On this episode we'll meet biophysicist, machine learning researcher, and CEO of UnlearnAI Dr. Charles Fisher. He and the team at Unlearn have the goal to build the entire biomedical machine learning stack, from scratch. Their strategy is that with a fit-for-purpose biomedical machine learning infrastructure and novel deep learning techniques, along with enough data about patients, that they can generate synthetic versions of actual patients, entirely in the data, with the goal to make them “computationally indistinguishable” from real patients. A “digital twin” that could help to better understand the impact of medicines before they’re used in a patient, or in clinical trials to be used alongside real patients in what they call “intelligent control arms.” Unlearn believes that we can obtain the same rigorous, statistically-powered clinical evidence but with fewer subjects. A fascinating approach to the problem of how to make clinical trials more efficient, and understand more about what may be possible with more and better patient data. This is the Tomorrow Scale podcast, hosted by Justin Briggs (@briggsly).
Unlearn AI: https://unlearn.health
Charles Fisher CV, Google Scholar: https://scholar.google.com/citations?user=MQlhMlwAAAAJ&hl=en
Boltzmann Encoded Adversarial Machines (BEAM) paper: https://arxiv.org/pdf/1804.08682.pdf
“The FDA needs to set standards for using artificial intelligence in drug development” by Dr. Charles Fisher in StatNews, 11/7/2019: https://www.statnews.com/2019/11/07/artificial-intelligence-drug-development-fda-standards-needed/
Dr. Fisher’s presentation at a recent FDA Meeting (begins on page 175; linked here since we didn't end up discussing each point after all): https://www.fda.gov/media/136577/download#page=175
Photocredit: Dr. Fisher’s headshot, augmented based on the blue binary background image, using a neural style transfer model found here: https://git.io/Jf4a6
The TomorrowScale Podcast was created to showcase scientists and entrepreneurs who are building science-based businesses, and to hear their stories from the benches and in the trenches of research & development. The views expressed by the host and guests are their own, and the content of this show should not be considered legal, tax, or investing advice. Thanks to our guests for sharing their time and knowledge with us. Thank you for listening. Please science responsibly.