within society in general and in health particularly. In the AI Now 2018 report, researchers from the AI Institute, tasked with examining the social implications of this technology, noted once again an urgent need for not only additional regulation and governance but also an expansion of interdisciplinary input into ongoing development and implementation (Whittaker et al. 2018). Previous policy publications in Canada highlighted the many attributes that equip nurses to make a substantial contribution in addressing these ethical AI challenges (Risling 2018).
Finally, perhaps not surprising, given the complexity of the science, there is a great deal of diversity and volume in AI publications. The volume and pace of publications in this area are starting to result in a literary "big data" challenge of its own. In this article, the results of a scoping review on the integration of AI into healthcare practice are presented, with a particular focus on how this may impact the work of Canada's nursing leaders to provide a foundation of essential AI knowledge. Actions nursing leaders can take today to advocate for the thoughtful and just integration of this technology into our practice, teaching and learning spaces are also included in a concluding discussion of future directions.
Using the methodological framework outlined by Levac et al. (2010) in their update to the work of Arksey and O'Malley, a comprehensive scoping study was undertaken to review the literature on the current use of AI in healthcare delivery. There are six steps in the review process: (1) identifying the research question or questions; (2) identifying relevant studies; (3) study selection; (4) charting the data; (5) collating, summarizing and reporting results; and (6) consultation, which is optional (Levac et al. 2010). The framework details the value in selecting both a broad and more specific research question or questions to establish an effective search strategy (Levac et al. 2010). The broad research question used to guide review was What applications of AI technology are currently being implemented in healthcare? This question supported the original focus of a broad exploration of AI use in health. The second question was refined as the review process progressed. It provided additional search parameters for focusing on the role nurses and nursing practice may hold in the advancement of this technology by asking How will the implementation of AI in healthcare delivery influence nursing care and leadership? Together, these questions provided the focus, clarity and direction needed to inform the subsequent stages of the research process.
Search Strategy and Data Sources
The search strategy included the identification of several electronic databases to source published research relevant to the questions. These included CINAHL (Cumulative Index to Nursing and Allied Health Literature), Embase, Medline, PubMed, Scopus and Web of Science. A preliminary search strategy was used to determine the medical subject headings and keywords. Results were restricted to English-language publications between 2008 and 2018. A full overview of the search terms and initial results from each database is featured in Figure 1. This foundational search addressed the second step of the research process, identifying relevant studies, and produced an initial publication count (n = 477) for review.
To complement the search of peer-reviewed literature, a targeted search of websites of relevant organizations was also undertaken. The study team focused on national or international organizations, such as Health Canada and World Health Organization, and did systematic keyword or direct webpage searches for materials that could address both research questions guiding the review. A broad search of Google and Google Scholar was also conducted. Although there was some grey literature broadly addressing AI in healthcare, there was nothing to contribute additional knowledge to the specific inquiry about the influence of this technology on nursing practice.
The third step of the review process was addressed by determining inclusion and exclusion criteria based on the specificity of the research questions. Once duplicates were removed from the initial search, three phases of exclusion were completed, an overview of which is presented in Figure 1. Each exclusion phase was completed by two members of the study team, with the consultation of a third party, the first author, when a decision on exclusion could not be met.
An article title review and a brief overview of abstracts were done as part of the first phase of exclusion to remove publications that did not have a specific focus on AI implementation in healthcare settings. This phase resulted in a reduced sample size (n = 164) for further examination. In the second exclusion phase, the authors reviewed full-text documents and confirmed that the remaining studies included a primary focus on AI use in healthcare settings (n = 69). The third and final exclusion phase required thoughtful consideration on how best to address the role of nursing within this specific technological context, given a discovered dearth of nursing-focused AI literature. In seeking to address the second question of the review, the study team elected to use the Canadian Nurses Association's (CNA 2009) most current position statement on nursing leadership as a way to screen the remaining studies, thereby maximizing results for a nursing audience. Although it is several years old, the CNA's call for nursing leaders to advance safe, quality and just healthcare environments is highly relevant, both in addressing the increased complexities of today's health systems and in reviewing the role of AI within them.
