Machine Learning Approach for Rapid, Accurate Point-of-Care Prediction of M-Spike Values in Multiple Myeloma

Keyphrases

• Multiple Myeloma 100%
• Point-of-care 100%
• Machine Learning Approach 100%
• M-spike 100%
• Machine Learning 33%
• Serum Protein Electrophoresis 33%
• Machine Learning System 33%
• Clinical Data 16%
• Am(III) 16%
• Spearman Coefficient 16%
• Clinical Decision-making 16%
• Treatment Delay 16%
• Retrospective Chart Review 16%
• Response Monitoring 16%
• Treatment Decisions 16%
• Disease Burden 16%
• Laboratory Data 16%
• Electronic Medical Records 16%
• Feature Select 16%
• Response Status 16%
• Pearson Correlation Coefficient 16%
• Cancer Care 16%
• Patient Information 16%
• Financial Barriers 16%
• Turnaround Time 16%
• Two-variable 16%
• Machine Learning Algorithms 16%
• Spike Protein 16%
• Underserved Populations 16%
• Electronic Information 16%
• Prognostic Potential 16%
• Urine Protein Electrophoresis 16%
• Random Forest Regression 16%
• Random Forest Analysis 16%
• Geographic Barriers 16%
• Social Barriers 16%
• Medical Progress 16%
• Weight Value 16%
• Tool Support 16%
• Serum Total Protein 16%

Medicine and Dentistry

• Multiple Myeloma 100%
• Malignant Neoplasm 33%
• Clinical Decision Making 33%
• Therapy Delay 33%
• Blood Protein 33%
• Disease Burden 33%
• Specialist Care 33%
• Serum Total Protein 33%
• Protein Electrophoresis 33%
• Electrophoresis 33%
• Electronic Patient Record 33%
• Underserved Population 33%

Neuroscience

• Electrophoresis 100%
• Clinical Decision Making 50%
• Blood Protein 50%
• Machine Learning Algorithm 50%