2018
Farrugia dates the beginning of the Mayo Clinic Platform to the end of 2018 or beginning of 2019.
“And that's the genesis of MCP, Mayo Clinic Platform. So I'll timestamp that as end of 2018, beginning of 2019.”
Topic
12 facts from 3 episodes, in date order. These are what speakers said on the shows, each linked to the moment it was said. They aren't independently verified.
2018
Farrugia dates the beginning of the Mayo Clinic Platform to the end of 2018 or beginning of 2019.
“And that's the genesis of MCP, Mayo Clinic Platform. So I'll timestamp that as end of 2018, beginning of 2019.”
2019
Halamka says the Mayo Clinic Platform was established in 2019 to provide repeatable processes and technologies for the machine learning operations lifecycle while protecting privacy.
“So Mayo Clinic platform was established in 2019 to give us repeatable processes and technologies for the whole MLOps lifecycle while protecting privacy and ensuring what we do is ethical and safe.”
2024
Mayo Clinic Platform's accelerator program has brought in about 40 startup companies.
“On the one hand, we have an accelerator program where we brought in about 40 companies so far.”
Undated
Halamka oversees 150 years of multimodal data on 10 million patients at the Mayo Clinic Platform, used for innovation and model development while kept private and secure.
“So my role as president of Mayo Clinic Platform is to oversee all of this 150 years of multimodal data on 10 million patients and use it for innovation and model development while keeping it private and secure.”
Undated
According to Halamka, the Mayo Clinic Platform has about 160 partner companies developing and testing algorithms and experimenting with large language models.
“we have about 160 partners. And these are companies that are developing novel algorithms, testing algorithms, experimenting with large language models.”
Undated
Mayo Clinic's distributed data network lets partner organizations keep data in their own secure locations while models are developed and validated against each other's data without centralizing it.
“Can we develop models against each other and validate them without having to centralize the data?”
Undated
Halamka says Mayo's 'data behind glass' approach keeps certified de-identified data inside the Mayo firewall in a cloud container.
“So really important that we use something called data behind glass is never leaving the Mayo firewall, the cloud container. It's fully de-identified, certified as de-identified.”
Undated
Mayo Clinic Platform puts de-identified data into the OMOP standard format under the control of the organizations that generated it.
“put them in an industry standard format, OMOP, under the control of those who generated the data.”
Undated
Brad Malin certifies each de-identified data set in the Mayo Clinic Platform federation.
“Brad Malin, one of the world leaders in DID, REID, does the certification of each of the resulting data sets.”
Undated
Working with the International Standards Organization, Mayo Clinic Platform extended OMOP to cover digital pathology and genomics.
“We've extended OMOP to include certain other kinds of data elements like digital pathology and genomics that are quite in core OMOP.”
Undated
In one partner data set Mayo's tools found that more than half of the social determinants of health data were missing, so AI based on them was discouraged.
“what we found is more than half of the social determinants of health were missing.”
Undated
Mayo CEO Gianrico Farrugia set Halamka a goal of touching 4 billion people by the end of his presidency.
“And by the end of your presidency, I want you to have touched 4 billion people.”
Episodes