By using foundation models to analyze vast datasets, companies can create a synthetic 'standard of care' arm for single-arm Phase 1 trials. The AI matches patients based on deep clinical and genomic parameters, providing insights comparable to a much larger Phase 3 trial.

To increase the predictive power of their data, Aphaia structured its Phase 2 study to mimic a Phase 3 trial. By imposing minimal constraints on patients (e.g., no coaching or calorie restrictions), the results are more likely to reflect real-world outcomes. This reduces the risk of a performance drop-off between phases, making the asset more attractive to potential partners.

Instead of the high-risk approach of replacing a trial's control arm with digital twins, Unlearn.ai adds counterfactual data to every participant. This method increases a trial's statistical power, allowing for smaller control arms or a higher chance of success, while satisfying regulatory constraints for pivotal trials.

The FDA initially agreed uniQure could use the robust Enroll HD database for its control group, a standard practice for rare diseases. Their later reversal, demanding a new placebo trial, creates significant regulatory uncertainty, making it harder for companies to develop therapies for rare conditions.

The podcast highlights propensity score matching, a statistical method creating a comparable control group from large observational datasets like Enroll HD. This is an established, FDA-approved method for rare diseases where placebos are unethical or impractical, yet the agency rejected its pre-specified use in uniQure's case.

To ensure patients have active disease progression and increase the likelihood of demonstrating a treatment effect, the company mandates a six-month monitoring period before intervention. This filters out slow-progressing patients where a positive outcome would be difficult to prove, thereby de-risking the clinical trial.

Instead of competing with traditional methods, synthetic research addresses the vast number of decisions made without data due to time or budget constraints. It quantifies the risk of acting on intuition alone, filling a critical gap where research was previously unfeasible, thus lowering the 'cost of doing nothing'.

Conquer's Farsight Twin can predict a patient's response to a novel drug, standard of care, and the combination therapy separately. This allows pharma companies to determine if a positive response in an early-phase trial is truly driven by their new asset or just the background therapy, providing crucial efficacy data.

To de-risk its EMERALD trial for a poorly documented patient population, Resolution Therapeutics first ran a natural history study (OPOL). This provided crucial data to inform the trial protocol and, more importantly, allowed the creation of a matched external control arm, a clever and capital-efficient strategy.