Comparison of Models for Predicting Outcomes in Patients with Coronary Artery Disease Focusing on Microsimulation

Background: physicians have difficulty to subjectively estimatethe cardiovascular risk of their patients. using an estimate of globalcardiovascular risk could be more relevant to guide decisions thanusing binary representation (presence or absence) of risk factorsdata. the main aim of the paper is to compare different modelsof predicting the progress of a coronary artery diseases (cad) tohelp the decision making of physician.methods: there are different standard models for predictingrisk factors such as models based on logistic regression model,cox regression model, dynamic logistic regression model, andsimulation models such as markov model and microsimulationmodel. each model has its own application which can or cannotuse by physicians to make a decision on treatment of each patient.results: there are five main common models for predicting ofoutcomes, including models based on logistic regression model (forshort-term outcomes), cox regression model (for intermediatetermoutcomes), dynamic logistic regression model, and simulationmodels such as markov and microsimulation models (for longtermoutcomes). the advantages and disadvantages of thesemodels have been discussed and summarized.conclusion: given the complex medical decisions that physiciansface in everyday practice, the multiple interrelated factors that playa role in choosing the optimal treatment, and the continuouslyaccumulating new evidence on determinants of outcome andtreatment options for cad, physicians may potentially benefitfrom a clinical decision support system that accounts for allthese considerations. the microsimulation model could providecardiologists, researchers, and medical students a user-friendlysoftware, which can be used as an intelligent interventional simulator.