Artificial intelligence (AI) and machine-learning company Unlearn, which creates “digital twins” of patients in clinical trials to improve efficiency of clinical studies, today announced that it has closed a $50 million Series B funding round.
The new investment will be used to continue deployment with pharmaceutical and biotech companies of Unlearn’s TwinRCTs—randomized trials that uses machine learning and historical data to achieve a higher probability of success with a smaller number of patients. The company’s technology is designed to increase the efficiency of randomized clinical trials (RTCs). Similar to a typical RTC, Unlearn randomizes enrolled patients to a treatment group and a control group, but can effectively decrease the number of patients needed for a clinical trial by the creation of digital twins for every patient enrolled by using a machine learning model trained on historical control data.
“By reducing the size of the control arm, more patients in a TwinRCT have access to a potentially beneficial experimental treatment instead of a placebo. Trials can be run faster and with the same resources so that patients can receive access to more effective treatments sooner,” said Dylan Morris, managing director at Insight Partners, a New York-based global venture capital and private equity firm that lead the latest financing round. “TwinRCTs not only increase trial efficiency but also provide rigorous evidence suitable for supporting regulatory decisions.”
According to the company, the treatment effects for the primary and secondary outcomes can all be estimated with greater precision after correcting for each patient’s prognostic score derived from their digital twin. The method is gaining traction with regulatory bodies and the European Medicines Agency (EMA) has published a draft qualification opinion indicating that this in silico approach can be used for the primary analysis of phase II and III studies because it doesn’t introduce bias.
“Unlearn continues to make rapid progress as we expand our work with global biopharmaceutical companies and advance productive conversations with global regulatory authorities who are committed to supporting innovation in clinical trials,” said Charles Fisher, Ph.D., founder and CEO of Unlearn. “This new financing is validation of our expanding footprint in clinical trials.”
Unlearn is also garnering attention from pharmaceutical and biotech companies for its ability to run faster, more efficient, and less expensive clinical trials. In February, the company announced a multi-year collaboration with Merck KGaA, Darmstadt, Germany, for the use of its digital twin technology in late-stage clinical trials across its immunology drug candidate pipeline, with the potential expand into other disease areas.
Founded in 2017, Unlearn first looked to apply its machine-learning approach as a clinical decision support tool for physicians that could use machine learning to answer physicians’ “what-if?” questions for each patient. So, what would be the potential outcome for a patient if she changed her diet, or stopped taking a current medication. But soon after, the company saw the potential for its technology. The company soon realized it could take this same prognostic approach to potentially improve the efficiency of clinical trials by using baseline data from the time of patient enrollment to predict how that patient would progress within the control arm of study.
“We realized that this information could allow us to run more efficient, ethical trials using smaller control groups. Although the concept of a digital twin wasn’t entirely new, with prior applications in engineering, their ability to inform medical decisions and use in reducing the size of control arms still belonged within the realm of science fiction,” wrote Fisher in a blog post on the Unlearn website describing the early development of its technology. “Discovering how far we could push ML to solve these kinds of problems became our north star. Today, we’re one step closer to making science fiction a reality with our TwinRCT technology.”
