N-gram support vector machines for scalable procedure and diagnosis classification, with applications to clinical free text data from the intensive care unit

Keyphrases

• Jaundice 100%
• Intensive Care Unit 100%
• Support Vector Machine 100%
• Diagnostic Classification 100%
• N-gram 100%
• Free-text Data 100%
• Clinical Free Text 100%
• Intracranial Hemorrhage 60%
• Mechanical Ventilation 40%
• Performance Improvement 40%
• Phototherapy 40%
• Intensive Care Unit Patients 40%
• Support Vector Machine Classifier 40%
• Unigram 40%
• Adult Intensive Care Unit 40%
• Neonatal ICU 40%
• NegEx 40%
• Medical Center 20%
• Performance Characteristics 20%
• Israel 20%
• Risk Adjustment 20%
• Diagnostic Accuracy 20%
• Neonatal Intensive Care Unit 20%
• Cost Reduction 20%
• Classification Performance 20%
• Automated Method 20%
• Excellent Performance 20%
• Free Text 20%
• Classification Task 20%
• Medical Charts 20%
• Patient-level 20%
• Clinical Notes 20%
• Diverse Patient Population 20%
• Support Vector 20%
• Data Collection Time 20%
• Intensive Care Unit Outcomes 20%
• Bigram 20%
• MIMIC-III Database 20%
• Deaconesses 20%
• Risk-adjustment Model 20%

Medicine and Dentistry

• Intensive Care Unit 100%
• Jaundice 83%
• Cerebral Hemorrhage 50%
• Phototherapy 33%
• Artificial Respiration 33%
• Health Care Cost 16%
• Patient Population 16%
• Neonatal Intensive Care Unit 16%
• Diagnostic Accuracy 16%

Computer Science

• Support Vector Machine 100%
• Support Vector 25%
• Level Predictor 25%
• Classification Task 25%
• Performance Characteristic 25%