The aim of this systematic review was to synthesize nursing studies leveraging artificial intelligence technology and to offer suggestions for future studies. The search for relevant articles was conducted in November 2018 using four databases, namely MEDLINE (PubMed), CINAHL, PsycINFO, and Ichushi Web (a Japanese medical database). Based on the medical subject headings, i.e., MeSH, the terms “artificial intelligence”, “machine learning”, “deep learning”, “neural networks”, and “nursing” were used for the search. Finally, 17 articles were analyzed. Thirteen studies (76%) were published after 2010. Five studies (29%) focused on management and two (12%) were linked to mental health in the discipline of nursing. The expression “artificial neural network(s)” was employed in nine studies (53%), while “machine learning” was used in eight studies (47%). Most of the studies indicated that artificial intelligence technology achieved high performance regarding the objectives of each study. It appeared that artificial intelligence technology has emerged as a powerful tool to develop nursing science. To further the application of AI technology to nursing science, an interdisciplinary approach (involving the department of informatics and data scientists) and construction of nursing and medical data premised on analysis by AI technology are required.
The term “artificial intelligence” (AI) was coined by John McCarthy at the Dartmouth Conference in 1956 (Association for the Advancement of Artificial Intelligence, 2019). AI and its building blocks, hereafter referred to as AI technology, have rapidly developed since the late 2010s, and this trend is expected to continue for some time in the future. AI is linked to computer systems that mimic human intelligence (i.e., they are capable of learning using the information provided, inferring the best answer, and self-correcting). According to Kaplan and Haenlein (2019), AI is defined as “a system’s ability to correctly interpret external data, learn from such data, and use those learnings to achieve specific goals and tasks through flexible adaptation” (p. 15). In recent years, AI technology has become popular in many households, and internet-focused and/or technology companies such as Alphabet, Amazon, Apple and Microsoft continue to deliver devices and services equipped with AI technology. In the near future, this technology is expected to become indispensable to our lives.
AI is influencing various fields. In medicine, the use of AI in clinical applications is steadily increasing (Hamet & Tremblay, 2017). For example, AI technology is being evaluated for the diagnosis, detection, and/or management of diabetes, cancer, heart disease, psychiatry and head lesions (Han, et al., 2015; Shankaracharya, et al., 2012; Tsao, et al., 2018; Zheng, et al., 2017; Bucinski, et al., 2010; Chiu, et al., 2009; Enshaei, et al., 2015; Sepandi, et al., 2018; Zadeh Shirazi, et al., 2018; Guidi, et al., 2014; Rahmouni, et al., 2008; Redlarski, et al., 2014; Chilamkurthy, et al., 2018; Chekroud, et al., 2016; Fulmer, et al., 2018; Kautzky, et al., 2017; Raeiati Banadkooki, et al., 2018; Ramasubbu, et al., 2016).
The application of AI has delivered results, particularly in radiology, pathology and dermatology (Miller & Brown, 2018). For example, a deep learning model by the AI department at Google can accurately predict the chances of a patient’s survival, long-term admission, or re-admission based on electronic health records (EHRs) (Rajkomar, et al., 2018). In addition, research on the identification of diseases using EHRs has advanced (Benke, 2019). These attempts to apply AI technology have been made in various health fields, demonstrating the potential to significantly advance medical sciences.
AI technology also positively contributes to the field of nursing. The technology exhibits the potential to improve the quality of care and the management of nursing. However, insights and knowledge from previous nursing studies leveraging AI technology have not been synthesized. The objective of this systematic and integrative review is to synthesize nursing studies leveraging AI technology, and to discuss potential applications for future studies.
The databases, search terms, and logical operations employed in this study are presented in Table 1. The search for relevant articles was conducted on November 7, 2018, using four English or Japanese databases, namely MEDLINE (Pubmed), CINAHL, PsycINFO, and Ichushi Web, a Japanese medical database. Based on MeSH terms, “artificial intelligence,” “machine learning,” “deep learning,” “neural networks,” and “nursing” were used with modifications in each database.
