Identification of significant risks in pediatric acute lymphoblastic leukemia (ALL) through machine learning (ML) approach

Keyphrases

• Significant Risk Factors 100%
• Acute Lymphoblastic Leukemia 100%
• Machine Learning Approach 100%
• Pediatric Acute Lymphoblastic Leukemia 100%
• Classification and Regression Tree 100%
• Exclusion Criteria 66%
• Hemoglobin 66%
• Random Forest 66%
• Childhood Acute Lymphoblastic Leukemia 66%
• Platelets 66%
• Gradient Boosting Machine 66%
• White Blood Cells 66%
• Consanguinity 66%
• B-cell Acute Lymphoblastic Leukemia (B-ALL) 66%
• T-acute Lymphoblastic Leukemia 66%
• Male Patients 33%
• Environmental Conditions 33%
• Environmental Factors 33%
• Socioeconomic Status 33%
• Treatment Outcome 33%
• Pediatric Patients 33%
• Rural Areas 33%
• Future Information 33%
• Overall Accuracy 33%
• Model Fitting 33%
• Drinking Water 33%
• Clinical Variables 33%
• Misclassification 33%
• Machine Learning Techniques 33%
• Machine Learning Algorithms 33%
• Supervised Machine Learning 33%
• 10-fold Cross Validation 33%
• Blood Biochemistry 33%
• Platelet Count 33%
• Classification Tree Algorithms 33%
• Sample Space 33%
• Leukemia Patients 33%
• Phenotypic Data 33%
• C5.0 Decision Tree Algorithm 33%
• Regression Tree Algorithm 33%
• Feature Attribute 33%
• Middle-class Families 33%
• Fit Accuracy 33%

Immunology and Microbiology

• Leukocyte 100%
• Hemoglobin 100%
• Random Forest 100%
• Consanguinity 100%
• Platelet 100%
• Supervised Machine Learning 50%
• Platelet Count 50%
• Decision Tree 50%

Biochemistry, Genetics and Molecular Biology

• Pediatrics 100%
• Leukocyte 50%
• Random Forest 50%
• Platelet 50%
• Consanguinity 50%
• Hemoglobin 50%
• Decision Tree 25%
• Blood Biochemistry 25%
• Platelet Count 25%
• Supervised Machine Learning 25%