The idea of digital twins, digital representations of humans built with computer models, is gaining traction in both the private and academic sectors. Digital twins have the potential to improve healthcare by assessing health risks before a disease becomes a symptom, helping clinicians decide when to intervene.
A future where doctors can use digital twins to determine the most effective course of treatment is ambitious. Unlearn.ai, a startup which raised $50 million in a Series B funding round, started with clinical trials. Unlearn's digital twin product replicates the characteristics of patients in trials to enable what the company claims are smaller, faster studies.
We use data from a lot of trials. The product is a clinical trial, not an artificial intelligence model, according to the CEO.
Physicists by training, Fisher, Smith, and Walsh founded Unlearn. Leap Motion was a startup that developed motion sensors for desktops and augmented reality headsets.
Fisher, Smith and Walsh wanted to create a service that could process historical clinical trial data sets from patients to build machine learning models, which could in turn be used to create digital twins with corresponding virtual medical records. The digital twins records would be longitudinal and include data from over time and across systems, and cover demographic information, common test results and biomarkers that look identical to actual patient records in a clinical trial.
Our intention wasn't to speed clinical trials, but to research machine learning. Fisher said that there had been no investment in machine learning as a technology for pharma development. Fisher was a principal scientist at Pfizer.
Digital twins are created for every patient in a clinical trial by Unlearn. Fisher says that treatment effects can be estimated with greater precision after adjusting for the results from the digital twins.
According to Fisher, Unlearn's capabilities were enough to convince three companies to engage in studies with its product. According to Fisher, Unlearn is being used to incorporate prognostic information from digital twins into its randomized controlled trials, which the former hopes will enable smaller control groups and generate evidence suitable for supporting regulatory decisions.
If Unlearn's digital twin technology works as advertised, it could be a boon for the medical industry, which has been forced to swallow steep costs and logistical challenges associated with clinical trials. Clinical trials that support the approval of new drugs in the U.S. have a median cost of $19 million. A lack of qualified participants and changes in protocol can cause a clinical trial to drag on for years.
Several studies raise questions about the limitations of digital twin technology. The accuracy of predictions made using digital twins could be affected by bias arising from underrepresentation of Black patients in clinical trial data.
According to a draft opinion from the European Medicines Agency, digital twins could be used for the primary analysis of phase 1 and phase 2 drug studies. The drug part of the U.S. Food and Drug Administration is similar to the EMA.
He is wondering if there could be bias in the trial. Fisher said it would be impossible.
With the new capital, Unlearn plans to double its 40-person workforce and expand into new disease areas.
The clinical trial technology industry has a problem: pharma companies are skeptical of new technology.
Insight Partners was one of the investors in the Series B.
All Rights Reserved © 2024
