Development of a Nurse Turnover Prediction Model in Korea Using Machine Learning

Predictive modeling of burnout based on organizational culture perceptions among health systems employees: a comparative study using correlation, decision tree, and Bayesian analyses

Burnout is a significant concern, particularly within the healthcare field, affecting both nurses and physicians. It is a common issue in health systems, which encompass a range of healthcare facilities, such as hospitals, physician practices, ambulatory sites, and administrative offices like finance. Despite this, there has not been an extensive exploration of burnout in employees working directly with patients versus those in non-patient-facing roles within these health systems. It is important to note that organizational culture plays a crucial role in influencing various aspects of employees' work-life balance and their experiences of burnout. This study adopts a cross-sectional design, involving the distribution of a 57-question Likert scale survey to employees in health systems. These employees serve in various roles, both patient-facing and non-patient-facing, within jointly owned healthcare organizations, which encompass hospitals, ambulatory sites, and administrative offices. The survey was disseminated through trade organizations and employees at the managerial level and above within these health systems. Data was collected between October 2022 and January 2023, resulting in a total of 67 responses. The study employs correlation analysis to explore the connection between organizational culture and burnout. Furthermore, a decision tree model is constructed to predict burnout scores based on survey responses, specifically the question regarding the perceived positivity of the organizational culture. The decision tree models indicate that perceiving organizational culture as positive, safety-oriented, and supportive predicts various outcomes for individuals, including job retention, positive experiences with patients, increased callousness, and stimulation while working with colleagues. Bayesian analysis, considering the small sample size, reinforces these findings and provides a different perspective, incorporating prior knowledge and credible intervals. An association test suggests a strong link between a positive organizational culture and burnout symptoms, while another test supports a connection with engagement signs. Similar to nurses and physicians, administrative health systems' personnel are susceptible to burnout. Organizational culture can affect burnout. Therefore, health systems' leaders should cultivate an organizational culture that protects against burnout.

Status and related factors of professional growth among young nursing talents: a cross-sectional study in China

BACKGROUND

The shortage of nurses has been a global human resources problem. A good professional growth environment is essential to developing potential nursing students and attracting nurses to join, and it has great significance in reducing nurse turnover. However, nurses' comprehensive perceptions of professional growth have not yet been examined.

METHODS

A cluster sampling method was used to conduct a professional growth questionnaire survey on young nursing talents from a large Chinese public tertiary A hospital in March 2022.

RESULTS

The score of professional growth among 243 young nursing talents was 57.92 ± 9.607, with a scoring rate of 77.23%. The scores for dimensions of professional growth, from lowest to highest, were rehabilitation growth, promotion speed, professional goal progress, and professional ability development. Attitudes towards participating in training, service as the quality manager or clinical teacher, self-efficacy, professional title, work-family support, education, and organizational commitment of young nursing talents were significantly associated with professional growth.

CONCLUSION

The professional growth of young nursing talents was at a moderate level and needed to be strengthened. Nursing leaders and managers are expected to develop management practices to enhance young nursing talents' professional growth in combination with the related factors.

Predicting Nurse Turnover for Highly Imbalanced Data Using the Synthetic Minority Over-Sampling Technique and Machine Learning Algorithms

Predicting nurse turnover is a growing challenge within the healthcare sector, profoundly impacting healthcare quality and the nursing profession. This study employs the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance issues in the 2018 National Sample Survey of Registered Nurses dataset and predict nurse turnover using machine learning algorithms. Four machine learning algorithms, namely logistic regression, random forests, decision tree, and extreme gradient boosting, were applied to the SMOTE-enhanced dataset. The data were split into 80% training and 20% validation sets. Eighteen carefully selected variables from the database served as predictive features, and the machine learning model identified age, working hours, electric health record/electronic medical record, individual income, and job type as important features concerning nurse turnover. The study includes a performance comparison based on accuracy, precision, recall (sensitivity), F1-score, and AUC. In summary, the results demonstrate that SMOTE-enhanced random forests exhibit the most robust predictive power in the classical approach (with all 18 predictive variables) and an optimized approach (utilizing eight key predictive variables). Extreme gradient boosting, decision tree, and logistic regression follow in performance. Notably, age emerges as the most influential factor in nurse turnover, with working hours, electric health record/electronic medical record usability, individual income, and region also playing significant roles. This research offers valuable insights for healthcare researchers and stakeholders, aiding in selecting suitable machine learning algorithms for nurse turnover prediction.