Disclosed embodiments provide a computer-implemented technique for selection and/or modification of surgical simulation scenarios based on patient similarity cohort identification. Prior to undergoing surgery, medical information of a patient, including genomic, physiological, and/or environmental data, is used to identify a patient cohort. The patient cohort represents a statistically significant sample size of similar patients, and complications that may have arose during similar surgical procedures to the procedure planned for the patient. Relevant scenarios are identified based on the patient cohort. These scenarios are then input to a surgical simulation system. The surgical simulation system may be implemented by virtual reality, augmented reality, and/or physical workpieces used for surgical practice and training. This can increase the probability of a successful outcome for the patient, and furthermore save costs by reducing the risk of malpractice lawsuits, thereby potentially lowering overall healthcare costs.