Enabling personalized perioperative risk prediction by using a machine-learning model based on preoperative data

Keyphrases

• Machine Learning Models 100%
• Preoperative Information 100%
• Perioperative Risk Stratification 100%
• Precision-recall Curve 66%
• Individual Risk 66%
• In-hospital Mortality 66%
• Interpretable Machine Learning 66%
• Information Gain 33%
• Relevant Parameters 33%
• Highly Accurate 33%
• Risk Factors 33%
• Identify Risk 33%
• Index Patient 33%
• Receiver Operating Characteristic 33%
• Area under the Receiver Operating Characteristic (AUROC) 33%
• Personalized Information 33%
• C-reactive Protein 33%
• Predictive Ability 33%
• Predictive Quality 33%
• Optimization Measures 33%
• Patient-level 33%
• Perioperative Care 33%
• June 2014 33%
• Individual Risk Factors 33%
• Ethical Approval 33%
• Extreme Gradient Boosting 33%
• Postoperative Mortality 33%
• Packed Cells 33%
• Preoperative Optimization 33%
• Waterfall Model 33%
• Personal Risk Factors 33%
• Patient Risk 33%
• Preoperative Risk Assessment 33%
• Model Evaluation 33%
• Shared Decision-making 33%
• Noncardiac Surgery 33%

Medicine and Dentistry

• Hospital Mortality 100%
• C Reactive Protein 50%
• Shared Decision Making 50%
• Surgical Mortality 50%
• Noncardiac Surgery 50%
• Perioperative Period 50%
• Erythrocyte Concentrate 50%