At the time of the initial search for this review, nursing-specific AI publications were not available. However, there was a significant amount of more general health research deemed directly relatable to nursing practice, and nursing leadership in particular. Using the CNA position statement, full-text copies of the remaining publications were reviewed to determine if they addressed any one of the requirements for nursing leaders to promote "(a) safe care delivery systems; (b) quality practice environments that provide appropriate human and other resources; and (c) social justice, resources to address broad determinants of health and services that reduce disparities and improve access to care for the vulnerable" (CNA 2009: 3). This last exclusion review resulted in a final set of (n = 30) including 26 empirical and four non-empirical publications.
Data Extraction and Analysis
A data extraction framework was developed by the study team to support standardization during the extraction process between reviewers. The following information was obtained and documented for all included publications: author(s), year of publication, country, research design and methods and findings related to AI implementation in healthcare settings. Also, a determination was made regarding which of the three aspects from the nursing leadership position statement best applied to each article. This work is summarized in the complete Pinch table of the review results found in the available here. Initially, two team members completed and cross-checked each data extraction using the agreed-upon framework. Any inability to reach consensus was resolved by a third team member, the first author and study lead, who also reviewed each article in establishing the final sorted themes.
There is a substantial amount of literature available exploring the use or proposed use of AI in the delivery of healthcare. This nursing-focused scoping review produced 26 empirical and four non-empirical studies for final consideration. Although empirical articles are often exclusively summarized in review publications, in studies on emerging issues, it is worthwhile to examine non-empirical work to determine key issues or calls to action. As noted, a complete summary of the key characteristics of the 30 extracted articles is included in the Appendix.
Figure 2 shows the findings of the scoping review regarding the publication dates of the papers in this review. Although a 10-year window was established for the review, the earliest publications returned in the results were from 2010 (Yang et al. 2010), with one additional article released within the first half of the study time block (Bindoff et al. 2012). The increased pace of publications in this area is highlighted in Figure 2, demonstrating a majority of articles in this review released within the past five years.
As shown in Figure 3, the United States (13, 43%) contributed the most significant amount of publications in the review. However, there is also a clearly demonstrated global interest in the use of AI in healthcare with strong representation from Spain (6, 20%) and Taiwan (3, 10%) and additional offerings from researchers located in Australia, Brazil, Iran, the Netherlands, Pakistan, Russia, Sweden and Turkey. There were no Canadian publications within the scope of the review, a notable finding in this work identifying a clear need for additional study in this country.
Figure 4 shows the specific areas or focal points of AI study and implementation in this review, with hospital workflow accounting for the largest percentage of the study (6, 20%). There was also high use in the areas of personalized healthcare (4, 14%) that included wearable medical sensors (Yin and Jha 2017) and respiratory services (4, 14%), among others.
Out of the 30 articles identified in the initial review, only two, Sensmeier (2017) and Zlotnik (2015), included discussion of the nursing role or professional view about AI use in healthcare. Therefore, another key finding of this study was a lack of published consultation, by or with nurses, on AI health application. There was also little mention of the current or potential impact of this technology on nursing practice or patients. As was detailed in the guidelines used to complete the final exclusion phase for this review, a lack of distinct nursing voice in this body of AI literature created an opportunity to examine the search results through the lens of nursing leadership. This was done by reviewing each article and classifying it within one of three areas of responsibility noted in a CNA nursing leadership position statement promoting "(a) safe care delivery systems; (b) quality practice environments that provide appropriate human and other resources; and (c) social justice, resources to address broad determinants of health and services that reduce disparities and improve access to care for the vulnerable" (2009: 3). Although there were some issues with potential overlapping elements within the articles and their relation to these leadership priorities, ultimately all 30 publications were assigned a primary designation; these data are also featured in the table in the Appendix.
There were 14 articles that addressed aspects of safe care delivery, which could be categorized into three distinct themes. The largest grouping of publications, six articles, featured work on decision support to reduce medical error (Yin and Jha 2017); improve medication review processes (Bindoff et al. 2012); create improved personalized care for specific diagnoses, such as breast cancer (Alaa et al. 2016; Yoon et al. 2017); improve clinical care for patients on ventilators (Akbulut et al. 2014); and activate electronic health record data as a real-time clinical decision support tool (Medrano et al. 2018).
