A machine-learning model for prediction of Acinetobacter baumannii hospital acquired infection

Keyphrases

• Machine Learning Models 100%
• Intensive Care Unit 100%
• Hospital-acquired Infection 100%
• Acinetobacter Baumannii (A. baumannii) 100%
• Multiple Indicators Multiple Causes (MIMIC) 75%
• Rabin 50%
• Medical Center 50%
• Antibiotics 50%
• Area under the Receiver Operating Characteristic (AUROC) 50%
• Tertiary Care Centers 50%
• Israeli 25%
• Predictive Power 25%
• Physiological Parameters 25%
• Improved Outcomes 25%
• Significant Predictors 25%
• Prediction Tool 25%
• Internal Validation 25%
• External Validation 25%
• Respiratory Failure 25%
• Acidosis 25%
• Prediction Model 25%
• Positive Predictive Value 25%
• Proper Treatment 25%
• Adult Patients 25%
• Negative Predictive Value 25%
• Infection Risk 25%
• Lactate Level 25%
• Discriminatory Power 25%
• Acinetobacter 25%
• Carbon Dioxide CO2 25%
• Lactate 25%
• Model-driven Development 25%
• Boston 25%
• Early Recognition 25%
• CO2 Levels 25%
• Development Validation 25%
• Metabolic Disturbances 25%
• Respiratory Rate 25%
• Cardiorespiratory Function 25%
• Machine Learning Prediction 25%
• Sensitivity/specificity 25%

Nursing and Health Professions

• Intensive Care Unit 100%
• Infection 100%
• Hospital Infection 100%
• Intensive Care 75%
• Predictive Value 50%
• Lactic Acid 50%
• Carbon Dioxide 50%
• Morbidity 25%
• Respiratory Failure 25%
• Cardiorespiratory 25%
• Metabolic Disorder 25%
• Acidosis 25%

Pharmacology, Toxicology and Pharmaceutical Science

• Infection 100%
• Hospital Infection 100%
• Acinetobacter Baumannii 100%
• Lactic Acid 50%
• Antibiotics 50%
• Carbon Dioxide 50%
• Morbidity 25%
• Acinetobacter 25%
• Respiratory Failure 25%
• Metabolic Disorder 25%
• Acidosis 25%