tech
March 30, 2026
Mantis Biotech is making 'digital twins' of humans to help solve medicine's data availability problem
Mantis takes disparate sources of data to make synthetic datasets that can be used to build so-called "digital twins" of the human body, representing anatomy, physiology and behavior.
TL;DR
- Large language models have the potential to advance genomics research, clinical documentation, diagnostics, drug discovery, and more.
- A key challenge for LLMs in healthcare is the scarcity of reliable data for rare diseases and unusual conditions.
- Mantis Biotech's platform integrates various data sources to create synthetic datasets for building 'digital twins' of the human body.
- These digital twins are physics-based, predictive models of anatomy, physiology, and behavior.
- Applications include data aggregation, analysis, testing new medical procedures, training surgical robots, and simulating medical issues or behavior patterns.
- The platform uses LLMs to process data and a physics engine to ground synthetic data and realistically model anatomy.
- Mantis has found success in professional sports, creating digital representations of athletes to track performance changes over time.
- The company recently raised $7.4 million in seed funding and plans to expand its platform for preventative healthcare, pharmaceutical labs, and researchers.
- The technology aims to provide insights into patient treatment responses and potentially fill gaps where patient data is difficult to access, unstructured, or siloed.
Continue reading the original article