The results of prediction study were featured in four articles related to a variety of health conditions and possible patient outcomes such as asthma (Finkelstein and Wood 2013; Luo et al. 2015), postpartum depression (Jimenez-Serrano et al. 2015) and sepsis mortality (Taylor et al. 2016). Finally, another four articles addressed patient supports, including home monitoring of older adults (Lopez-Guede et al. 2015), medication adherence support for patients with movement disorders (Tucker et al. 2015), guidance for patient laboratory use (Semenov and Kopanitsa 2016) and disease self-management (Velikova et al. 2015).
The remaining 16 articles reported results of interest to nursing leaders in advancing quality practice environments that provide appropriate human and other resources (CNA 2009). In this grouping, there were three themes as well. First, a set of general application publications or discussions that also incorporated all but one of the non-empirical publications. This work included commentary on ambient intelligence in healthcare systems (Acampora et al. 2013), the use of AI in general biomedical application (Salman et al. 2017; Sheikhtaheri et al. 2014), discussion on the ethical challenges inherent in implementing this technology (Char et al. 2018) and one of only two nursing-focused publications (Sensmeier 2017).
Another grouping of seven articles provided information pertaining to resource allocation, often highlighting potential for cost savings by addressing specific clinical care issues such as pressure ulcers (Fossum et al. 2013), nosocomial infections (Gómez-Vallejo et al. 2016), ventilator weaning (Hsu et al. 2013) and the development of personalized cancer treatment plans (Sharma et al. 2016); using telehealth to support recently discharged patients and assess need for readmission (Lin et al. 2014); and, finally, examining how prediction models can be used to provide patient data related to graft survival outcomes in kidney transplant (Topuz et al. 2018) or length of stay for complex cases such as for burn patients (Yang et al. 2010).
The third theme in this set related to workflow study (Lee et al. 2015), including scheduling of both space, featured in the final non-empirical article on surgery booking in the operating room (Dios et al. 2015), and people (Yousefi et al. 2018; Zlotnik et al. 2015). Excluding the commentary on operating room scheduling, the remainder of this work was all done within emergency department settings.
A further finding of note in this review is a lack of commentary, or study, on the implications of an increased presence of AI in health pertaining to issues of "social justice, resources to address broad determinants of health and services that reduce disparities and improve access to care for the vulnerable" (CNA 2009: 3). There was one publication that addressed some ethical aspects of this technological evolution (Char et al. 2018), but that discussion was medically focused and did not highlight issues of social justice that would likely be featured in a comprehensive nursing-focused ethical review on AI application or that would have allowed it to represent this aspect of nursing leadership. This is a clear need in advancing the science of AI in health and nursing and something that should be undertaken by nursing leaders and/or nursing informaticists.
This scoping review provides a comprehensive look at research publications on AI implementation in healthcare delivery around the world. The selection criteria used in this scoping review were designed to return relevant research for nursing leaders, providing a broad evidence base on the delivery of healthcare using AI, including nursing implications. Currently, there is widespread exploration of potential applications of AI in health systems across multiple disciplines, featuring many diverse uses. Although the majority of the articles identified in this review addressed how AI can aid practitioners in the delivery of care, there were some articles that featured patients as the targeted users of AI-driven applications (Semenov and Kopanitsa 2016; Velikova et al. 2015) and others that addressed issues directly relatable to nursing practice, such as staffing (Zlotnik et al. 2015). There is a need for additional study featuring the voices of end users of these technologies, be they patients or practitioners.
This increase in collaborative investigation may also help address persistent concerns related to the ethical implications of an increased presence of AI technology in the Canadian healthcare system. Nurses have much to add to the debate on the ethics of AI. As professionals grounded by a commitment to social justice and equitable care, nurses are experts in addressing the complexities of social determinants of health and evidence-informed practice and have long served as historical mediators in the complex relationship between patients and technology (Risling 2018).
