3790 research outputs found
Sort by
Comparing machine learning algorithms to predict 5-year survival in patients with chronic myeloid leukemia
No full textIntroduction Chronic myeloid leukemia (CML) is a myeloproliferative disorder resulting from the translocation of chromosomes 19 and 22. CML includes 15-20 of all cases of leukemia. Although bone marrow transplant and, more recently, tyrosine kinase inhibitors (TKIs) as a first-line treatment have significantly prolonged survival in CML patients, accurate prediction using available patient-level factors can be challenging. We intended to predict 5-year survival among CML patients via eight machine learning (ML) algorithms and compare their performance. Methods The data of 837 CML patients were retrospectively extracted and randomly split into training and test segments (70:30 ratio). The outcome variable was 5-year survival with potential values of alive or deceased. The dataset for the full features and important features selected by minimal redundancy maximal relevance (mRMR) feature selection were fed into eight ML techniques, including eXtreme gradient boosting (XGBoost), multilayer perceptron (MLP), pattern recognition network, k-nearest neighborhood (KNN), probabilistic neural network, support vector machine (SVM) (kernel = linear), SVM (kernel = RBF), and J-48. The scikit-learn library in Python was used to implement the models. Finally, the performance of the developed models was measured using some evaluation criteria with 95 confidence intervals (CI). Results Spleen palpable, age, and unexplained hemorrhage were identified as the top three effective features affecting CML 5-year survival. The performance of ML models using the selected-features was superior to that of the full-features dataset. Among the eight ML algorithms, SVM (kernel = RBF) had the best performance in tenfold cross-validation with an accuracy of 85.7, specificity of 85, sensitivity of 86, F-measure of 87, kappa statistic of 86.1, and area under the curve (AUC) of 85 for the selected-features. Using the full-features dataset yielded an accuracy of 69.7, specificity of 69.1, sensitivity of 71.3, F-measure of 72, kappa statistic of 75.2, and AUC of 70.1. Conclusions Accurate prediction of the survival likelihood of CML patients can inform caregivers to promote patient prognostication and choose the best possible treatment path. While external validation is required, our developed models will offer customized treatment and may guide the prescription of personalized medicine for CML patients
Response capability of hospitals to an incident caused by mass gatherings in southeast Iran
No full textBACKGROUND AND OBJECTIVES: Hospitals are expected to provide a safe environment for patients, visitors, and employees during emergencies and disasters, as well as provide health care to disaster survivors. The aim of this study was to evaluate the response capability of hospitals to an incident caused by mass gatherings (MG) in Kerman province. METHODS: This cross-sectional study was performed among hospitals of Kerman city in 2021. To collect data, the emergency response checklist-WHO (2011) was utilized with 90 questions prepared in nine domains. Data analysis was carried out using SPSS version 20 with descriptive tests. RESULTS: In this incident, 438 people were injured and 61 killed (31 women and 30 men). Of the 438 injured taken to hospitals, 193 were treated on an outpatient basis, 146 were hospitalized and 99 were treated at Advanced Medical Post (AMP) and mobile hospital in the scene. Results showed a moderate response level of hospitals to an incidence (151.50+/-18.28). Among the components of hospitals' response to incidence, the command and control component had the highest mean score (159.16 +/- 22.39) while the surge capacity component had the lowest mean score (129.78 +/- 25.21). CONCLUSION: Our hospitals faced new challenges in this incident; therefore, policymakers and executives managers of the health system in Iran should develop a comprehensive strategic plan to promote hospitals' preparedness for suitable and timely response to MG incidences and improve risk perception of mass gathering participants and hospitals personnel through training and implementing discussion and operation-based exercises
Development and psychometric properties of Iranian midwives job satisfaction instrument (MJSI): A sequential exploratory study
