Unlearn

Share this post

An updated digital twin generator for Alzheimer's disease (version 3.1)

unlearnai.substack.com

Discover more from Unlearn

Unlearn's purpose is to advance AI to eliminate trial and error in medicine. Subscribe to learn about how we're innovating AI today to attain this future.
Continue reading
Sign in

An updated digital twin generator for Alzheimer's disease (version 3.1)

By Jon Walsh, Founder and Head of Modeling, Unlearn.AI

Unlearn
Jul 31, 2023
Share this post

An updated digital twin generator for Alzheimer's disease (version 3.1)

unlearnai.substack.com
Share

We’re excited to announce the latest release of our Alzheimer’s Disease Digital Twin Generator, AD-DTG-3.1.  Coming just a month after our most recent AD DTG release that introduces a novel architecture, this release makes some improvements that we’ll be using across disease areas in the future.

Missing data is a challenge that rears its head in multiple ways. Participants in a study will miss observations, and different studies will measure different outcomes, creating a patchwork of data where missingness is standard and not an exception.  We leverage as much data as possible to reliably predict outcomes, but a consequence of this completeness means that sometimes this means that certain things that our model uses won’t be measured in a clinical trial.

When we make digital twins, we want the predictions to be as insensitive as possible to missing data. If a feature is important, participants that are missing that feature will have a lower precision. Our DTG specification sheets, available on our website, characterize this sensitivity. But how we approach making predictions from missing data will impact this sensitivity.  For example, if we just replace missing data with the most common value, we’ll be more sensitive than if we did a more intelligent imputation or handling of that missing data.

Our latest DTG release updates how we handle missing data at baseline by swapping out a component in the architecture.  In this new version, we use a neural network imputation model, co-trained as part of the Neural Boltzmann Machine, to impute data used for the creation of digital twins.  This model can learn from the other variables to impute, in a context-dependent way, the value for missing baseline variables.  This results not just in a reduced sensitivity to missing data at baseline, but better performance for the DTG overall.  You can find the updated DTG spec sheet on our website, and can expect more improvements as we continue to innovate in machine learning.

Recently, a potential customer asked, “what should we measure at baseline in our trial to make the best use of your model?”.  This is the kind of question we love, because it shows a deep understanding of how predictive models work. We build digital twin generators from diverse data sources, both in terms of populations and outcomes, to make strong and robust digital twins.  This release takes us one step closer in our mission of eliminating trial and error in medicine.

Share this post

An updated digital twin generator for Alzheimer's disease (version 3.1)

unlearnai.substack.com
Share
Previous
Next
Comments
Top
New
Community

No posts

Ready for more?

© 2023 Unlearn
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing