Workplace Predictors of Quality and Safe Patient Care Delivery Among Nurses Using Machine Learning Techniques

Decoding machine learning in nursing research: A scoping review of effective algorithms

INTRODUCTION

The rapid evolution of artificial intelligence (AI) technology has revolutionized healthcare, particularly through the integration of AI into health information systems. This transformation has significantly impacted the roles of nurses and nurse practitioners, prompting extensive research to assess the effectiveness of AI-integrated systems. This scoping review focuses on machine learning (ML) used in nursing, specifically investigating ML algorithms, model evaluation methods, areas of focus related to nursing, and the most effective ML algorithms.

DESIGN

The scoping review followed the Preferred Reporting Items for Systematic Review and Meta-Analysis Extension for Scoping Reviews (PRISMA-ScR) guidelines.

METHODS

A structured search was performed across seven databases according to PRISMA-ScR: PubMed, EMBASE, CINAHL, Web of Science, OVID, PsycINFO, and ProQuest. The quality of the final reviewed studies was assessed using the Medical Education Research Study Quality Instrument (MERSQI).

RESULTS

Twenty-six articles published between 2019 and 2023 met the inclusion and exclusion criteria, and 46% of studies were conducted in the US. The average MERSQI score was 12.2, indicative of moderate- to high-quality studies. The most used ML algorithm was Random Forest. The four second-most used were logistic regression, least absolute shrinkage and selection operator, decision tree, and support vector machine. Most ML models were evaluated by calculating sensitivity (recall)/specificity, accuracy, receiver operating characteristic (ROC), area under the ROC (AUROC), and positive/negative prediction value (precision). Half of the studies focused on nursing staff or students and hospital readmission or emergency department visits. Only 11 articles reported the most effective ML algorithm(s).

CONCLUSION

The scoping review provides insights into the current status of ML research in nursing and recognition of its significance in nursing research, confirming the benefits of ML in healthcare. Recommendations include incorporating experimental designs in research studies to optimize the use of ML models across various nursing domains.

CLINICAL RELEVANCE

The scoping review demonstrates substantial clinical relevance of ML applications for nurses, nurse practitioners, administrators, and researchers. The integration of ML into healthcare systems and its impact on nursing practices have important implications for patient care, resource management, and the evolution of nursing research.

Retention of international nurses in receiving country: Voices of Indonesian nurses in Japanese healthcare facilities

Objectives

This study aimed to explore the voices of Indonesian migrant nurses on their retention in Japanese healthcare facilities.

Methods

A descriptive qualitative study was conducted between June and September 2023. The snowball sampling method was utilized to recruit 22 Indonesian nurses working in healthcare facilities in seven prefectures of Japan. Semi-structured interviews were conducted based on their shared experiences. All interview data were audio-recorded, transcribed verbatim, and analyzed using thematic analysis.

Results

Six prominent themes and 15 subthemes emerged: 1) organizational factors (caring leader, involvement in decision making, career development, and participation in training); 2) social support systems (group support, colleagues support and friend support); 3) individual drive (lifelong learning and persistent); 4) national policies (government support in public service and flexibility in finding a comfortable placement); 5) family factors (positive support of child education and development and maintaining relationship with spouse); and 6) economic factors (staying due to high salary and increasing income streams).

Conclusions

Retention of Indonesian migrant nurses in Japan is a multifaceted challenge that hinges on various interconnected factors. This study has gone some way toward enhancing our understanding of international nurse retention in the receiving countries. Corresponding supports at the individual, family, organizational, economic, social, and national policy levels should be considered to keep them in their destination countries.

Workplace Violence and Worker Well-Being: A Preliminary Cross-Sectional Study

PURPOSE

To investigate the prevalence of workplace violence (WPV) in home health care and long-term care facilities (LTCFs) and explore the relationship between WPV and worker well-being.

METHOD

A cross-sectional survey was conducted with health care workers in an agency that provided care in homes or LTCFs. Six measures of worker well-being were collected: satisfaction with work and life, work-related rumination, work/family conflict, burnout, and turnover intention. Surveys also assessed type and frequency of WPV.

RESULTS

Seventeen participants completed surveys. Verbal abuse by patients was the most often experienced type of WPV. Employees who reported experiencing WPV had higher burnout and lower satisfaction with work and life.

CONCLUSION

WPV routinely occurs in home health care and LTCFs and appears to be related to worker well-being. Facility managers who can control WPV will likely impact the well-being of employees. [Journal of Gerontological Nursing, 50(11), 44-52.].

Workplace Predictors of Violence against Nurses Using Machine Learning Techniques: A Cross-Sectional Study Utilizing the National Standard of Psychological Workplace Health and Safety

Background: Nurses experience an alarming rate of violence in the workplace. While previous work has indicated that working conditions play an important role in workplace violence outcomes, these studies have not used comprehensive and systematically operationalized variables. Methods: Through cross-sectional survey responses from 4066 British Columbian nurses, we identified which of the 13 psychosocial factors, as outlined in the National Standard of Psychological Workplace Health and Safety, are most predictive of workplace violence perpetrated against nurses by patients and their visitors (Type II violence) and organizational employees (Type III violence). Results: Eighty-seven percent of respondents indicated that they had experienced Type II violence, whereas 48% indicated they had experienced Type III violence over the last year. Lack of physical safety, workload management, and psychological protection were the top three psychosocial factors in the workplace predictive of Type II violence, whereas lack of civility and respect, organizational culture, and psychological support were the top three factors associated with Type III violence. Conclusions: The findings in this study shed light on the distinct psychosocial factors in the workplace in need of investment and intervention to address Type II and III violence.

The Association between Mental Health Symptoms and Quality and Safety of Patient Care before and during COVID-19 among Canadian Nurses

(1) Background: While the association between nurse mental health and quality and safety of patient care delivery was well documented pre-pandemic, fewer research studies have examined this relationship in the context of COVID-19. This study examines the impact of various mental health symptoms experienced by nurses on quality and safety before and during the COVID-19 pandemic; (2) Methods: A secondary analysis of cross-sectional survey data from 4729 and 3585 nurses in one Canadian province between December 2019 and June-July 2020 was conducted. Data were analyzed using between group difference tests and logistic regression; (3) Results: Compared to pre-COVID-19, during COVID-19 nurses reported a higher safety grade, a greater likelihood of recommending their units for care and lower quality of nursing care. Most mental health symptoms were higher during COVID-19 and higher levels of mental health symptoms were correlated with lower ratings of quality and safety both pre- and during COVID-19; (4) Conclusion: Mental health symptoms have implications for nurses’ quality and safety of patient care delivery, with the association between mental health symptoms and quality and safety following a dose–response relationship before and during COVID-19. These findings suggest that it is worthwhile for nurse mental health symptoms to be included as hospital level performance metrics.