The length of hospital stay (LOS) is a significant indicator of the quality of patient care, hospital efficiency, and operational resilience. Considering the importance of LOS in hospital resource management, this research aims to improve the accuracy of LOS prediction using hyperparameter optimization (HPO). Expert physicians and related studies were reviewed to determine the variables affecting LOS. The electronic medical records of 200 patients in the department of internal medicine of a hospital in Iran were collected randomly. As the performance of machine learning (ML) models can vary based on the characteristics of the features, several models were applied and evaluated in this study. In particular, k-nearest neighbors (KNN), multivariate regression, decision tree (DT), random forest (RF), artificial neural network (ANN), and XGBoost have been evaluated and improved. The genetic algorithm (GA) was applied to optimize the tree-based models. In addition, the dummy coding technique, sometimes called the One-Hot encoding, was used to encode categorical features to increase prediction accuracy. Compared with other algorithms, the XGBoost model optimized by GA (XGB_GA) achieved higher accuracy and better prediction performance. The mean and median of absolute errors in the test dataset for this model were 1.54 and 1.14 days, respectively. In other words, the XGB_GA model reduced the mean absolute error by 37%, which is beneficial in the reliable design of a clinical decision support system.

Introduction: The importance of using the competent managers in the healthcare system, shows the need to recognize their competencies and having standards to measure competencies. In this regard, the purpose of this article is to determine the validity and reliability of the competency assessment tool of the American College of Health Care Executives for the managers of healthcare networks in Zanjan province. Methods: This study is a descriptive-analytical study in which data collection was performed using the American College of Health Care Executives Competencies Assessment tool. This tool was provided to 30 healthcare management professors and experts, in Zanjan province. To investigate the validity, internal consistency and repeatability Content Validation methods, Cronbach's Alpha coefficient and Retesting were used respectively. Data were analyzed using Excel 2010 and SPSS 18 software. Results: The results showed that 235 out of 302 questions related to the American College of Health Care Executives Competencies Assessment tool had low content validity and should be rejected. The content validity index of the final questionnaire was calculated to be 0.84, which is acceptable. The results also showed that the final questionnaire was reliable with α=0.98 and repeatable. Conclusion: Utilizing a framework to assess the competencies of healthcare network managers can be of benefit in choosing qualified managers. According to the results of this study, the provided tool shows a desirable reliability and a fairly convenient validity to be used in healthcare networks of Zanjan province.

Background & Aims: The present study aimed to evaluate the relationship between teamwork and performance of the medical staff of Shahid Rajaei Cardiovascular, Medical and Research Center in Tehran, Iran. In a health system, teamwork is highly important for increasing the quality of services and the provision of safe and effective care. In addition, teamwork is recognized as an integral part of safe and efficient performance in a hospital. In addition, patient safety and health are considered a critical issue in the health systems of various countries. Therefore, teamwork and communication to prevent and reduce the medical staff's errors are of utmost importance. The present study was carried out to assess the relationship between the teamwork of nurses and the performance of the medical staff of Shahid Rajaei Cardiovascular, Medical and Research Center in Tehran.Materials & Methods: This descriptive-analytical research was performed in 2016. The statistical population included all nurses with a BSc, MSc, or higher degree working at medical centers of the university (n=290). The present research was carried out as correlational research, which is a type of descriptive study (nonexperimental) that evaluates the relationship among variables based on research objectives. In total, 290 individuals were selected by simple non-random sampling method, and data were collected using a staff performance questionnaire by Choharie et al. and a teamwork questionnaire by Luncheon. The validity and reliability of the researcher-based questionnaire used in the present study were confirmed, and data analysis was performed in SPSS version 16 using the Pearson correlation coefficient and t-test. Results: In the evaluation of the correlation of two variables, the Pearson correlation coefficient will be applied if both variables are in relative and distance scale. If the correlation coefficient of the population is ρ and the correlation coefficient is a sample with n volume of the population r, r might be obtained randomly. To this end, we exploited the significance test of the correlation coefficient to determine whether the two variables were random or independent. In other words, the question was: are the correlation coefficient of community zero or not. The coefficient estimates the level of correlation between two distance or relative variables with a value in the range of +1 and -1. A positive value is interpreted as changes occurred in the two variables in the same direction. In other words, an increase in one variable leads to an increase in the other variable. On the other hand, a negative r value means that the two variables operate in the opposite direction. In other words, an increase in the value of one variable decreases the value of the other variable and vice versa. In addition, a zero value shows the lack of relationship between the two variables, whereas a positive and negative value is indicative of a completely positive and completely negative correlation, respectively. In the present study, the mean and standard d...

No abstract