309283_en-US

liliconcom

Machine Learning and Biomarker Sub-Group Analysis for Precision Medicine

 

See how to:

• Understand basics of machine learning
  • Compare differences between statistical modeling using data sample from a larger population and algorithmic modeling (machine learning) where data mechanism is unknown
• Understand 4 types of models
  • Models that use different algorithms (regression, tree-based models, neural networks)
  • Models that use different parameter settings (grid search, random search, genetic algorithms)
  • Models that use different features (feature selection, feature extraction, feature engineering)
  • Models that deploy training sets (bagging, boosting, 5-fold cross validation)
• Understand use of subgroup analysis and using subgroup identification (find correct patients for a given drug) and optimal treatment regimens (best drug for a given patient)
• Use JMP Genomics
  • To predict death from sepsis on data collected at hospital admittance
  • To Identify differential molecular expression signatures for normal vs. polyp tissues attributable to chemoprevention therapy treatment in FAP
  • To use subgroup analyses to find clinical measures or metabolite biomarkers that exhibit 

• Resources

  • An integrated clinico-metabolomic model improves prediction of death in sepsis case study
  • Related JMP success story  describing use of JMP Genomics for the vast majority of all analyses

 

 

 

31+ minAdvancedGenomicsMastering JMPVideo