Publications by authors named "Cirruse Salehnasab"
Article Synopsis
- * The study analyzed 303 clinical records and utilized 26 features to compare the performance of various ML algorithms, including SVM, Random Forest, and KNN, for their effectiveness in identifying CAD.
- * Results showed that SVM and Random Forest were the most effective algorithms, suggesting that ML can provide valuable support to doctors and enhance clinical decision-making in diagnosing CAD.
Article Synopsis
- Acute graft-versus-host disease (aGvHD) significantly impacts 35% of patients undergoing allogeneic hematopoietic stem cell transplantation (AHSCT), leading to serious health complications.
- A study developed a Clinical Decision Support System (CDSS) using machine learning algorithms on data from 182 patients to effectively predict aGvHD at the time of transplant, evaluating the models based on accuracy, sensitivity, and specificity.
- The XGBClassifier and HistGradientBoostingClassifier emerged as the most effective models, achieving an average accuracy of 90.70% and demonstrating a strong prediction agreement with patient outcomes at 92%, indicating the potential of machine learning in enhancing clinical decision-making.
Background: The acute graft-versus-host disease (aGvHD) is the most important cause of mortality in patients receiving allogeneic hematopoietic stem cell transplantation. Given that it occurs at the stage of severe tissue damage, its diagnosis is late. With the advancement of machine learning (ML), promising real-time models to predict aGvHD have emerged.
View Article and Find Full Text PDFBackground: Preterm birth is a major cause of prenatal and postnatal mortality particularly in developing countries. This study investigated the maternal risk factors associated with the risk of preterm birth.
Methods: A population-based case-control study was conducted in several provinces of Iran on 2463 mothers referred to health care centers.