Table 1: Databases and search terms
This systematic and integrative review defined relevant articles as nursing studies that employed AI technology. Referring to the nursing definitions of the International Council of Nurses (2002), nursing studies were defined as focusing on the promotion of health, prevention of illness, and care for the physically and mentally ill and disabled people of all ages in all health care facilities and various community settings. Studies with nurses as the subjects were included. The AI technology in this study included machine learning, deep learning, and neural networks. Support vector machines were included in the review. If these technologies were mentioned in an article, that article was considered as relevant. However, data mining, including text mining and web mining, were not a focus of this study, as some studies (Chen & Fawcett, 2016; Westra, et al., 2017) have already addressed these.
Therefore, the inclusion criteria for an article were as follows:
(1) the nursing study employed AI technology;
(2) publication was in English or Japanese;
(3) the original article was in a peer-reviewed journal; and
(4) publication was on or before November 7, 2018.
The exclusion criteria were as follows:
(1) not a nursing study and/or not employing AI technology;
(2) publication in a language other than English or Japanese;
(3) not an original article in a peer-reviewed journal.
The search process leveraged in part the reporting process guide (Moher, Liberati, Tetzlaff, & Altman, 2009), as depicted in Figure 1. From four databases, a total of 580 articles were initially extracted. Following a review of the title and abstract, 535 articles were removed using the inclusion and exclusion criteria. The remaining 45 articles were checked for eligibility by full-text screening. In the end, 17 articles remained.
Figure 1. Flowchart of systematic search and selection of studies
The quality of the articles was assessed using the checklist for quantitative studies (Kmet, Lee, & Cook, 2004). The checklist had 14 components described by the article as having methodological content (e.g., study design, sufficient description of subject characteristics and analytic methods). All 17 articles were deemed appropriate for the analysis.
The last name of the first author, published year, objective(s) of the study, role of AI, machine learning, deep learning, or artificial neural networks in the study, dataset, limitations and key findings regarding the technology, and discipline of nursing were extracted from each article. The discipline of nursing was then categorized based on a focused theme for each article.
The summary of the articles is presented in Table 2. The findings for this review were based on the following: (1) methodology, (2) discipline of nursing, (3) types of AI technology, (4) research objectives and role of AI technology, (5) dataset, (6) key findings, and (7) limitations regarding the AI technology.
2.1 | 2.2 | 2.3 | 2.4 | 2.5 | 2.6
Table 2. Description of Studies Reviewed
Five studies (29%) were reported from the United States (USA) (Bose, et al., 2019; Choi, et al., 2018; Harvey, 1993; Stallings-Welden, et al., 2018; Woolery, et al., 1991), three (18%) from Spain (Ladstätter, et al., 2016; Zlotnik, et al., 2016; Zlotnik, et al., 2015), and two each (12%) from Japan (Yokota, et al, 2018; Yokota, et al., 2017) and Taiwan (Lin, et al., 2006; Tzeng, et al., 2004). In addition, one each (6%) was reported from Austria (Ladstätter, et al., 2010), Brazil (Grübler, et al., 2018), Canada (Beauchet, et al., 2018), China (Chen, et al., 2018), and Italy (Bagnasco, et al., 2015).
Two (12%) studies were published in the 1990s (Harvey, 1993; Woolery, et al., 1991) and 2000s (Lin, et al., 2006; Tzeng, et al., 2004). The remaining 13 (76%) studies were published after 2010 (Bagnasco, et al., 2015; Beauchet, et al., 2018; Bose, et al., 2019; Chen, et al., 2018; Choi, et al., 2018; Grübler, et al., 2018; Ladstätter, et al., 2016; Ladstätter, et al., 2010; Stallings-Welden, et al., 2018; Yokota, et al., 2018; Yokota, et al., 2017; Zlotnik, et al., 2016; Zlotnik, et al., 2015).
Five studies (30%) were classified as directed towards nursing management (Bagnasco, et al., 2015; Grübler, et al., 2018; Tzeng, et al., 2004; Zlotnik, et al., 2016; Zlotnik, et al., 2015). Two each (12%) were classified as directed towards mental health (Ladstätter, et al., 2016; Ladstätter, et al., 2010) and safety management (Yokota, et al., 2017). One each (6%) was classified as focusing on community health (Bose, et al., 2019), heart and vascular diseases (Chen, et al., 2018), convalescence (Stallings-Welden, et al., 2018), acute care (Lin, et al., 2006), diagnosis (Harvey, 1993), and system development (Woolery, et al., 1991). One study (Beauchet, et al., 2018) straddled the two categories of safety management and geriatrics.
