Recurrence predictive models for patients with hepatocellular carcinoma after radiofrequency ablation using support vector machines with feature selection methods

Keyphrases

• Feature Selection Methods 100%
• Support Vector Machine 100%
• Predictive Models 100%
• Hepatocellular Carcinoma 100%
• Radiofrequency Ablation 100%
• High Risk 40%
• Ablation Therapy 40%
• Random Forest 40%
• 5-fold Cross Validation 40%
• Hepatocellular Carcinoma Patients 40%
• Genetic Algorithm 20%
• Hybrid Method 20%
• Sensitivity Specificity 20%
• Patient Identification 20%
• Simulated Annealing 20%
• Area under the ROC Curve 20%
• Support Vector Machine Model 20%
• Tumor Eradication 20%
• Simulated Annealing Algorithm 20%
• Random Forest Method 20%
• Hepatocellular Carcinoma Recurrence 20%
• Effective Treatment 20%
• Newly Diagnosed 20%
• Tumor Recurrence 20%
• Positive Predictive Value 20%
• Negative Predictive Value 20%
• Clinical Features 20%
• Recurrent Patients 20%
• Hybrid Feature Selection Method 20%
• First Treatment 20%
• Genetic Algorithm Simulated Annealing 20%

Biochemistry, Genetics and Molecular Biology

• Support Vector Machine 100%
• Radiofrequency 100%
• Feature Extraction 100%
• Random Forest 60%
• Genetic Algorithm 40%

Pharmacology, Toxicology and Pharmaceutical Science

• Liver Cell Carcinoma 100%
• Recurrent Disease 100%
• Cross-Validation 50%
• Neoplasm 25%
• Tumor Recurrence 25%
• Clinical Feature 25%