No full textBACKGROUND: Job satisfaction refers to a person's attitude toward his/her job and its various aspects. Job satisfaction improves the quality of service and employees' physical and mental health. The present study aimed to design a valid and reliable instrument to assess Iranian midwives job satisfaction instrument (MJSI). METHODS: This is a sequential exploratory study for tool design. This study in two phases; (qualitative and tool's psychometric evaluation) was conducted in Ilam, Iran, 2019 years. In the first phase, a qualitative content analysis was carried out by in-depth and semi-structured individual interviews with 10 experts. Then, the pool of items extracted from the qualitative phase was completed by reviewing the existing texts and tools. The second phase of the study involved reducing the overlapping items and validating the tool. In order to investigate the construct validity, a cross sectional study was conducted with the participation of 121 midwives with census sampling. Data analysis was performed by SPSS-19 software using exploratory factor analysis and reliability tests (Cronbach's alpha). RESULTS: In the qualitative phase and after reviewing the existing texts and tools by the research team, a 58-item questionnaire was developed and then entered into the psychometric phase. Then, the tool was finalized with five factors, including: 1) communication features, 2) professional features, 3) responsibility aspects, 4) physical-mental aspects and 5) social aspects, respectively. After the psychometric process, by removing the items in different stages, a specific questionnaire was developed to measure the midwives' job satisfaction with 25 items which explained a total of 49.95 of the total variance. Reliability of the tool was approved by Cronbach's alpha = 0.71 and test-retest with 2-weeks intervals, indicating an appropriate stability for the scale (ICC = 0.898). CONCLUSION: The 25-item self-reporting midwives job satisfaction tool had acceptable validity and reliability. We recommend the use of this tool for evaluating the job satisfaction of midwives, as well as management and research purposes
Ketorolac and Predicted Severe Acute Pancreatitis: A Randomized, Controlled Clinical Trial
No full textObjective: We evaluated the effect of ketorolac on reducing the severity of acute pancreatitis.Design: Randomized clinical trial.Setting: University hospital.Participants: Fifty six adult patients, with predicted severe acute pancreatitis, were randomly divided into two groups.Methods: The patients in the study group received intravenous ketorolac, 10 mg, three times daily from the time of enrollment for a maximum of five days as needed along with standard medical treatment. Primary outcome measure was the change in the serum level of high sensitive c reactive protein (hs-CRP). Patients were also followed up in terms of hospitalization duration, need for ICU, development of organ failure, persistent organ failure, pancreatic necrosis, nutritional assessment, and mortality. The study was continued to gather clinical follow up information up to four months.Results: Serum level of hs-CRP was significantly lower in the ketorolac group compared with the control group on days 3, 4, and 5. There was no significant difference in organ failure, pseudocyst formation, acute necrotic collection, mortality and ICU transfer between two groups. Days of hospitalization were significantly lower in the study group. The feeding start time was significantly shorter in the study group with no need for tube feeding in the ketorolac group. Frequency of NPO (not per oral) was significantly lower in the ketorolac group.Conclusion: The use of ketorolac may improve feeding outcomes and shorten length of hospitalization in predicted severe acute pancreatitis
Time Management Behaviors and Emotional Intelligence in Head Nurses in Emergency and Intensive Care Units
No full textBackground: Time management is of particular importance in nursing. One of the most effective variables associated with time management is emotional intelligence (EI). This study assessed the relationship between time management and EI and the level of EI and time management skills in head nurses in emergency and intensive care units. Methods: A cross-sectional study was conducted on all head nurses in the emergency and intensive care units of nine educational hospitals at Isfahan University of Medical Sciences in Iran in 2015 using Bradberry-Greaves’ EI and Macan’s Time Management Questionnaires. Results: Participants’ total time management score was (104.15 ± 6.98); total EI score was (128 ± 15.80). There was no significant relationship between overall EI and time management skills. There was a significant relationship between age and the emotional self-awareness dimension of EI (p =.027) and the mechanics dimension of time management (p =.037), and between work experience and overall time management skills (p =.049) and the mechanics dimension of time management (p =.038). Conclusions: Specific EI and time management skills may help head nurses to cope with the challenges they face, which may improve the quality of nursing care. Nursing leaders should consider the importance of time management and EI in increasing motivation and satisfaction of nursing staff and improving quality of care. © Copyright 2022 Creative Health Care Management
