The application and use of artificial intelligence in cancer nursing: A systematic review

TY - JOUR

T1 - The application and use of artificial intelligence in cancer nursing: A systematic review

AU - O'Connor, Siobhán

AU - Vercell, Amy

AU - Wong, David

AU - Yorke, Janelle

AU - Fallatah, Fatmah Abdulsamad

AU - Cave, Louise

AU - Chen, Lu-Yen Anny

N1 - Funding Information: Only one study, Im and Chee (2011) evaluated an AI-based tool with nurses to help them make better decisions about managing cancer pain, suggesting improvements to the design and functionality of the digital tool. However, its effect on clinical decision making and quality of patient care was not assessed. The impact of AI based digital tools in clinical practice settings has been investigated in other studies. Ginestra et al. (2019) developed an early warning score (EWS) system with machine learning algorithms to predict sepsis or septic shock. This was deployed in a large academic hospital in the United States with nurses and physicians, who received alerts from the EWS system about at-risk patients, but their perceptions of the AI based tool were poor as most reported no change in their understanding of patient risk and only a handful of alerts led to change in patient management. Furthermore, few randomized controlled trials of AI-based digital health interventions have been published which are needed to generate robust evidence of its effectiveness in improving outcomes (Angus, 2020). Other studies have examined implementation issues when integrating machine learning models into clinical practice and reported numerous socio-technical factors such as the unfamiliarity of AI among clinicians and lack of AI education, trust in the accuracy and utility of predictive models, and IT support among other issues that affected this process (Joshi et al., 2022; Sandhu et al., 2020).The review also revealed that nurses led the research studies or actively participated in developing and testing AI algorithms in oncology, and in one case implemented and evaluated an AI based tool in clinical practice. However, in a few studies nurses were more passively involved or not included which reflects the findings of other reviews of AI in the nursing profession (von Gerich et al., 2022; Seibert et al., 2021). Although nurses often work in multidisciplinary teams and environments, particularly in acute hospital settings, Ronquillo et al. (2021) advocate for nurses to take a lead in the development and application of AI techniques such as machine learning and NLP in healthcare. This could help ensure that any predictive models and AI-based digital tools have clinical utility and take account of the workflow and workload of nurses in oncology, as nurses are the primary carer givers in clinical settings. Furthermore, AI tools for cancer patients were missing from the review but are under development (van Wijk, 2022), as predictive algorithms may support patient self-management and are being integrated into health apps, wearable and assisted living devices, and robotics. For instance, Battersby et al. (2018) used a patient-reported outcome measure (PROM) to develop and validate an online tool to predict postoperative bowel dysfunction to support cancer specialists and patients. This area of AI research is likely to expand in the future as more focus is given to supporting cancer patients to self-care at home. Publisher Copyright: © 2024 The Authors

PY - 2024/1/14

Y1 - 2024/1/14

N2 - PurposeArtificial Intelligence is being applied in oncology to improve patient and service outcomes. Yet, there is a limited understanding of how these advanced computational techniques are employed in cancer nursing to inform clinical practice. This review aimed to identify and synthesise evidence on artificial intelligence in cancer nursing.MethodsCINAHL, MEDLINE, PsycINFO, and PubMed were searched using key terms between January 2010 and December 2022. Titles, abstracts, and then full texts were screened against eligibility criteria, resulting in twenty studies being included. Critical appraisal was undertaken, and relevant data extracted and analysed. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed.ResultsArtificial intelligence was used in numerous areas including breast, colorectal, liver, and ovarian cancer care among others. Algorithms were trained and tested on primary and secondary datasets to build predictive models of health problems related to cancer. Studies reported this led to improvements in the accuracy of predicting health outcomes or identifying variables that improved outcome prediction. While nurses led most studies, few deployed an artificial intelligence based digital tool with cancer nurses in a real-world setting as studies largely focused on developing and validating predictive models.ConclusionElectronic cancer nursing datasets should be established to enable artificial intelligence techniques to be tested and if effective implemented in digital prediction and other AI-based tools. Cancer nurses need more education on machine learning and natural language processing, so they can lead and contribute to artificial intelligence developments in oncology.

AB - PurposeArtificial Intelligence is being applied in oncology to improve patient and service outcomes. Yet, there is a limited understanding of how these advanced computational techniques are employed in cancer nursing to inform clinical practice. This review aimed to identify and synthesise evidence on artificial intelligence in cancer nursing.MethodsCINAHL, MEDLINE, PsycINFO, and PubMed were searched using key terms between January 2010 and December 2022. Titles, abstracts, and then full texts were screened against eligibility criteria, resulting in twenty studies being included. Critical appraisal was undertaken, and relevant data extracted and analysed. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were followed.ResultsArtificial intelligence was used in numerous areas including breast, colorectal, liver, and ovarian cancer care among others. Algorithms were trained and tested on primary and secondary datasets to build predictive models of health problems related to cancer. Studies reported this led to improvements in the accuracy of predicting health outcomes or identifying variables that improved outcome prediction. While nurses led most studies, few deployed an artificial intelligence based digital tool with cancer nurses in a real-world setting as studies largely focused on developing and validating predictive models.ConclusionElectronic cancer nursing datasets should be established to enable artificial intelligence techniques to be tested and if effective implemented in digital prediction and other AI-based tools. Cancer nurses need more education on machine learning and natural language processing, so they can lead and contribute to artificial intelligence developments in oncology.

UR - http://www.scopus.com/inward/record.url?scp=85184067956&partnerID=8YFLogxK

U2 - 10.1016/j.ejon.2024.102510

DO - 10.1016/j.ejon.2024.102510

M3 - Article

SN - 1462-3889

VL - 68

JO - European Journal of Oncology Nursing

JF - European Journal of Oncology Nursing

M1 - 102510

ER -