Platform
The Unlearn Platform
Digital Twin Generators
Research
Artificial Intelligence
Clinical Research
Company
Evidence
About
Careers
Blog
Press
Book a demo

Trusted by leading sponsors.
Grounded in science.
Proven in trials.

Unlearn’s digital twins are being used by some of the world’s largest pharmaceutical companies and most innovative biotechs—backed by global regulators and supported by cutting-edge machine learning research.

Paving the Regulatory Path for AI in Clinical Trials

Unlearn’s methods have been recognized and supported by both U.S. and European regulators.

PROCOVA was officially qualified by the European Medicines Agency for use in Phase 2 and 3 trials with continuous outcomes.

U.S. FDA provided positive feedback on PROCOVA, supporting its use in covariate-adjusted analyses across clinical development.

FDA recommends that sponsors adjust for covariates that are anticipated to be most strongly associated with the outcome of interest…it may be useful to use previous studies to select prognostic covariates or form prognostic indices.

In a trial that uses covariate adjustment, the sample size and power calculations can be based on adjusted or unadjusted methods.

CHMP qualifies PROCOVA and that the proposed procedures could enable increases in power and/or decreases in sample size in phase 2 and 3 in clinical trials with continuous outcomes.

Real-world results

Driving Impact Across Clinical Development

Our AI-powered solutions are being used across clinical development to reduce trial size, increase power, accelerate timelines, and enable richer trial insights. Explore real-world examples of how sponsors are using digital twins to solve critical challenges.

Benefit

Reduce sample sizes while maintaining power

AD/PD
Machine Learning Model Enables Accelerated Enrollment Timelines in Parkinson’s Disease Clinical Trials
AbbVie
Assessment of AI-generated Digital Twin (DT) Methodology on Reduction of Treatment Effect Variance and Potential Clinical Trial Sample Size Saving Using a Phase 2 Trial Dataset From Patients With Alzheimer’s Disease (AD)
AbbVie
Digital twin predictions of patient outcomes enable more efficient and powerful Clinical Trials
J & J
Accelerating randomized clinical trials in Alzheimer’s disease using generative machine learning model forecasts of disease progression
MDS
Boosting Clinical Trial Power in Parkinson’s Disease with AI-Generated Digital Twins
Unlearn
Boosting Clinical Trial Power in ALS with AI-Generated Digital Twins; 2024 Annual NEALS Meeting
Roche
Evaluating Digital Twins for Alzheimer’s Disease using Data from a Completed Phase 2 Clinical Trial
Unlearn
Boosting Clinical Trial Power in ALS with AI-Generated Digital Twins; 35th International Symposium on ALS/MND

Benefit

Reduce variability to improve decision making in early-stage trials

remynd
Use of digital twins in a Phase 2a trial to predict disease-progression of participants with mild-to-moderate Alzheimer's Disease supports early signals of efficacy

Benefit

Use digital twins as an external comparator to support efficacy findings in early-stage studies

ProJenX
ProJenX and Unlearn Announce Partnership to Augment ALS Clinical Trial PRO-101 with Digital Twin Model
QurAlis
Streamlining Efficiency of QRL-201 Randomized Control Trial & Increasing Confidence of Results with Generative AI Technology.

Benefit

Mitigate data variability when enrolling globally diverse populations

AD/PD
Enhancing Clinical Trial Inclusivity in AD with Digital Twins Generator

Benefit

Optimize study design, including endpoint, time point, and eligibility strategies

Trace
Trial Planning with Unlearn

Why leading sponsors choose unlearn

“Working with Unlearn to mine their extensive, well-curated database through the use of the ALS DTG will enable us to explore smarter designs and make confident and informed decisions as we plan our Phase 1/2 trial. Ultimately, these insights can help us to move faster for people living with ALS who are waiting for new treatment options."

Eric Green, M.D., Ph.D., co-founder and CEO of Trace Neuroscience

View Case Study

“The ecosystem at the moment doesn’t sustain the way we’ve been doing it traditionally. And (Unlearn) is at the leading edge of this thinking.”

Kasper Roet, QurAlis

View Case Study

Research & Thought Leadership

Pioneering AI Research

Unlearn’s platform is powered by novel, disease-specific AI models called Digital Twin Generators (DTGs). Learn more about how we build and validate these models:

Date
Title
Publisher
Date
May 2, 2024
Digital Twin Generators for Disease Modeling
Publisher
arXiv
Date
March 20, 2024
Defining digital twins in drug discovery and development
Publisher
Unlearn
Date
February 6, 2024
How to position clinical trials with digital twins for regulatory success
Publisher
Unlearn
Date
November 23, 2023
Bayesian Prognostic Covariate Adjustment With Additive Mixture Priors
Publisher
arXiv
Date
May 15, 2023
Neural Boltzmann Machines
Publisher
arXiv
Date
December 20, 2022
Evaluating Digital Twins for Alzheimer’s Disease using Data from a Completed Phase 2 Clinical Trial
Publisher
Alzheimer’s Association
Date
December 19, 2022
Prognostic Covariate Adjustment for Binary Outcomes Using Stratification
Publisher
arXiv
Date
August 9, 2022
Restricted mean survival time estimate using covariate adjusted pseudovalue regression to improve precision
Publisher
arXiv
Date
May 2, 2024
Digital Twin Generators for Disease Modeling
Publisher
arXiv
Date
March 20, 2024
Defining digital twins in drug discovery and development
Publisher
Unlearn
Date
May 15, 2023
Neural Boltzmann Machines
Publisher
arXiv
Date
December 24, 2020
Modeling Disease Progression in Mild Cognitive Impairment and Alzheimer’s Disease with Digital Twins
Publisher
arXiv
Date
February 4, 2020
Generating Digital Twins with Multiple Sclerosis Using Probabilistic Neural Networks
Publisher
arXiv
Date
September 20, 2019
Machine learning for comprehensive forecasting of Alzheimer’s Disease progression
Publisher
Nature
Date
May 27, 2019
A high-bias, low-variance introduction to Machine Learning for physicists
Publisher
arXiv

Flexible Engagement Models That Work for You

Whether you need full-service support or want to integrate AI into your own infrastructure, Unlearn offers the flexibility to meet your data and operational needs. We can source data, build applications, and deliver services entirely on our platform—or we can leverage your proprietary data to build and deploy custom applications on your infrastructure. Our approach is built for biopharma partners who need speed, security, and adaptability without sacrificing performance.

Full-Service Model

We source data, build models, and deliver results end-to-end on our platform

Custom Infrastructure

We integrate with your infrastructure to build secure, proprietary solutions using your data

Data & Platform Strength

Therapeutic indications
20
+
Clinical study records
1
M

Experts in Data Sourcing and Operationalizing Unstructured Data

Unlearn has deep expertise in transforming complex clinical data into AI-ready formats. Our Platform draws from over 1 million longitudinal clinical study records and spans 20+ indications, including neuroscience, immunology, cardiovascular, and metabolic diseases. This rich data foundation powers scalable, scientifically rigorous disease-specific ML models with exceptional performance.

Learn about our AI Research
Discover the power of the Unlearn Platform
Book a Demo
Platform
The Unlearn PlatformDigital Twin Generators
Research
Artificial IntelligenceClinical Research
company
AboutCareersBlogPress
Connect
© 2025 Unlearn.ai, Inc. All rights reserved.
TermsPrivacyData Acknowledgements
Sign in