At Unlearn, our goal is to inform, advance, and accelerate research to help bring new treatments to patients who need them faster. Leveraging sophisticated machine learning and historical patient data, we generate new evidence — Digital Twins, or predicted placebo outcomes for each patient in a trial. Clinical trials powered by Digital Twins provide greater statistical power to answer existing and new research questions, in a shorter time frame, and are easy to integrate into protocols and analysis plans. In this whitepaper, we provide an overview of Digital Twins and how this innovation makes it possible to prospectively design smaller trials with higher statistical power, or to recover power in ongoing trials impacted by low enrollment or high dropout rates.