The CNA (2009) has called upon nursing leaders to "study, develop, test and implement effective, innovative and fiscally responsible policy solutions" (p. 3). This review has provided an introductory overview of how the use of AI could aid in these efforts. It has also revealed, however, how infrequently nurses are consulted or featured in the development and testing of these technologies. Nursing has long considered the implications of its connection to technology, and using AI as a valuable addition to evidence-informed practice, already inherent in nursing care, provides an existing framework to maximize the benefits of this technology for nurses and patients. The diverse nature of the environments in which AI can be implemented supports the argument that nurses, present in most if not all such settings, should be consulted in determining how AI can be most ethically and effectively integrated into these healthcare domains. As noted in one of the nursing-focused publications in this review, "the future will be informed by data and the use of intelligent technologies that can take action based on information. We'll be able to deliver care better, faster and safer if we appropriately harness the power of AI." (Sensmeier 2017: 18).
This review was limited by the foundational scope of inquiry determined at the outset of the study and as such delivers a focused examination of AI health application within a specific nursing leadership context. The use of broad search terms returned significant results and also revealed other potentially relevant publication types. For example, the use of decision supports as a search term provides insight into the substantial history of this work within nursing. However, when search terms were combined to include reference to AI or machine learning, much of these publications were removed, as these were not commonly featured aspects of earlier computer-aided decision support exploration. This exercise further highlighted current issues related to the scale of complexity represented within AI. Finally, there was a great diversity of topic and application in the final search results. Although this does allow readers to see the breadth of potential AI use in healthcare systems as well as the aforementioned nomenclature issues, it did present challenges in terms of synthesizing results into a condensed presentation. Also, many of the studies were proof-of-concept or pilot works, with the majority of the publications concluding with calls for additional investigation to be completed.
The pace of AI publications has not abated since the searching related to this review was completed. A few critical publications of note have emerged that are relevant to the work of this scoping study. Perhaps the most noteworthy of these is an AI review article published by Topol (2019). Although done through a biomedical lens, this publication is a valuable resource in understanding what areas of medicine AI is emerging in as well as its application in health systems and data analysis. An increasing interest in AI and the nurse's role is also featured in early 2019 publications (Bergese et al. 2019; Kwon et al. 2019; Li et al. 2019; Sullivan et al. 2019), including one Canadian publication (Kwon et al. 2019). This work included research on the value of AI in predicting pediatric emergency department return visits (Bergese et al. 2019), pressure injuries for patients at the end of life (Li et al. 2019) and mortality risks in homebound older adults (Sullivan et al. 2019). The Canadian case study detailed the importance of promoting the use of nursing knowledge in machine learning to improve its relevance and performance (Kwon et al. 2019). It is gratifying to see the appearance of a nursing voice in this critical discussion, and especially to note how often the value of nursing data or nursing practice is being highlighted as an essential element of future AI healthcare success. Nursing informaticists have an important leadership role of their own in continuing this work and conducting research that establishes a strong foundation of evidence regarding the necessity of nursing data and care in this AI evolution.
Next steps for nursing leaders in all practice settings should include advocacy for not only how nursing practice may best be served by AI solutions but also how these types of solutions could benefit patients. To accomplish this, the critical importance of the involvement of nurses, and ideally patients, in early AI co-design and implementation planning should be made clear (Sensmeier 2017). Nursing informaticists will also be essential to this advancement, exploring factors related to uptake and sustained use of these solutions and, as noted, establishing evidence-based evaluations of the effectiveness of AI solutions. There is already a significant body of nursing informatics expertise on the integration of other digital health solutions into practice, especially regarding clinical workflow, decision support, patient care and encouraging practitioner adoption and sustained use of new technologies. However, the responsibility of contributing to robust and, perhaps more importantly, ethical AI healthcare future does not just lie with nurse informaticists. All nurses have a role to play as we negotiate our emerging digital health future.
There are several practical ways in which nursing leaders can contribute to an AI evolution. First, by increasing awareness of this technology and its healthcare application among nursing staff, in discussion with institutional leadership colleagues, and peers. Second, examining the role of nursing in digital health decision-making within institutions across the country and advocating for changes where needed to ensure equitable representation in these vital dialogues. is also imperative that nursing leaders continue to support nursing informaticists contributing to such key informatics initiatives, such as the advancement of standardized nursing data and representation of nursing assessment and intervention in electronic medical or health records. Finally, although nursing has a significant role to play in the future of digital health, including the use of AI, we will be challenged to fulfill these obligations if we do not increase the breadth and depth of informatics education available to nursing students, and through professional development opportunities. Nursing informatics experts should also be increasingly represented in appropriate institutional leadership roles related to the advancement of digital health.