Developing an artificial neural network for detecting COVID-19 disease
No full textBACKGROUND: From December 2019, atypical pneumonia termed COVID-19 has been increasing exponentially across the world. It poses a great threat and challenge to world health and the economy. Medical specialists face uncertainty in making decisions based on their judgment for COVID-19. Thus, this study aimed to establish an intelligent model based on artificial neural networks (ANNs) for diagnosing COVID-19. MATERIALS AND METHODS: Using a single-center registry, we studied the records of 250 confirmed COVID-19 and 150 negative cases from February 9, 2020, to October 20, 2020. The correlation coefficient technique was used to determine the most significant variables of the ANN model. The variables at P < 0.05 were used for model construction. We applied the back-propagation technique for training a neural network on the dataset. After comparing different neural network configurations, the best configuration of ANN was acquired, then its strength has been evaluated. RESULTS: After the feature selection process, a total of 18 variables were determined as the most relevant predictors for developing the ANN models. The results indicated that two nested loops' architecture of 9-10-15-2 (10 and 15 neurons used in layer 1 and layer 2, respectively) with the area under the curve of 0.982, the sensitivity of 96.4, specificity of 90.6, and accuracy of 94 was introduced as the best configuration model for COVID-19 diagnosis. CONCLUSION: The proposed ANN-based clinical decision support system could be considered as a suitable computational technique for the frontline practitioner in early detection, effective intervention, and possibly a reduction of mortality in patients with COVID-19. © 2022 Journal of Education and Health Promotion
A machine learning-based system for detecting leishmaniasis in microscopic images
No full textBackground Leishmaniasis, a disease caused by a protozoan, causes numerous deaths in humans each year. After malaria, leishmaniasis is known to be the deadliest parasitic disease globally. Direct visual detection of leishmania parasite through microscopy is the frequent method for diagnosis of this disease. However, this method is time-consuming and subject to errors. This study was aimed to develop an artificial intelligence-based algorithm for automatic diagnosis of leishmaniasis. Methods We used the Viola-Jones algorithm to develop a leishmania parasite detection system. The algorithm includes three procedures: feature extraction, integral image creation, and classification. Haar-like features are used as features. An integral image was used to represent an abstract of the image that significantly speeds up the algorithm. The adaBoost technique was used to select the discriminate features and to train the classifier. Results A 65 recall and 50 precision was concluded in the detection of macrophages infected with the leishmania parasite. Also, these numbers were 52 and 71, respectively, related to amastigotes outside of macrophages. Conclusion The developed system is accurate, fast, easy to use, and cost-effective. Therefore, artificial intelligence might be used as an alternative for the current leishmanial diagnosis methods
A new COVID-19 intubation prediction strategy using an intelligent feature selection and K-NN method
