The article, “Use of machine learning to predict creativity among nurses: a multidisciplinary approach” by Rola H. Mudallal, Majd T. Mrayyan, and Mohammad Kharabsheh, published in BMC Nursing in 2025, investigates the largely underexplored area of creativity within the nursing profession.
Background and Rationale: In an era defined by rapid advancements in science and technology, creativity has become an increasingly vital requirement in nursing to meet the evolving daily needs of patients and navigate complex healthcare systems. While its importance for organizational success and the generation of innovative ideas in patient care is acknowledged, research specifically focusing on nurses’ creativity and its influencing factors remains limited. This critical gap underscores the necessity for deeper empirical insights into the psychological and social elements that foster creativity among nursing staff.
Purpose and Objectives: This study was primarily aimed to address this gap by:
- Exploring the various factors that influence nurses’ creativity.
- Assessing the self-perceived level of creativity among Jordanian nurses.
- Developing a sophisticated decision support system (DSS) utilizing machine learning (ML) techniques to accurately predict creativity levels among nurses. This represents an innovative application of artificial intelligence (AI) in nursing research, designed to analyze the dynamic and non-linear characteristics of human creativity.
Methodology: The researchers adopted a multidisciplinary design, thoughtfully blending traditional statistical methods with advanced machine learning algorithms. This approach integrated descriptive, cross-sectional, and correlational designs to comprehensively understand and assess nurses’ creativity. The study recruited a convenience sample of 191 registered nurses from eight hospitals (both private and public) across four major governorates in Jordan, ensuring a representation of the broader nursing community. Data was collected via an online survey, and variables measured included self-rated creativity, humble leadership, psychological safety, and various personal and work environment characteristics.
Key Findings: The study yielded several significant insights:
- Jordanian staff nurses reported a notably high level of creativity (M = 44.95).
- Through multiple linear regression analysis, five principal factors were identified as significant predictors of nurses’ creativity: humble leadership, psychological safety, years of experience, official quality initiatives, and education level. These factors collectively accounted for approximately 30% of the variance observed in perceived creativity.
- The machine learning model demonstrated strong prediction performance with high precision. Specifically, the Naïve Bayes classifier exhibited impressive recall rates: 99% for psychological safety, approximately 98% for both gender and time commitment, 96% for years of experience, 92% for nurse age, and 82% for humble leadership. The study highlighted that K-star and Naïve Bayes classifiers provided superior classification accuracy and F-measure compared to other ML classifiers evaluated.
- Crucially, a decision support system (DSS) was successfully developed based on these findings, aiming to assist nurse managers in predicting and evaluating the creativity levels of their nursing staff.
Implications: The authors conclude by offering actionable recommendations derived from their findings. They advise nurse managers to actively foster flexible leadership styles, cultivate a psychologically safe work environment, and strongly encourage staff development initiatives to enhance nurses’ creativity. The newly developed DSS is presented as a valuable, objective, and data-driven tool that can significantly aid nurse managers in making more informed decisions regarding staff allocation, professional development, and resource optimization, thereby ultimately contributing to improved patient outcomes and operational efficiency. The study further advocates for the increased adoption of machine learning models in nursing research, citing their demonstrated precision and predictive power in addressing complex healthcare challenges.
Reference: Mudallal, R. H., Mrayyan, M. T., & Kharabsheh, M. (2025). Use of machine learning to predict creativity among nurses: a multidisciplinary approach. BMC Nursing, 24(539). https://doi.org/10.1186/s12912-025-03151-4