There is much promise in the potential of AI to address some of the most complex problems inherent in the Canadian healthcare system, especially related to spiralling costs, inefficiencies and safe care. The voice and influence of nursing can be amplified in this digital future if we are able to harness the power of this technology in advancing our abilities to provide skilful evidence-informed care. However, the opposite outcome is also possible. Now is the time when we must commit to engaging in the integration of AI into our workplaces and equip ourselves and our profession with the enhanced nursing intelligence needed to ensure our future success.
About the Author
Tracie L. Risling, RN, PhD, Associate Professor, College of Nursing, University of Saskatchewan, Saskatoon, SK
Cydney Low, BSN, College of Nursing, University of Saskatchewan, Saskatoon, SK
Acampora, G., D.J. Cook, P. Rashidi and A.V. Vasilakos. 2013. A Survey on Ambient Intelligence in Healthcare. Proceedings of the IEEE 101(12): 2470–94. doi:10.1109/jproc.2013.2262913.
Akbulut, F.P., E. Akkur, A. Akan and B.S. Yarman. 2014. A Decision Support System to Determine Optimal Ventilator Settings. BMC Medical Informatics and Decision Making 14(3): 1–11. doi:10.1186/1472-6947-14-3.
Alaa, A.M., K.H. Moon, W. Hsu and M. Van Der Schaar. 2016. Confident Care: A Clinical Decision Support System for Personalized Breast Cancer Screening. IEEE Transactions on Multimedia 18(10): 1942–55. doi:10.1109/TMM.2016.2589160.
Canadian Nurses Association. 2009. Nursing Leadership Position Statement. Retrieved August 5, 2018. <https://bit.ly/30kgeIO>.
Bergese, I., S. Frigerio, M. Clari, E. Castagno, A. De Clemente, E. Ponticelli, et al. 2019. An Innovative Model to Predict Pediatric Emergency Department Return Visits. Pediatric Emergency Care 35(3): 231–36. doi:10.1097/PEC.0000000000000910.
Bindoff, I., A. Stafford, G. Peterson, B.H. Kang and P. Tenni. 2012. The Potential for Intelligent Decision Support Systems to Improve the Quality and Consistency of Medication Reviews. Journal of Clinical Pharmacy and Therapeutics 37(4): 452–58. doi:10.1111/j.1365-2710.2011.01327.x.
Char, D.S., N.H. Shah and D. Magnus. 2018. Implementing Machine Learning In Health Care: Addressing Ethical Challenges. New England Journal of Medicine 378(11): 981–83. doi:10.1056/NEJMp1714229.
Copeland, B.J. 2018. Artificial Intelligence. Encylopedia Brittanica. Retrieved November 30, 2018. <https://www.britannica.com/technology/artificial-intelligence>.
Dios, M., J.M. Molina-Pariente, V. Fernandez-Viagas, J.L. Andrade-Pineda and J.M. Framinan. 2015. A Decision Support System for Operating Room Scheduling. Computers and Industrial Engineering 88: 430–43. doi:10.1016/j.cie.2015.08.001.
Finkelstein, J. and J. Wood. 2013. Predicting Asthma Exacerbations Using Artificial Intelligence. Studies in Health Technology and Informatics 190: 56–58.
Fossum, M., M. Ehnfors, E. Svensson, L.M. Hansen and A. Ehrenberg. 2013. Effects of a Computerized Decision Support System on Care Planning for Pressure Ulcers and Malnutrition in Nursing Homes: An Intervention Study. International Journal of Medical Informatics 82(10): 911–21. doi:10.1016/j.ijmedinf.2013.05.009.
Gómez-Vallejo, H.J., B. Uriel-Latorre, M. Sande-Meijide, B. Villamarín-Bello, R. Pavón, F. Fdez-Riverola and D. Glez-Peña. 2016. A Case-Based Reasoning System for Aiding Detection and Classification of Nosocomial Infections. Decision Support Systems 84: 104–16. doi:10.1016/j.dss.2016.02.005.
