Detection of factors affecting kidney function using machine learning methods.

Due to the increasing prevalence of chronic kidney disease and its high mortality rate, study of risk factors affecting the progression of the disease is of great importance. Here in this work, we aim to develop a framework for using machine learning methods to identify factors affecting kidney function. To this end classification methods are trained to predict the serum creatinine level based on numerical values of other blood test parameters in one of the three classes representing different ranges of the variable values. Models are trained using the data from blood test results of healthy and patient subjects including 46 different blood test parameters. The best developed models are random forest and LightGBM. Interpretation of the resulting model reveals a direct relationship between vitamin D and blood creatinine level. The detected analogy between these two parameters is reliable, regarding the relatively high predictive accuracy of the random forest model reaching the AUC of 0.90 and the accuracy of 0.74. Moreover, in this paper we develop a Bayesian network to infer the direct relationships between blood test parameters which have consistent results with the classification models. The proposed framework uses an inclusive set of advanced imputation methods to deal with the main challenge of working with electronic health data, missing values. Hence it can be applied to similar clinical studies to investigate and discover the relationships between the factors under study.

Investigating the effectiveness of innovative intervention based on compassion, awareness, resilience, and empowerment on burnout in nurses of two educational hospitals in Isfahan.

BACKGROUND: Burnout is a syndrome of emotional exhaustion, depersonalization, and low professional efficacy that health workers, especially nurses, experience the highest rates of this. Burnout causes stress and negative attitude towards work and feeling unable to perform tasks in the person. The purpose of this study was to investigate the effect of a method called compassion, awareness, resilience, and empowerment (CARE) on nurses' burnout. MATERIALS AND METHODS: This study was a semi-experimental study with control group, the statistical population in this study was nurses of Kashani Hospital in Isfahan as intervention group and nurses of Al-Zahra Hospital as control group. The samples were selected by stratified sampling. For both groups before and after and 3 months after the intervention, the burnout questionnaire (Maslach Burnout Inventory) was completed. The intervention was performed in 5 sessions of 90 min 1 day a week. Data were analyzed by SPSS version 25 software (IBM Inc., USA) and independent t-test, repeated measures analysis of variance and Chi-square test and Friedman test, significance level was set at P < 0.05. RESULTS: The comparison of mean and intensity of burnout and two dimensions of emotional exhaustion and depersonalization showed a difference between the two groups and this difference was statistically significant (P < 0.05). Mean of Individual performance also had a statistically significant difference between the two groups (P < 0.05), but its intensity did not change. CONCLUSION: CARE method can be effective in burnout of nurses and it can be used as a practical method. This training program can be implemented both preservice and in-service for health workers.

Corrective Exercises or Ergonomic Principles for Workers with Low Back Pain.

INTRODUCTION: Work-related musculoskeletal disorders (WRMSD) are considered the main cause of occupational diseases. Health care workers, nursing assistants, and service forces that perform manual labor are the most vulnerable to musculoskeletal disorders, especially low back pain, due to the nature of their jobs. The purpose of this study was to compare the effectiveness of corrective exercise training to ergonomic principles training on low back pain in nursing assistants and service forces. METHODS: A nonrandomized clinical trial study was done on 75 staff (nursing assistants and service forces) with low back pain. The participants were divided into three groups: corrective exercise training, ergonomic principles training, and control group. Pain intensity and disability questionnaires were completed before and after 8 weeks of intervention by each group and analyzed. RESULTS: The mean intensity of pain after intervention in corrective exercises group (3.8 ± 1.5) was markedly less than the ergonomic group (4.7 ± 1.4) and control group (5.5 ± 1.7) (P = 0.001). The mean disability score after intervention in the corrective exercises group (17.3 ± 9.6) was significantly less than the ergonomic group (21.8 ± 12.6) and control group (25.3 ± 11.2) (P < 0.001). CONCLUSION: While corrective exercises training and ergonomic principles training both have a significant effect on reducing the severity of pain and disability caused by low back pain, corrective exercises training is more effective than ergonomic principle training.