Clustering of trauma patients based on longitudinal data and the application of machine learning to predict recovery

Keyphrases

• Psychosocial Outcomes 100%
• Longitudinal Data 100%
• Patient-centered 100%
• Trauma Patients 100%
• Clinical Validity 100%
• Machine Learning Applications 100%
• Recovery Profile 100%
• Risk Factors 50%
• Quality Assessment 50%
• Future Health 50%
• Descriptive Statistics 50%
• Trauma 50%
• Bayesian Methods 50%
• Clinical Expertise 50%
• Shared Decision Making 50%
• Cluster Solutions 50%
• Targeted Intervention 50%
• Random Forest 50%
• Majority Class 50%
• Physical Outcomes 50%
• Statistical Learning 50%
• Supervised Machine Learning 50%
• Supervised Learning 50%
• Yield Recovery 50%
• High Classification Accuracy 50%
• High-dimensional Supervised Classification 50%
• Supervised Clustering 50%
• Machine Learning Metrics 50%
• Longitudinal Recovery 50%
• Cluster Assignment 50%
• Unsupervised Techniques 50%
• Deep Gaussian Mixture Model 50%
• Cluster Quality 50%

Computer Science

• Longitudinal Data 100%
• Machine Learning 100%
• Learning System 100%
• Decision-Making 33%
• Gaussian Mixture Model 33%
• Majority Class 33%
• Classification Accuracy 33%
• Quality Assessment 33%
• Random Decision Forest 33%
• Supervised Learning 33%
• Shared Decision 33%
• Unsupervised Technique 33%
• Supervised Classification 33%

Pharmacology, Toxicology and Pharmaceutical Science

• Injury 100%
• Mixture Model 50%