Impact of Artificial Intelligence in Nursing for Geriatric Clinical Care for Chronic Diseases: A Systematic Literature Review

• Published in: IEEE access 2024, Vol.12, p.122557-122587
• Main Authors: Moghadam, Mahdieh Poodineh, Moghadam, Zabih Allah, Qazani, Mohammad Reza Chalak, Plawiak, Pawel, Alizadehsani, Roohallah
• Format: Article
• Language: English
• Subjects: Artificial intelligence; chronic disease; Deep learning; Diseases; Geriatrics; Machine learning; Medical diagnostic imaging; Medical services; Nurse; Older adults; older patients
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3450970

Nurses are essential in managing the healthcare of older adults, particularly those over 65, who often face multiple chronic conditions. This group requires comprehensive physical, mental, and functional care. Recent advancements in artificial intelligence (AI) have significantly improved nursing capabilities by enabling real-time health monitoring, thus bolstering the early detection and prevention of severe health issues. Despite these advancements, the current systematic literature predominantly focuses on machine learning (ML) applications for a limited set of chronic diseases, often overlooking the extensive capabilities of deep learning (DL) technologies. Additionally, these reviews cover a narrow spectrum of studies, potentially needing broader insights and developments in the field. To address these shortcomings, our study conducts a systematic literature review of ML and DL applications in geriatric care for chronic disease management. We meticulously analyzed peer-reviewed articles published from 2014 to 2024, concentrating on AI technologies in elderly care. This review included 76 selected articles from leading publishers such as Elsevier, Springer, IEEE, MDPI, Wiley, Taylor & Francis, Nature, Cambridge University Press, Oxford University Press, and arXiv, which we categorized into three main groups: Neurological disorders (27 articles), Mental Health disorders (22 articles), and Physical/physiological disorders (27 articles). Our findings reveal that Random Forest, logistic regression, and convolutional neural network (CNN) are the most frequently used AI techniques, typically evaluated by accuracy metrics and the area under the curve (AUC). The findings indicate that although AI applications in geriatric care are promising, they require significant enhancements in technology and methodology to improve accuracy and reliability. Future research should focus on developing advanced AI tools, integrating cutting-edge deep learning models and comprehensive datasets to refine diagnostics and treatment protocols for chronic diseases in the elderly, ultimately enhancing patient outcomes.