Arka Publishing CompanyCanon Journal of Medicine2676-54465202520250405Application of Machine Learning Models for Predicting COVID-19 Mortality: A Retrospective Cohort Study Using Random Forest Algorithm010110.30477/cjm.2025.481343.1092ENGhazalSherkatInnovative Medical Research Center, Faculty of Medicine, Mashhad Medical Sciences, Islamic Azad University, Mashhad, IranMohamad AminPourhoseingholiBasic and Molecular Epidemiology of Gastrointestinal Disorders Research Center, Research Institute for Gastroenterology and Liver Diseases, Shahid Beheshti University of Medical Sciences, Tehran, Iran0000-0002-0121-8031Seyyedeh ZahraMostafavianDepartment of Community Medicine, Faculty of Medicine, Mashhad Medical Sciences, Islamic Azad University, Mashhad, Iran.0000-0002-0121-8031Journal Article20241002Background: The COVID-19 pandemic has posed immense challenges to healthcare systems worldwide, making it critical to identify predictors of patient mortality. Machine learning algorithms have shown great promise in predicting outcomes for COVID-19 patients based on clinical and laboratory data. This study aimed to evaluate the performance of three machine learning models—Random Forest, Support Vector Machine (SVM), and Logistic Regression—in predicting mortality among COVID-19 patients using clinical and laboratory data.<br />Methods: A retrospective cohort study was conducted on 2,500 COVID-19 patients admitted to three major hospitals in Tehran, Iran, between 2020 and 2021. Demographic, clinical, and laboratory data were collected. Machine learning models were trained to predict mortality, and their performance was evaluated using the area under the curve (AUC), sensitivity, specificity, and positive predictive value (PPV). Model validation was performed using 10-fold cross-validation and an 80-20 train-test split to ensure robustness and generalizability.<br />Results: The Random Forest model outperformed both SVM and Logistic Regression with an AUC of 83.3%, sensitivity of 63.0%, and specificity of 90.5%. Important predictors of mortality included age, gender, comorbidities (such as diabetes, ischemic heart disease, and cancer), ICU admission, and laboratory markers (e.g., ALT, white blood cell count, and creatinine levels).<br />Conclusion: The Random Forest algorithm demonstrated superior predictive performance compared to SVM and Logistic Regression in predicting mortality among COVID-19 patients. These findings suggest that machine learning models, particularly Random Forest, can be instrumental in identifying high-risk patients and supporting clinical decision-making.https://www.canonjm.com/article_218208_9f52c6de1ad0e0e5032479715fd55955.pdfArka Publishing CompanyCanon Journal of Medicine2676-54465202520250603A Step Toward Faster, Fairer, and More Flexible Publishing at Canon Journal of Medicine020210.30477/cjm.2025.222394ENMohamad AminPourhoseingholiUniversity of Nottingham, NIHR Nottingham Biomedical Research Centre0000-0002-0121-8031Journal Article20250530The Canon Journal of Medicine (CJM) is transitioning to a continuous publication model starting June 2025. This strategic shift aims to address challenges posed by variable submission volumes and enhance the timely dissemination of medical research. Under the new model, articles will be published online immediately after peer review and final formatting, eliminating delays associated with quarterly issue compilation. Core values such as rigorous peer review, open access, ethical publishing, and no fees remain unchanged. This transition promotes faster visibility for authors, immediate access for readers, and sustained journal activity, aligning CJM with the evolving demands of scientific communication.https://www.canonjm.com/article_222394_4da2c50f76b849f46d636e1d56f01eea.pdfArka Publishing CompanyCanon Journal of Medicine2676-54465202520250715The Prevalence of Postcode Stress Among Nurses: A Systematic Review and Meta-Analysis Protocol030310.30477/cjm.2025.506951.1099ENAbbasHeydariProfessor, School of Nursing and Midwifery, Mashhad University of Medical Sciences, Mashhad, Iran.0000-0002-1082-7488Zahra SadatManzariProfessor, Nursing and Midwifery Care Research Center, Mashhad University of Medical Sciences, Mashhad, Iran.0000-0001-8270-7357SaeedKhayat KakhkiPhD Student of Nursing, Student Research Committee, School of Nursing and Midwifery, Mashhad University of Medical Sciences, Mashhad, Iran.0000-0002-2739-7103Journal Article20250216Background: