Application of machine learning algorithms to screen potential biomarkers under cadmium exposure based on human urine metabolic profiles

Keyphrases

• Human Urine 100%
• Metabolic Profiling 100%
• Cadmium Exposure 100%
• Potential Biomarkers 100%
• Machine Learning Applications 100%
• Negative Ionization Mode 100%
• Machine Learning Algorithms 100%
• Random Forest Classifier 100%
• Liquid Chromatography-high Resolution Mass Spectrometry (LC-HRMS) 66%
• Area under the Curve 66%
• Metabolic 33%
• Health Risk 33%
• Urine Samples 33%
• Adverse Health Effects 33%
• Performance Prediction 33%
• XGBoost 33%
• Extreme Gradient Boosting(XGBoost) 33%
• Machine Learning Models 33%
• Environmental Cadmium 33%
• Accuracy Performance 33%
• 5-fold Cross Validation 33%
• Machine Learning Approach 33%
• Biomarker Panel 33%
• Urine Analysis 33%
• XGBoost Classifier 33%

Chemical Engineering

• Learning System 100%
• Mass Spectrometry 40%

Material Science

• Cadmium 100%