Mantis Biotech is making 'digital twins' of humans to help solve medicine's data availability problem

Mantis Biotech of New York is developing a platform to create synthetic datasets for building digital twins of the human body. The digital twins are physics based predictive models of anatomy, physiology, and behavior designed to fill gaps in medical data availability. The platform draws from sources such as textbooks, motion capture cameras, biometric sensors, training logs, and medical imaging. It uses an LLM based system to route, validate, and synthesize data streams before processing them through a physics engine to produce high fidelity renders. Founder and CEO Georgia Witchel said the models could support studying and testing new medical procedures, training surgical robots, and simulating medical issues. The approach may help researchers access data on rare diseases and edge cases that are difficult to obtain due to ethical and regulatory constraints. Mantis has an NBA team as a client and recently raised 7.4 million dollars in seed funding led by Decibel VC with participation from Y Combinator, angel investors, and Liquid 2. The company plans to expand the technology for pharmaceutical labs and researchers working on FDA trials as well as preventative healthcare applications.