Postcode stress is a significant concern among nurses in high-stakes environments like emergencies and intensive care units. This stress arises from the emotional and psychological burden of performing cardiopulmonary resuscitation (CPR), especially when outcomes are unfavorable. Despite its recognized impact on nurses' mental health and patient care quality, empirical research does not quantify its prevalence and identify contributing factors. This study aims to conduct a systematic review and meta-analysis to determine the prevalence of postcode stress among nurses, providing a comprehensive understanding of this phenomenon to inform effective interventions and support mechanisms.<br /><br />Methods: A thorough search was conducted across various online databases. Studies were deemed eligible for inclusion if they examined postcode stress within nursing practice utilizing validated instruments, irrespective of the academic status, gender, country, setting, ethnicity, race, or limitations of the studies. Two reviewers independently undertook data extraction and quality assessment, following the PRISMA guidelines. <br /><br />Discussion: Post-resuscitation stress, or "postcode stress," significantly impacts critical care nurses involved in failed CPR attempts. This emotional burden can lead to moderate to severe stress levels and symptoms like post-traumatic stress disorder, affecting mental health and job satisfaction. Key factors include high-stakes settings, emotional investment in patient care, and perceived responsibility. Like structured debriefing sessions, institutional support alleviates these adverse effects, highlighting the need for supportive work environments. Positive coping strategies and regular stress assessments can enhance nurses' well-being and improve patient care outcomes.<br /><br />Systematic review registration: PROSPERO CRD42025646495. This protocol follows the PRISMA-P guidelines for reporting systematic reviews.https://www.canonjm.com/article_224993_8e3e1494bed449cc5e157acf5a7140dd.pdfArka Publishing CompanyCanon Journal of Medicine2676-54465202520251029The Prevalence of Moral Sensitivity Among Nurses: A Systematic Review and Meta-Analysis Protocol040410.30477/cjm.2025.514990.1101ENAbbasHeydariProfessor, School of Nursing and Midwifery, Mashhad University of Medical Sciences, Mashhad, Iran.0000-0002-1082-7488SaeedKhayat KakhkiPhD Student of Nursing, Student Research Committee, School of Nursing and Midwifery, Mashhad University of Medical Sciences, Mashhad, Iran.0000-0002-2739-7103Journal Article20250404<strong>Background:</strong><br>Moral sensitivity is crucial in nursing ethics, significantly impacting patient care and decision-making. By recognizing ethical dilemmas, nurses provide compassionate, patient-centered care that improves outcomes. This review explores the levels of moral sensitivity among nurses and factors influencing its role, aiming to enhance ethical decision-making and standards in nursing.
<br><strong>Methods:</strong><br>This systematic review will follow the Joanna Briggs Institute methodology and the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A comprehensive search will be conducted across multiple databases, including PubMed, Web of Science, Scopus, PsycINFO, Embase, and CINAHL, from January 1995 to April 2025. The search will not be restricted by study design or language. Studies on moral sensitivity scores in nursing practice, their levels, and the factors influencing them will be considered. The evidence synthesis will incorporate qualitative and quantitative analyses, with the results examined using descriptive statistics and thematic synthesis. The Theoretical Domains Framework will be utilised to categorise the factors influencing moral sensitivity.
<br><strong>Discussion:</strong><br>This study highlights the significance of moral sensitivity in nurses for ethical decision-making and patient care. Findings will reveal factors influencing moral sensitivity in nursing and showcase strengths and gaps in practices and education. Ultimately, the data will inform targeted interventions and educational strategies aimed at enhancing moral sensitivity and improving patient outcomes.
<br><strong>Systematic review registration:</strong><br>PROSPERO CRD420251010641. This protocol follows the PRISMA-P guidelines for reporting systematic reviews.https://www.canonjm.com/article_236610_2ebfb6cd6a284c2314202b21c87d6ccf.pdf