Introducing our Digital Twin Generators for Hypertension, Dyslipidemia, and Type-2 Diabetes


February 15, 2024

By Eric Tramel, Frank Fuller, and Cary Murray, ML team extraordinaire

Metabolic diseases are a leading cause of global morbidity and mortality, impacting millions of lives each year. Although many new and existing therapies aim to mitigate the severity of these diseases, their downstream effects continue to dominate healthcare. In response, clinical science continues to advance our current standard of care by developing more effective treatments. We’re pleased to contribute to these advancements with the release of three new digital twin generators (DTGs) to accelerate trials targeting acute hypertension, dyslipidemia, and type-2 diabetes. These DTGs are designed to predict key clinical outcomes within the complex standard of care treatments in each of these areas, thereby improving our ability to model these conditions.

Each of our three new DTGs targets a specific segment of their respective disease area:

  • Dyslipidemia, involves abnormal lipid levels in the blood and is a critical risk factor for cardiovascular diseases. Our DTG can be used in hyperlipidemia trials where participants currently manage their cholesterol levels with statins.
  • Hypertension, or high blood pressure, is another condition affecting nearly half of all adults, which can lead to severe health complications like stroke if not managed effectively. Our DTG can be used for short treatment duration trials (<= 3 months) where participants are currently managing blood pressure with diuretics, beta-blockers, or a variety of other medications.
  • Type-2 diabetes, a chronic condition characterized by insulin resistance and elevated blood sugar levels, is a significant public health concern. Our DTG predicts blood sugar levels, cholesterol, and various lab and safety measures specifically for subjects with heart disease.

The power of Neural Boltzmann Machines in DTGs

Our latest DTGs are powered by our Neural Boltzmann Machines (NBMs), a conditional generative model that joins the direct predictive power of neural networks with the unsupervised distributional modeling offered by Restricted Boltzmann Machines (RBMs). NBMs excel in handling complex, incomplete, and noisy data, making them ideal for simulating the diversity of patient history and outcomes in metabolic diseases.

Coupled with our pioneering TwinRCTTM trial designs, our DTG technology represents a leap forward in clinical trial design and execution. Our digital twin generators create an individual digital twin for every trial participant before they are randomized into the experimental or control arm. The participant’s digital twin forecasts their health outcomes under placebo, regardless of their actual assignment. Digital twins enable TwinRCTs, highly powered clinical trials with smaller control groups, allowing more patients to receive experimental treatment. TwinRCTs reduce the time it takes to bring new drugs and therapies to market—a particularly beneficial approach for metabolic disease trials, where patient management, recruitment, and treatment adherence are challenging. Our methods using participants’ digital twins are qualified by the European Medicines Agency and align with current FDA guidance.

Join us in transforming clinical trials

The journey to combat metabolic diseases is long and complex, the introduction of these DTGs represents a significant step forward. We invite you to join us in this exciting new phase of clinical research, where innovation meets efficacy, to bring about a healthier future for all.

Please visit our website or contact us directly to learn more about our DTG technology and applications in metabolic disease trials. Your feedback and collaboration are invaluable as we continue to refine and expand our solutions in the fight against metabolic diseases.

To find out more about the coverage, capabilities, and training data of our DTGs, please visit our website to find detailed specification sheets for these and all the disease indications we support.

Heading 1

Heading 2

Heading 3

Heading 4

Heading 5
Heading 6

Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur.

Example of a caption
Block quote that is a longer piece of text and wraps lines.

Ordered list

  1. Item 1
  2. Item 2
  3. Item 3

Unordered list

  • Item A
  • Item B
  • Item C

Text link

Bold text