How are we changing clinical trials?

Publications

Machine learning for comprehensive forecasting of Alzheimer's Disease progression

We have shown that generative models capable of sampling conditional probability distributions over a diverse array of clinical variables can accurately model the...
Press

Will digital clones transform how pharmas run clinical trials? This S.F. startup is counting on it.

Publications

Generating Digital Control Subjects using Machine Learning for Alzheimer's Disease Clinical Trials (CTAD 2019)

Press

Broadening Role for External Control Arms in Clinical Trials

Unlearn.AI Inc. is going a step further, using data from historical trials and patient registries to build algorithms that simulate artificial patients.
The ability to reduce the burden on control subjects with subjects in clinical trials for complex diseases like Alzheimer’s Disease would drastically improve the search..
The San Francisco-based company creates digital replicas of participants in clinical drug trials using artificial intelligence.

The FDA needs to set standards for using artificial intelligence in drug development

Digital Twin Advances Poised to Expand Clinical Trial Reach

What is a Digital Twin?

The Advantages of Modeling Clinical Data for Control Arms

Podcasts

UCSF Rosenman Institute - The Health Technology Podcast #59: Digital Twins for Clinical Trials

Charles Fisher: Digital Twins for Clinical Trials
Publications

Generating Digital Twins with Multiple Sclerosis Using Probabilistic Neural Networks

Using a dataset of subjects enrolled in the placebo arms of MS clinical trials, we trained a Conditional Restricted Boltzmann Machine to generate digital subjects.
Publications

Boltzmann Encoded Adversarial Machines

Blog

Learning from Data Across the Alzheimer's Disease Spectrum

Blog

Better Clinical Trials without Statistical Significance

To take into account uncertainty, we should be conservative and estimate the smallest treatment effect that we would expect to observe over many repeated studies.
At AAIC, I watched the talks with this question in mind: how would we build a model of disease progression in the early stages of AD?
The deep learning revolution has driven tremendous advances on supervised learning problems, and a primary outcome is that feed-forward neural networks have become a powerful tool.

Contact us

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.