Blog

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

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

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

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

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.

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

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

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.

What exactly is drug development?

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?

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.

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.

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

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

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

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

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.

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

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

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

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?