AI-powered TwinRCTs hit enrollment targets faster because they require fewer patients to achieve the same power compared to traditional trial designs.
Many patients are wary of participating in clinical trials due to the prospect of receiving a placebo. TwinRCTs make control groups smaller, increasing a patients’s chance of receiving the experimental treatment.
Unlike first-generation TwinRCTs, patient digital twins in TwinRCTs II are emphasized or de-emphasized based on the confidence of the prediction, leading to an increase in trial power.
After a patient’s first clinical trial visit, our digital twin generator creates multiple probabilistic predictions of how that patient’s disease would progress over time if they received a placebo.
A patient’s predicted longitudinal disease progression is calculated as the mean of the distribution. In TwinRCTs II, the confidence of that prediction is also calculated by the spread of the distribution.
With TwinRCTs II, patient digital twins with high confidence are emphasized and ones with low confidence are de-emphasized, increasing trial power.