Mantis Biotech is developing “digital twins” of humans to address the lack of reliable medical data, especially for rare diseases and unusual conditions. These digital twins are physics-based predictive models of anatomy, physiology, and behavior, built from diverse sources like textbooks, motion capture, biometric sensors, training logs, and medical imaging.
The platform uses large language models to validate and synthesize data, then runs it through a physics engine to generate high-fidelity simulations. This allows researchers and professionals to study procedures, train surgical robots, simulate medical issues, and predict patterns, such as an athlete’s risk of injury.
Mantis has already seen success in professional sports, working with NBA teams to model athlete performance over time. The startup recently raised $7.4 million in seed funding to expand the platform, aiming to support preventative healthcare, pharmaceutical research, and FDA trials, while protecting privacy by using synthetic data instead of real patient data.