The term “artificial neural networks” was employed in nine studies (53%) (Bagnasco, et al., 2015; Beauchet, et al., 2018; Chen, et al., 2018; Grübler, et al., 2018; Harvey, 1993; Ladstätter, et al., 2016; Ladstätter, et al., 2010; Lin, et al., 2006; Zlotnik, et al., 2016). The term “machine learning” was used in eight studies (47%) (Bose, et al., 2019; Choi, et al., 2018; Stallings-Welden, et al., 2018; Tzeng, et al., 2004; Woolery, et al., 1991; Yokota, et al., 2018; Yokota, et al., 2017; Zlotnik, et al., 2015). In one study (6%) (Yokota, et al., 2018), the term “deep learning” was also employed in addition to “machine learning.”
Most studies aimed to predict clinical or managerial outcomes using AI technology. The clinical outcomes centered on fall prediction (Beauchet, et al., 2018; Yokota, et al., 2018; Yokota, et al., 2017), surgery-related injury (Chen, et al., 2018), nausea (Stallings-Welden, et al., 2018), depression (Choi, et al., 2018), and survival of patients (Lin, et al., 2006). The managerial themes were bed allocation (Grübler, et al., 2018), decision support of the probability of admission of patients in emergency departments (Zlotnik, et al., 2016), communication risks (Bagnasco, et al., 2015), nurse burnout (Ladstätter, et al., 2016; Ladstätter, et al., 2010), intention of nurses to quit (Tzeng, et al., 2004), nursing diagnostics (Harvey, 1993), and knowledge acquisition for nurses (Woolery, et al., 1991). Additionally, two studies revealed related factors using AI technology (Ladstätter, et al., 2016; Ladstätter, et al., 2010).
Medical records were the main source of data (Beauchet, et al., 2018; Chen, et al., 2018; Grübler, et al., 2018; Lin, et al., 2006; Stallings-Welden, et al., 2018; Yokota, et al., 2017; Zlotnik, et al., 2016; Zlotnik, et al., 2015). From this dataset, several hundreds to millions of data points were used to test and/or train machines. Data collected from a self-reported questionnaire was employed in four studies (Tzeng, et al., 2004; Ladstätter, et al., 2016; Ladstätter, et al., 2010; Woolery, et al., 1991). The remainder of the studies used a clinical incident reporting system (Yokota, et al., 2018) and a population-based database (Bose, et al., 2019; Choi, et al., 2018).
Most of the studies indicated that AI technology achieved high performance in the prediction of outcomes. In some studies, the performance of AI technology was higher than that of standard statistical methods (Ladstätter, et al., 2010; Lin, et al., 2006).
The limits in sample size for adequate neural network analysis were raised in one study (6%) (Beauchet, et al., 2018). Doubts on relevance and lack of confidence in the model developed were mentioned in three studies (18%) (Bose, et al., 2019; Choi, et al., 2018; Harvey, 1993). Yokota, et al., (2017) pointed out that the constructed fall risk prediction model was a black box, i.e., we do not know how the outcome was derived. Zlotnik, et al., (2015) reported that machine learning would not be able to cope with emergency cases, e.g., in the event of a disaster.
This is the first systematic and integrative review that focused on nursing studies that leveraged AI technology. The application of these technologies in nursing research has increased in recent years. In most studies, AI technology helped achieve the stated purpose. To extend the application of AI technology to nursing sciences, an interdisciplinary approach is required, involving the department of informatics and data scientists, construction of a robust dataset with a large amount of information by promoting multicenter collaborative research, and appropriate wording by the nurse in the description section of the (electronic) medical record to support natural language processing.
The most significant finding of this review is that AI technology demonstrated high-performance capability and attained the objectives in most relevant studies. AI technology can adapt to various nursing disciplines. The relevant studies handled management, mental health, safety management, and vascular diseases, among others. Therefore, it can be suggested that AI technology can significantly aid in developing nursing research. In some studies, the performance of AI technology was higher than that of traditional statistical methods, such as hierarchical stepwise regression (Ladstätter, et al., 2010; Lin, et al., 2006). Machine learning can process a huge number of predictors and combine them interactively and non-linearly (Mullainathan & Spiess, 2017). In some relevant studies (Beauchet, et al., 2018; Chen, et al., 2018; Grübler, et al., 2018; Lin, et al., 2006; Stallings-Welden, et al., 2018; Yokota, et al., 2017; Zlotnik, et al., 2016; Zlotnik, et al., 2015), the medical records of a single hospital were employed as a data source. However, enormous amounts of data are required to train AI technology. Therefore, the prediction accuracy of AI technology can further be improved by constructing a larger dataset from the records of multiple hospitals.