No full textBackground: Predicting severe respiratory failure due to COVID-19 can help triage patients to higher levels of care, resource allocation and decrease morbidity and mortality. The need for this research derives from the increasing demand for innovative technologies to overcome complex data analysis and decision-making tasks in critical care units. Hence the aim of our paper is to present a new algorithm for selecting the best features from the dataset and developing Machine Learning(ML) based models to predict the intubation risk of hospitalized COVID-19 patients. Methods: In this retrospective single-center study, the data of 1225 COVID-19 patients from February 9, 2020, to July 20, 2021, were analyzed by several ML algorithms which included, Decision Tree(DT), Support Vector Machine (SVM), Multilayer perceptron (MLP), and K-Nearest Neighbors(K-NN). First, the most important predictors were identified using the Horse herd Optimization Algorithm (HOA). Then, by comparing the ML algorithms' performance using some evaluation criteria, the best performing one was identified. Results: Predictive models were trained using 12 validated features. Also, it found that proposed DT-based predictive model enables a reasonable level of accuracy (=93) in predicting the risk of intubation among hospitalized COVID-19 patients. Conclusions: The experimental results demonstrate the effectiveness of the proposed meta-heuristic feature selection technique in combining with DT model in predicting intubation risk for hospitalized patients with COVID-19. The proposed model have the potential to inform frontline clinicians with quantitative and non-invasive tool to assess illness severity and to identify high risk patients
Comparison of Antibody Responses Following Vaccination with AstraZeneca and Sinopharm
No full textBackground: Vaccines are the most effective way to prevent Coronavirus 2 severe acute respiratory syndrome (SARS-CoV-2). Objectives: To compare the antibody response of healthy individuals vaccinated with either the AstraZeneca (ChAdOx1 nCoV-19) or the Sinopharm (BBIBP-CorV) vaccine, in those who had no prior infection with SARS-CoV-2. Methods: Thirty seven participants were included, of which 17 were administered the AstraZeneca (ChAdOx1 nCoV-19) vaccine, while 20 were given the Sinopharm (BBIBP-CorV) vaccine. SARS-CoV-2 neutralizing antibody and anti-receptor-binding domain (RBD) IgG levels were checked 4 weeks after giving the first and the second dose of either vaccine using the enzyme-linked immunosorbent assay (ELISA) technique. Results: The AstraZeneca (ChAdOx1 nCoV-19) vaccine exhibited a higher levels of anti-(RBD) IgG compared with the Sinopharm (BBIBP-CorV) in both the first (14.51 μg/ml vs. 1.160 μg/ml) and the second (46.68 μg/ml vs. 11.43 μg/ml) doses. About neutralizing Abs, the titer of the antibody was higher in the AstraZeneca (ChAdOx1 nCoV-19) recipients than in the Sinopharm (BBIBP-CorV) subjects after the first (7.77 μg/ml vs. 1.79 μg/ml, P<0.0001) and the second dose (10.36 μg/ml vs. 4.88 μg/ml, P<0.0001). Conclusions: Recipients vaccinated with two doses of the AstraZeneca (ChAdOx1 nCoV-19) had superior quantitative antibody levels than Sinopharm (BBIBP-CorV)-vaccinated subjects. These data suggest that a booster dose may be needed for the Sinopharm (BBIBP-CorV) recipients, to control the COVID-19 pandemic. © 2022, Shiraz University of Medical Sciences. All rights reserved
Common data elements and features of brucellosis health information management system
No full textIntroduction: A key step in constructing any health information management system (HIMS) is to decide on a set of minimal yet comprehensive data items. The consensus dataset would be homogenous between healthcare settings and can pave the way for scientific collaborations. Iran is the fourth endemic country for brucellosis in the world. Despite its huge burden on society, the economy, and the environment, there is no agreed-upon minimum data set (MDS) for reporting this disease, and the data collected are rarely homogenous or directly comparable. Objective: To establish the brucellosis MDS that may enable homogeneity in data collection, data reporting, and data exchange among various HIMSs. Methods: A two-step process, including an extensive literature search and a two-round Delphi survey, was performed to foster consensus about the required data items. The collected data were analyzed using SPSS V22 (SPSS Inc., Chicago, IL). Results: The final MDS platform of our study contained 134 items divided into five main categories of administrative information, epidemiology, diagnosis investigation, complications, and signs and symptoms. Conclusion: This study provided a practical MDS for brucellosis that can help collect unified and comprehensive data for electronic health record systems (EHRs), disease surveillance, and registries, and easily integrate them with other HIMSs. The developed MDS can promote the collaboration of policy-makers, healthcare providers, and researchers to prevent, control, and manage brucellosis. © 202