Hsu, J.C., Y.F. Chen, W.S. Chung, T.H. Tan, T. Chen and J.Y. Chiang. 2013. Clinical Verification of a Clinical Decision Support System for Ventilator Weaning. BioMedical Engineering Online 12(SUPPL 1): 1–14. doi:10.1186/1475-925X-12-S1-S4.
Jimenez-Serrano, S., S. Tortajada and J. M. Garcia-Gomez. 2015. A Mobile Health Application to Predict Postpartum Depression Based on Machine Learning. Telemedicine Journal and E-Health: The Official Journal of the American Telemedicine Association 21(7): 567–74. doi:10.1089/tmj.2014.0113.
Kwon, J.Y., M.E. Karim, M. Topaz and L.M. Currie. 2019. Nurses ‘Seeing Forest for the Trees' in the Age of Machine Learning. CIN-Computers Informatics Nursing 37(4): 203–12. doi:10.1097/CIN.0000000000000508.
Lee, E.K., H.Y. Atallah, M.D. Wright, E.T. Post, C. Thomas, D.T. Wu and L.L. Haley. 2015. Transforming Hospital Emergency Department Workflow and Patient Care. Interfaces 45(1): 58–82. doi:10.1287/inte.2014.0788.
Levac, D., H. Colquhoun and K.K. O'Brien. 2010. Scoping Studies: Advancing the Methodology. Implementation Science 5: 1–9. doi:10.1186/1748-5908-5-69.
Li, H., S. Lin and Y. Hwang. 2019. Using Nursing Information and Data Mining to Explore the Factors that Predict Pressure Injuries for Patients at the End of Life. CIN: Computers, Informatics, Nursing 37: 133–40. doi:10.1097/CIN.0000000000000489.
Lin, H., Y.L. Hsu, M.S. Hsu and C.M. Cheng. 2014. Development of a Telehealthcare Decision Support System For Patients Discharged From The Hospital. Telemedicine Journal and E-Health:The Official Journal of the American Telemedicine Association 20(8): 748–56. doi:10.1089/tmj.2013.0261.
Lopez-Guede, J.M., A. Moreno-Fernandez-De-Leceta, A. Martinez-Garcia and M. Grana. 2015. Lynx: Automatic Elderly Behavior Prediction in Home Telecare. BioMed Research International 2015: 1-18. doi:10.1155/2015/201939.
Luo, G., B.L. Stone, B. Fassl, C.G. Maloney, P.H. Gesteland, S.R. Yerram and F.L. Nkoy. 2015. Predicting Asthma Control Deterioration In Children. BMC Medical Informatics and Decision Making 15(84): 1–9. doi:10.1186/s12911-015-0208-9.
Medrano, I.H., J.T. Guijarro, C. Belda, A. Urena, I. Salcedo, L. Espinosa-Anke, et al. 2018. Savana: Re-using Electronic Health Records with Artificial Intelligence. International Journal of Interactive Multimedia and Artificial Intelligence 4(7): 8–12. doi:10.9781/ijimai.2017.03.001.
Risling, T. 2018. Why AI Needs Nursing. Retrieved from Policy Options IRPP website. Retreived December 1, 2018. http://policyoptions.irpp.org/magazines/february-2018/why-ai-needs-nursing/.
Salman, M., A.W. Ahmed, O.A. Khan, B. Raza and K. Latif. 2017. Artificial Intelligence in Bio-Medical Domain An Overview of AI Based Innovations in Medical. International Journal of Advanced Computer Science and Applications 8(8): 319–327.
Semenov, I. and G. Kopanitsa. 2016. Development of a Clinical Decision Support System for the Patients of a Laboratory Service. Studies Health Technolgy Information 228: 90–94.
Sensmeier, J. 2017. Harnessing the Power of Artificial Intelligence. Nursing Management 48(11): 14–19. doi:10.1097/01.NUMA.0000526062.69220.41.
Sharma, A., J. Hostetter, J. Morrison, K. Wang and E. Siegel. 2016. Focused Decision Support: A Data Mining Tool to Query the Prostate, Lung, Colorectal, and Ovarian Cancer Screening Trial Dataset and Guide Screening Management for the Individual Patient. Journal of Digital Imaging 29(2): 160–164. doi:10.1007/s10278-015-9826-0.