Regarding research settings, the largest number (29%) of papers were from the USA. The second largest (18%) were from Spain, and the third largest (12%) were from both Japan and Taiwan. The Elsevier AI report (2018), which covered the period between 1997 and 2017, identified the top 10 countries with respect to AI papers as being China, US, India, United Kingdom, Japan, Germany, Spain, France, and Canada. The literature examined in this review also reflected this tendency to a large extent. In terms of the published years, most of the studies (76%) were published after 2010. When searching for terms “artificial intelligence, or machine learning, or deep learning, or neural networks” in MEDLINE (PubMed), the number of papers gradually increased after the year 2000 and sharply increased after the year 2010. This is consistent with trends in research involving the use of AI technology in the medical field, and the amount of nursing research using AI technology is expected to increase in the future.
Several limitations within this study must be considered. First, all the databases used in this review were medical. As some nursing studies employing AI, machine learning, deep learning, or artificial neural networks were conducted by interdisciplinary teams, it is conceivable that not all studies were included in this systematic search. However, having used a major medical database, the search conducted in the medical field was exhaustive. Secondly, this review could not include articles written in languages other than English or Japanese. Among the relevant articles, 11 were reported to be from countries where English is not the first language (e.g., Spain, Japan, and Taiwan). In these countries, other nursing articles that leveraged AI technology were possibly published in the local language. Finally, technologies such as AI are being rapidly applied to various academic disciplines. Hence, new nursing studies leveraging these technologies will continue to be published. Therefore, continually reviewing the trends in nursing studies leveraging AI and discussing the fusion of nursing sciences and AI is essential.
AI has the potential to help develop nursing science. To extend the application of AI technology to nursing science, an interdisciplinary approach is indispensable. Traditionally, nurses have been deeply involved with clinical experts. Going forward, collaboration with departments of engineering and informatics, as well as data scientists, is necessary. The construction of a dataset suitable for machine-based analysis is also key. For this purpose, constructing a robust dataset with a large amount of information by promoting multicenter collaborative research is necessary. Finally, we should acknowledge once again the importance of the description section of the electronic medical record contributed by the nurses. Here, important information on the patients is hidden. In this review, a few studies used natural language processing. To facilitate further advances in the field, using appropriate wording with a consideration for secondary and tertiary usage of the described items is necessary.
This systematic and integrative review revealed that the application of AI technology in nursing research has increased in recent years, and that AI technology will be a powerful tool to develop nursing science in the future. To further advance the application of AI technology in nursing science, an interdisciplinary approach is required, involving the department of engineering and informatics, as well as data scientists. In addition, constructing a robust dataset with a large amount of information by promoting multicenter collaborative research is important. Appropriate wording by the nurses in the description section of the (electronic) medical record can facilitate more research based on natural language processing.
The views and opinions expressed in this blog or by commenters are those of the author and do not necessarily reflect the official policy or position of HIMSS or its affiliates.
Powered by the HIMSS Foundation and the HIMSS Nursing Informatics Community, the Online Journal of Nursing Informatics is a free, international, peer reviewed publication that is published three times a year and supports all functional areas of nursing informatics.
