Data Synthesis

Data Synthesis in Clinical Trials

Our Active Intelligence Platform uses Generative AI models (GANs, VAEs) to augment underlying patterns in the dynamic measurements collected by a smart wearable.
  • Synthetic data are generated to reduce clinical trial sample size and duration
  • Generative AI models learn the patterns of their input data and then generate new data with similar characteristics
  • This is feasible as our analysis is personalized and baseline data are updated in an iterative fashion everyday

Risk Levels

  • AiCare uses a Decision Tree Ensemble based multiclass classification approach to classify risk into 3 levels: high, medium, and no risk
  • A maximum tree depth of 3 levels is deployed
  • The intrinsic graph of the decision tree facilitated the explainability of the model
  • Due to the nature of the decision tree to bisect the data space and the tendency to overfit the training data when classes are not well separated, we introduced regularization term in order to balance the bias-variance tradeoff (the second term of the training objective equation below)