Sheikhtaheri, A., F. Sadoughi and Z. Hashemi Dehaghi. 2014. Developing and Using Expert Systems and Neural Networks in Medicine: A Review on Benefits and Challenges. Journal of Medical Systems 38(9): 1–6. doi:10.1007/s10916-014-0110-5.
Sullivan, S.S., S. Hewner, V. Chandola and B.L. Westra. 2019. Mortality Risk in Homebound Older Adults Predicted from Routinely Collected Nursing Data. Nursing Research, 68: 156–66. doi:10.1097/NNR.0000000000000328.
Taylor, R.A., J.R. Pare, A.K. Venkatesh, H. Mowafi, E.R. Melnick, W. Fleischman and M.K. Hall. 2016. Prediction of In-hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data-Driven, Machine Learning Approach. Academic Emergency Medicine 23(3): 269–78. doi:10.1111/acem.12876.
Topol, E.J. 2019. High-Performance Medicine: The Convergence of Human and Artificial Intelligence. Nature Medicine 25: 44–56. doi:10.1038/s41591-018-0300-7.
Topuz, K., F.D. Zengul, A. Dag, A. Almehmi and M.B. Yildirim. 2018. Predicting Graft Survival Among Kidney Transplant Recipients: A Bayesian Decision Support Model. Decision Support Systems 106: 97–109. doi:10.1016/j.dss.2017.12.004.
Tucker, C.S., I. Behoora, H.B. Nembhard, M. Lewis, N.W. Sterling and X.M. Huang. 2015. Machine Learning Classification of Medication Adherence in Patients with Movement Disorders Using Non-wearable Sensors. Computers in Biology and Medicine 66: 120–134. doi:10.1016/j.compbiomed.2015.08.012.
Velikova, M., P.J.F. Lucas and M. Van Der Heijden. 2015. Intelligent Disease Self-Management With Mobile Technology. Computer 48(2): 32–39. doi:10.1109/MC.2015.48.
Whittaker, M., K. Crawford, R. Dobbe, G. Fried, E. Kaziunas, V. Mathur, et al. 2018. AI Now Report 2018. Retrieved December 6, 2018. <https://ainowinstitute.org/AI_Now_2018_Report.pdf>.
Yang, C.S., C.P. Wei, C.C. Yuan and J.Y. Schoung. 2010. Predicting The Length of Hospital Stay of Burn Patients: Comparisons of Prediction Accuracy Among Different Clinical Stages. Decision Support Systems 50(1): 325–35. doi:10.1016/j.dss.2010.09.001.
Yin, H.X. and N.K. Jha. 2017. A Health Decision Support System for Disease Diagnosis Based on Wearable Medical Sensors and Machine Learning Ensembles. IEEE Transactions on Multi-Scale Computing Systems 3(4): 228–41. doi:10.1109/tmscs.2017.2710194.
Yoon, J., C. Davtyan and M.V.D. Schaar. 2017. Discovery and Clinical Decision Support for Personalized Healthcare. IEEE Journal of Biomedical and Health Informatics 21(4): 1133–45. doi:10.1109/JBHI.2016.2574857.
Yousefi, M., R.P.M. Ferreira, J.H. Kim and F.S. Fogliatto. 2018. Chaotic Genetic Algorithm and Adaboost Ensemble Metamodeling Approach for Optimum Resource Planning in Emergency Departments. Artificial Intelligence in Medicine 84: 23–33. doi:10.1016/j.artmed.2017.10.002.
Zlotnik, A., A. Gallardo-Antolin, M.C. Alfaro, M.C.P. Perez and J.M.M. Martinez. 2015. Emergency Department Visit Forecasting and Dynamic Nursing Staff Allocation Using Machine Learning Techniques with Readily Available Open-Source Software. CIN-Computers Informatics Nursing 33(8): 368–77. doi:10.1097/cin.0000000000000173.
Be the first to comment on this!
This article is for subscribers only. To view the entire article
Note: Please enter a display name. Your email address will not be publically displayed