Association for the Advancement of Artificial Intelligence (AAAI). (2019). A Brief History of AI. Retrieved from https://aitopics.org/misc/brief-history
Bagnasco, A., Siri, A., Aleo, G., Rocco, G., & Sasso, L. (2015). Applying artificial neural networks to predict communication risks in the emergency department. Journal of Advanced Nursing, 71(10), 2293-2304. doi:10.1111/jan.12691
Beauchet, O., Noublanche, F., Simon, R., Sekhon, H., Chabot, J., Levinoff, E. J., . . . Launay, C. P. (2018). Falls Risk Prediction for older inpatients in acute care medical wards: Is there an Interest to combine an Early Nurse Assessment and the Artificial Neural Network Analysis? The Journal of Nutrition, Health and Aging, 22(1), 131-137. doi:10.1007/s12603-017-0950-z
Benke, K. K. (2019). Data Analytics and Machine Learning for Disease Identification in Electronic Health Records. JAMA Ophthalmology, 137(5):497-498. doi:10.1001/jamaophthalmol.2018.7055
Bose, E., Maganti, S., Bowles, K. H., Brueshoff, B. L., & Monsen, K. A. (2019). Machine Learning Methods for Identifying Critical Data Elements in Nursing Documentation. Nursing Research, 68(1), 65-72. doi:10.1097/nnr.0000000000000315
Bucinski, A., Marszall, M. P., Krysinski, J., Lemieszek, A., & Zaluski, J. (2010). Contribution of artificial intelligence to the knowledge of prognostic factors in Hodgkin's lymphoma. European Journal of Cancer Prevention, 19(4), 308-312. doi:10.1097/CEJ.0b013e32833ad353
Chekroud, A. M., Zotti, R. J., Shehzad, Z., Gueorguieva, R., Johnson, M. K., Trivedi, M. H., . . . Corlett, P. R. (2016). Cross-trial prediction of treatment outcome in depression: a machine learning approach. Lancet Psychiatry, 3(3), 243-250. doi:10.1016/s2215-0366(15)00471-x
Chen, H. L., Yu, S. J., Xu, Y., Yu, S. Q., Zhang, J. Q., Zhao, J. Y., . . . Zhu, B. (2018). Artificial Neural Network: A Method for Prediction of Surgery-Related Pressure Injury in Cardiovascular Surgical Patients. Journal of Wound, Ostomy and Continence Nursing, 45(1), 26-30. doi:10.1097/won.0000000000000388
Chen, L. A., & Fawcett, T. N. (2016). Using Data Mining Strategies in Clinical Decision Making: A Literature Review. CIN: Computers, Informatics, Nursing, 34(10), 448-454. doi:10.1097/cin.0000000000000282
Chilamkurthy, S., Ghosh, R., Tanamala, S., Biviji, M., Campeau, N. G., Venugopal, V. K., . . . Warier, P. (2018). Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study. Lancet, 392(10162), 2388-2396. doi:10.1016/s0140-6736(18)31645-3
Chiu, J. S., Wang, Y. F., Su, Y. C., Wei, L. H., Liao, J. G., & Li, Y. C. (2009). Artificial neural network to predict skeletal metastasis in patients with prostate cancer. Journal of Medical Systems, 33(2), 91-100. doi: 10.1007/s10916-008-9168-2
Choi, J., Choi, J., & Jung, H. T. (2018). Applying Machine-Learning Techniques to Build Self-reported Depression Prediction Models. CIN: Computers, Informatics, Nursing, 36(7), 317-321. doi:10.1097/cin.0000000000000463
Elsevier. (2018). Elsevier AI report. Retrieved from https://public.tableau.com/profile/isabella.cingolani1149#!/vizhome/Els…
Enshaei, A., Robson, C. N., & Edmondson, R. J. (2015). Artificial Intelligence Systems as Prognostic and Predictive Tools in Ovarian Cancer. Annals of Surgical Oncology, 22(12), 3970-3975. doi:10.1245/s10434-015-4475-6
Fulmer, R., Joerin, A., Gentile, B., Lakerink, L., & Rauws, M. (2018). Using Psychological Artificial Intelligence (Tess) to Relieve Symptoms of Depression and Anxiety: Randomized Controlled Trial. JMIR Mental Health, 5(4), e64. doi:10.2196/mental.9782
Grübler, M. D. S., da Costa, C. A., Righi, R. D. R., Rigo, S. J., & Chiwiacowsky, L. D. (2018). A Hospital Bed Allocation Hybrid Model Based on Situation Awareness. CIN: Computers, Informatics, Nursing, 36(5), 249-255. doi:10.1097/cin.0000000000000421
