Development of an image-based Random Forest classifier for prediction of surgery duration of laparoscopic sigmoid resections

Keyphrases

• Image-based 100%
• Area under the Receiver Operating Characteristic (AUROC) 100%
• Timing of Surgery 100%
• Laparoscopic Sigmoid Resection 100%
• Random Forest Classifier 100%
• Computational Imaging 60%
• Biometrics 40%
• Patient Data 40%
• Intraoperative CT 40%
• Multiple Logistic Regression 40%
• Operative Time 20%
• Visceral Surgery 20%
• Patient Care 20%
• Anatomical Parameters 20%
• Prediction Accuracy 20%
• Performance Metrics 20%
• Random Forest Model 20%
• Left-handed 20%
• Imaging Parameters 20%
• Socioeconomic Burden 20%
• Logistic Regression Model 20%
• Healthcare Resources 20%
• Multicenter Cohort Study 20%
• Training Population 20%
• Procedure Duration 20%
• Sigmoid Diverticulitis 20%
• Random Splitting 20%
• Surgical Scheduling 20%
• Diverticular Disease 20%
• Procedure Specific 20%
• Predictive Model 20%
• Ileocecal Resection 20%
• Receiver Operating Characteristic-area under the Curve 20%

Medicine and Dentistry

• Sigmoidectomy 100%
• Logistic Regression Analysis 50%
• Patient-Data 50%
• Patient Care 25%
• Cohort Analysis 25%
• Sigmoid 25%
• Diverticulitis 25%
• Diverticulum 25%
• Colectomy 25%
• Diseases 25%
• Area under the Curve 25%