Blog

Blog

Embracing Innovation to Move Forward

At Unlearn, our goal is to use the data available from historical trials, to generate new evidence to inform and advance research.
Blog

Transforming Clinical Trials with Intelligent Control Arms

Digital twins can be used to populate an intelligent control arm, a type of external control arm with a variety of applications.
Blog

Different Clinical Data, Different Purpose

To solve the problem of trial inefficiency, clinical trial sponsors are turning to external data sources to supplement and increase efficiency of clinical trials.
Blog

Digital Twins for Matching (Third Time's a Charm)

Using a machine-learning model, we can create exact matches for actual subjects at baseline, which are called digital twins.
Blog

Propensity Score Matching: A Method of Last Resort?

While propensity score matching makes it easier to match subjects with complex covariates, it generates a less precise estimate of how effective a drug is.
Blog

How Many People Do We Need to Find an Exact Match?

The goal of this post is to show (by way of a lottery analogy) that if we want to find an exact match for a subject with Alzheimer's, we would need a dataset with millions of patients -- an infeasible
Blog

Can We Find an Exact Match from Historical Data?

Finding matches based on a large number of variables is difficult, often impossible.
Blog

What is a Digital Twin?

Let’s go through an aerospace example to illustrate what is required to make a digital twin, how it’s created, and how it’s used.
Blog

Basics of Drug Development

What exactly is drug development?
Blog

Learning from Data Across the Alzheimer's Disease Spectrum

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?
Blog

Reflections on AAIC 2019: Community, Cause, and Challenges

While treating the patient is the utmost priority, we need to understand that Alzheimer’s impacts every part of a person’s life and to address all of those parts, both effectively and compassionately.
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.
Blog

The Unlearn Story

Unlearn revels in being different. Most notably, its location is rather unusual for a technology start-up.
Blog

Celebrating Our Second Unlearniversary

Today marks Unlearn's second birthday - what we fondly call our unlearniversary.
Blog

Historical Data for Control Arms of Clinical Trials

Clinical trials take a long time, eating into the patent lifetime of a therapeutic. Why do they take a long time?
Blog

What's Wrong with Clinical Trials?

The biggest problem with clinical trials is they take too long.
Blog

The Advantages of Modeling Clinical Data for Control Arms

Models are the key to unlocking the full potential of historical data to inform current trials with a broad spectrum of trial designs and patient covariates.
Blog

Uncertainty is More Important to AI than Explainability

Uncertainty is an alternative to explainability that places no constraints on the complexity of the underlying algorithm.
Blog

Introducing Paysage

Paysage is a powerful library for training RBMs — and more-generally, energy-based neural network models.
Blog

The Travails of Comparing Generative Models

Increasingly, the task of machine learning will be to explore the formidable frontier of unsupervised learning.
Blog

Don't Model Humans with SNPs

Imagine a computational biologist who wants to build a model to predict the prognosis of a patient with Alzheimer’s disease. What variables should he choose?