Publications by authors named "Mohamed Ahmed Sobhy"
Article Synopsis
- The study aimed to predict in-hospital mortality in patients with Acute Coronary Syndrome (ACS) using machine learning (ML) algorithms, specifically focusing on the QTc interval, and compared these predictions to established risk scores.
- Researchers analyzed data from 500 ACS patients over two years, developing three ML models: Random Forest, Naive Bayes, and PART, measuring their effectiveness against the GRACE and TIMI risk scores.
- The models showed promising performance, with the ML algorithms achieving an area under the curve (AUC) of 0.83 to 0.93, while the GRACE score had an AUC of 0.90, highlighting the potential of using ML for mortality prediction in hospital settings.
Background: Right ventricle infarction (RVI) is predominantly a complication of inferior wall myocardial infarction; it occurs in approximately one third of these patients. Right ventricular dysfunction in patients with inferior STEMI and RV infarction was under assessed. Nevertheless, studies which targeted RV assessment by echocardiography, did not routinely evaluate RV diastolic dysfunction.
View Article and Find Full Text PDFBackground: SYNTAX Scores I (SSI) assesses the complexity of CAD; SYNTAX Score II (SSII) uses both SSI and other clinical variables, in estimation of 4 years mortality following both coronary artery bypass grafting surgery (CABG) and percutaneous coronary intervention (PCI) and gives recommendations for the best revascularization strategy in a specific patient. Our aim is to investigate the impact of both SYNTAX Scores on short-term outcome following CABG.
Results: Prospectively, we studied 150 patients with multi-vessels coronary artery disease, referred to perform, elective primary isolated CABG.