Search

The reported fatality rate of COVID-19 was significantly differ between different countries, provinces in a country, and hospitals in a province. It is important to find and analysed the source of variation in fatality rates to control future epidemics of infection disease. This study propose an approach to investigates the hospital quality of care and its impact on the in-hospital fatality rates of COVID-19 among over 30 years old patients in Iran. The study included 78,217 COVID-19 hospitalized patients over 30 years old from 34 hospitals in Razavi Khorasan province between January 20, 2020, and June 20, 2021. Attribute control charts were employed to evaluate the quality of care in hospitals during four peaks of COVID-19. To account for the impact of hospital quality on in-hospital fatality rates by adjusting on patient characteristics, two predictive models; Poisson and Binomial regression were utilized. The adjusted odds ratio of COVID-19 fatality in no quality confirmed (NQC) hospitals to the quality confirmed (QC) hospitals is 3.48 C.I.95% (2.38, 5.10) at the first peak among patients without other risk factors. The significant negative interactions with QC and peaks indicates that the provision of quality care serves to mitigate the risk of fatality in NQC hospitals during these peaks. The significant negative interaction between diabetes and QC demonstrated that the relative risk in NQC hospitals for no diabetes patient is higher than diabetic patients. There is no significant interaction between age, SaO2, and ARDS with QC; it means that the odds of fatality in NQC hospitals is not depends to these factors. The use of attribute control charts facilitated timely identification of trends and outliers, enabling proactive interventions to enhance patient care. This research underscores the critical role of hospital quality in managing patient outcomes during the COVID-19 pandemic and emphasizes the necessity for continuous monitoring and quality improvement initiatives in healthcare settings. The findings advocate for collaborative efforts among healthcare providers to implement best practices, particularly during surges in cases, to optimize resource allocation and improve overall quality of care., Competing Interests: Declarations. Competing interests: The authors declare no competing interests. Ethical approval and consent to participate: This study was done on the record information from HIS (Health Information System) registry data of patients who take regular treatment at hospitals of Razavi Khorasan province. Informed consent was obtained from all subjects and/or their legal guardian(s). Also, ethics of this Study approved at Research Ethics Committee of Mashhad University of Medical Sciences with the reference number: IR.MUMS.REC.1401.066., (© 2025. The Author(s).)

Background: The aim of this study was to evaluate the safety of Sinofarm vaccine (BBIBP-CorV) in patients with multiple sclerosis (pwMS)., Methods: This study was conducted on pwMS patients in Isfahan, Iran. All participants received two doses of BBIBP-CorV (Sinopharm vaccine). Demographic information and data on vaccine side effects were collected after each dose using questionnaires. All patients that recorded worsening of MS symptoms were evaluated and those with true relapse were treated with IV methyl prednisolone., Results: Of the 1538 patients, 1151 (74.8%) were female and the mean age was 40.45 ± 9.74. The average disease duration was 10.38±6.81 years and 76.1% of participants had RRMS. 92.8% of the participants were using DMTs and mean EDSS was 2.06 ± 3.16. 54.2% (833 patient) reported at least one adverse event after the first dose of vaccine and 46.8% (720 patient) after the second dose; in both cases going away in a few days. Most prevalent adverse events after both doses were injection site pain, headache, myalgia, fever and fatigue. Adverse events were more prevalent in younger and less prevalent in mildly disabled patients. There were seven cases of Covid-19 infection between the first and second vaccination dose, and eight cases during one-month follow -up after the second dose, none of whom needed mechanical ventilation. Ten patients after first dose and thirteen patients after the second dose experienced acute relapse. A patient had two relapses, one after each vaccine dose that were clinically and radiologically confirmed. The first relapse occurred seven days after the first vaccination with hemiparesis and other relapse, 14 days after the second dose with diplopia, hemiparesis and ataxia., Conclusion: Adverse events in pwMS following vaccination with Sinopharm vaccine was similar to the general population, which were more common in younger patients and less common in those with mild disability. As no increase in relapse rate after vaccination was detected, Sinopharm vaccine was safe in MS patients., (Copyright © 2022. Published by Elsevier B.V.)

Background & Aim: Timely identification of the patients requiring intensive care unit admission (ICU) could be life‐saving. We aimed to compare different machine learning algorithms to predict the requirements for ICU admission in COVID‐19 patients. Methods: We screened all patients with COVID‐19 at six academic hospitals in Tehran comprising our study population. A total of 44,112 COVID‐19 patients (≥18 years old) were included, among which 7722 patients were hospitalized. We used a Random Forest algorithm to select significant variables. Then, prediction models were developed using the Support Vector Machine, Naıve Bayes, logistic regression, lightGBM, decision tree, and K‐Nearest Neighbor algorithms. Sensitivity, specificity, accuracy, F1 score, and receiver operating characteristic‐Area Under the Curve (AUC) were used to compare the prediction performance of different models. Results: Based on random Forest, the following predictors were selected: age, cardiac disease, cough, hypertension, diabetes, influenza & pneumonia, malignancy, and nervous system disease. Age was found to have the strongest association with ICU admission among COVID‐19 patients. All six models achieved an AUC greater than 0.60. Naıve Bayes achieved the best predictive performance (AUC = 0.71). Conclusion: Naïve Bayes and lightGBM demonstrated promising results in predicting ICU admission needs in COVID‐19 patients. Machine learning models could help quickly identify high‐risk patients upon entry and reduce mortality and morbidity among COVID‐19 patients. [ABSTRACT FROM AUTHOR]

Background and Aims: To explore the use of different machine learning models in prediction of COVID‐19 mortality in hospitalized patients. Materials and Methods: A total of 44,112 patients from six academic hospitals who were admitted for COVID‐19 between March 2020 and August 2021 were included in this study. Variables were obtained from their electronic medical records. Random forest‐recursive feature elimination was used to select key features. Decision tree, random forest, LightGBM, and XGBoost model were developed. Sensitivity, specificity, accuracy, F‐1 score, and receiver operating characteristic (ROC)‐AUC were used to compare the prediction performance of different models. Results: Random forest‐recursive feature elimination selected following features to include in the prediction model: Age, sex, hypertension, malignancy, pneumonia, cardiac problem, cough, dyspnea, and respiratory system disease. XGBoost and LightGBM showed the best performance with an ROC‐AUC of 0.83 [0.822−0.842] and 0.83 [0.816−0.837] and sensitivity of 0.77. Conclusion: XGBoost, LightGBM, and random forest have a relatively high predictive performance in prediction of mortality in COVID‐19 patients and can be applied in hospital settings, however, future research are needed to externally confirm the validation of these models. [ABSTRACT FROM AUTHOR]