Guidi, G., Pettenati, M. C., Melillo, P., & Iadanza, E. (2014). A machine learning system to improve heart failure patient assistance. IEEE Journal of Biomedical and Health Informatics, 18(6), 1750-1756. doi:10.1109/jbhi.2014.2337752
Hamet, P., & Tremblay, J. (2017). Artificial intelligence in medicine. Metabolism, 69s, S36-s40. doi:10.1016/j.metabol.2017.01.011
Han, L., Luo, S., Yu, J., Pan, L., & Chen, S. (2015). Rule extraction from support vector machines using ensemble learning approach: an application for diagnosis of diabetes. IEEE Journal of Biomedical and Health Informatics, 19(2), 728-734. doi:10.1109/jbhi.2014.2325615
Harvey, R. M. (1993). Nursing diagnosis by computers: an application of neural networks. Nursing Diagnosis List, 4(1), 26-34. doi: 10.1111/j.1744-618X.1993.tb00080.x
International Council of Nurses. (2002). Nursing definitions. Retrieved from: https://www.icn.ch/nursing-policy/nursing-definitions
Kaplan, A., & Haenlein, M. (2019). Siri, Siri, in my hand: Who’s the fairest in the land? On the interpretations, illustrations, and implications of artificial intelligence. Business Horizons, 62(1), 15-25. doi:10.1016/j.bushor.2018.08.004
Kautzky, A., Baldinger-Melich, P., Kranz, G. S., Vanicek, T., Souery, D., Montgomery, S., . . . Kasper, S. (2017). A New Prediction Model for Evaluating Treatment-Resistant Depression. Journal of Clinical Psychiatry, 78(2), 215-222. doi:10.4088/JCP.15m10381
Ladstätter, F., Garrosa, E., Badea, C., & Moreno, B. (2010). Application of artificial neural networks to a study of nursing burnout. Ergonomics, 53(9), 1085-1096. doi:10.1080/00140139.2010.502251
Ladstätter, F., Garrosa, E., Moreno-Jimenez, B., Ponsoda, V., Reales Aviles, J. M., & Dai, J. (2016). Expanding the occupational health methodology: A concatenated artificial neural network approach to model the burnout process in Chinese nurses. Ergonomics, 59(2), 207-221. doi:10.1080/00140139.2015.1061141
Kmet, L., Lee, Robert., & Cook, Linda. (2004). Standard Quality Assessment Criteria for Evaluating Primary Research Papers from a Variety of Fields. Edmonton, AB: Alberta Heritage Foundation for Medical Research. Retrieved from https://www.ihe.ca/publications/standard-quality-assessment-criteria-fo…
Lin, S. P., Lee, C. H., Lu, Y. S., & Hsu, L. N. (2006). A comparison of MICU survival prediction using the logistic regression model and artificial neural network model. Journal of Nursing Research, 14(4), 306-314. doi: 10.1097/01.JNR.0000387590.19963.8e
Miller, D. D., & Brown, E. W. (2018). Artificial Intelligence in Medical Practice: The Question to the Answer? The American Journal of Medicine, 131(2), 129-133. doi:10.1016/j.amjmed.2017.10.035
Moher, D., Liberati, A., Tetzlaff, J., & Altman, D. G. (2009). Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. PLoS Medicine, 6(7), e1000097. doi:10.1371/journal.pmed.1000097
Mullainathan, S., & Spiess, J. (2017). Machine Learning: An Applied Econometric Approach. Journal of Economic Perspectives, 31(2), 87-106. doi: 10.1257/jep.31.2.87
Raeiati Banadkooki, M., Mielke, C., Wolf, K. H., Haux, R., & Marschollek, M. (2018). Automatic Detection of Depression by Using a Neural Network. Studies in health technology and informatics, 251, 3-6. doi: 10.3233/978-1-61499-880-8-3
Rahmouni, H. W., Ky, B., Plappert, T., Duffy, K., Wiegers, S. E., Ferrari, V. A., . . . St John Sutton, M. (2008). Clinical utility of automated assessment of left ventricular ejection fraction using artificial intelligence-assisted border detection. American Heart Journal, 155(3), 562-570. doi:10.1016/j.ahj.2007.11.002
Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., . . . Dean, J. (2018). Scalable and accurate deep learning with electronic health records. Npj Digital Medicine, 1, 10. doi:10.1038/s41746-018-0029-1
Ramasubbu, R., Brown, M. R., Cortese, F., Gaxiola, I., Goodyear, B., Greenshaw, A. J., . . . Greiner, R. (2016). Accuracy of automated classification of major depressive disorder as a function of symptom severity. NeuroImage: Clinical, 12, 320-331. doi:10.1016/j.nicl.2016.07.012
