"Mantis Biotech claims it's developing the solution to fill this data availability gap. The company's platform integrates disparate sources of data to make synthetic datasets that can be used to build so-called 'digital twins' of the human body: physics-based, predictive models of anatomy, physiology, and behavior."
"These digital twins could be used for studying and testing new medical procedures, training surgical robots, and simulating and predicting medical issues or even patterns of behavior."
"To build these twins, Mantis' platform first takes data from a variety of sources such as textbooks, motion capture cameras, biometric sensors, training logs and medical imaging."
"We're able to take all these disparate data sources and then turn them into predictive models for how people are going to perform."
Large language models have the potential to revolutionize genomics research and clinical practices by improving diagnostics and drug discovery. However, they face challenges with rare diseases where data is limited. Mantis Biotech aims to address this issue by creating synthetic datasets through its platform, which integrates various data sources. These datasets can form digital twins of the human body, enabling predictive modeling for medical procedures and athlete performance, among other applications. The platform utilizes an LLM-based system to synthesize data and generate high-fidelity models for analysis.
Read at TechCrunch
Unable to calculate read time
Collection
[
|
...
]