Using machine learning to identify key subject categories predicting the pre-clerkship and clerkship performance: 8-year cohort study

Keyphrases

• Machine Learning 100%
• Pre-clerkship 100%
• Clerkship Performance 100%
• Medical Students 27%
• Clerkship 27%
• Basic Medical Sciences 27%
• Prediction Model 18%
• Machine Learning Techniques 18%
• Predictive Ability 18%
• Area under the ROC Curve 18%
• Medical Program 18%
• Premed 18%
• Histology 9%
• Data Preprocessing 9%
• Social Sciences 9%
• Student Needs 9%
• Student Understanding 9%
• Cross-validation Method 9%
• Random Forest 9%
• 10-fold Cross Validation 9%
• Microbiology 9%
• Serial Process 9%
• Machine Learning Models 9%
• Immunology 9%
• Solid Foundation 9%
• Collection Data 9%
• Physician-scientist 9%
• Medical Sociology 9%
• Medical Humanities 9%
• Academic Data 9%
• Basic Pharmacology 9%

Social Sciences

• Medical Student 100%
• Medical Science 100%
• Learning Method 66%
• Cross-Validation 33%
• Sociology 33%
• Scientists 33%
• Basic Science 33%
• Social Science 33%

Engineering

• Learning System 100%
• Machine Learning Technique 50%
• Predictive Ability 50%
• Data Preprocessing 25%
• Transition Point 25%
• Random Forest 25%
• Predicted Model 25%