Redlarski, G., Gradolewski, D., & Palkowski, A. (2014). A system for heart sounds classification. PLoS One, 9(11), e112673. doi:10.1371/journal.pone.0112673
Sepandi, M., Taghdir, M., Rezaianzadeh, A., & Rahimikazerooni, S. (2018). Assessing Breast Cancer Risk with an Artificial Neural Network. Asian Pacific Journal of Cancer Prevention, 19(4), 1017-1019. doi:10.22034/apjcp.2018.19.4.1017
Shankaracharya, Odedra, D., Samanta, S., & Vidyarthi, A. S. (2012). Computational intelligence-based diagnosis tool for the detection of prediabetes and type 2 diabetes in India. The Review of Diabetic Studies, 9(1), 55-62. doi:10.1900/rds.2012.9.55
Stallings-Welden, L. M., Doerner, M., Ketchem, E. L., Benkert, L., Alka, S., & Stallings, J. D. (2018). A Comparison of Aromatherapy to Standard Care for Relief of PONV and PDNV in Ambulatory Surgical Patients. Journal of PeriAnesthesia Nursing, 33(2), 116-128. doi:10.1016/j.jopan.2016.09.001
Tsao, H. Y., Chan, P. Y., & Su, E. C. (2018). Predicting diabetic retinopathy and identifying interpretable biomedical features using machine learning algorithms. BMC Bioinformatics, 19(Suppl 9), 283. doi:10.1186/s12859-018-2277-0
Tzeng, H. M., Hsieh, J. G., & Lin, Y. L. (2004). Predicting nurses' intention to quit with a support vector machine: a new approach to set up an early warning mechanism in human resource management. CIN: Computers, Informatics, Nursing, 22(4), 232-242. doi: https://doi.org/10.1097/00024665-200407000-00012
Westra, B. L., Sylvia, M., Weinfurter, E. F., Pruinelli, L., Park, J. I., Dodd, D., . . . Delaney, C. W. (2017). Big data science: A literature review of nursing research exemplars. Nursing Outlook, 65(5), 549-561. doi:10.1016/j.outlook.2016.11.021
Woolery, L., Grzymala-Busse, J., Summers, S., & Budihardjo, A. (1991). The use of machine learning program LERS-LB 2.5 in knowledge acquisition for expert system development in nursing. CIN: Computers, Informatics, Nursing, 9(6), 227-234.
Yokota, S., Endo, M., & Ohe, K. (2017). Establishing a Classification System for High Fall-Risk Among Inpatients Using Support Vector Machines. CIN: Computers, Informatics, Nursing, 35(8), 408-416. doi:10.1097/cin.0000000000000332
Yokota, S., Shinohara, E., & Ohe, K. (2018). Can Staff Distinguish Falls: Experimental Hypothesis Verification Using Japanese Incident Reports and Natural Language Processing. Studies in Health Technology and Informatics, 250, 159-163. doi: 10.1097/cin.0000000000000332
Zadeh Shirazi, A., Seyyed Mahdavi Chabok, S. J., & Mohammadi, Z. (2018). A novel and reliable computational intelligence system for breast cancer detection. Medical & Biological Engineering & Computing, 56(5), 721-732. doi:10.1007/s11517-017-1721-z
Zheng, T., Xie, W., Xu, L., He, X., Zhang, Y., You, M., . . . Chen, Y. (2017). A machine learning-based framework to identify type 2 diabetes through electronic health records. International Journal of Medical Informatics, 97, 120-127. doi:10.1016/j.ijmedinf.2016.09.014
Zlotnik, A., Alfaro, M. C., Perez, M. C., Gallardo-Antolin, A., & Martinez, J. M. (2016). Building a Decision Support System for Inpatient Admission Prediction With the Manchester Triage System and Administrative Check-in Variables. CIN: Computers, Informatics, Nursing, 34(5), 224-230. doi:10.1097/cin.0000000000000230
Zlotnik, A., Gallardo-Antolin, A., Cuchi Alfaro, M., Perez Perez, M. C., & Montero Martinez, J. M. (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), 368-377. doi:10.1097/cin.0000000000000173
Ryota Kikuchi, PhD, RN, PHN is a research associate of the Department of Pediatric and Family Nursing, Division of Health Sciences, Graduate School of Medicine, Osaka University. This study was supported by JSPS KAKENHI Grant Number 17K17845. The author would like to thank A Kikuchi B.A. for his deep insights used for this work.