Imec Advances in Creating Medical Digital Twin for Gut Health

We’re excited to bring back Transform 2022 in person on July 19 and virtually from July 20-28. Join leaders in AI and data for in-depth discussions and exciting networking opportunities. register today!


Human gut health is closely linked to mental well-being, various degenerative diseases, and chronic inflammation. The balance of microbes in the different sections of the digestive tract is an important part of this. Researchers have made incredible progress in analyzing the microbes that come out at the end and in taking samples near the two openings. But so far, the relative composition of microbes in different sections of the medium has been a bit of a mystery.

An ambitious collaboration in Europe hopes to change that by building a Double digital of the human gut and its relationship to various health outcomes. At Imec Conference on future summits in Antwerp, Chris Van Hoof, vice president of R&D at Imec and general manager of the OnePlanet research center, discussed the company’s efforts to build a digital twin of the human intestine. Imec’s team is working to achieve this by combining new sensors, analytics and machine learning techniques with advice from nutritionists, doctors, medical researchers, chip designers and scientists from around the world. data.

Medical researchers are making great strides in building medical digital twins by exploring the human from the outside. But so far we have very little understanding of what goes on inside the digestive tract.

“You can do gastroscopy, colonoscopy, and stool analysis, but no one has mapped the entire gastrointestinal tract,” Van Hoof told VentureBeat.

Imec is a state-of-the-art R&D center facilitating industrial collaboration around silicon chips, nanotechnology and health. The current effort involves collaboration with researchers from Wageningen University and Research and Radboud University Medical Center. And Van Hoof said they are seeking input and advice from others to help guide the search and scale up the initial research.

The largest surface

Medically speaking, the surface of the intestine, called the lumen, is outside the body. Doctors consider it the largest area of ​​the human body, at around 30 square meters. It acts as a filter and a gatekeeper to capture nutrients and excrete wastes. And gut health is correlated with diabetes, metabolic health, weight loss, poor immunity, mental health, and dozens of diseases.

There are approximately 500 to 800 different populations of microbes in the body. The relative balance of these populations is often correlated with different pathologies. Various studies have linked several chronic diseases to microbial populations. And many seemingly unrelated diseases share common microbiome signatures, Van Hoof said.

Researchers don’t know why people develop a particular suit or how to adjust it. In a recent study, a few of Van Hoof’s colleagues ate a diet high in a range of plants that may affect their gut health. Everyone on the diet saw a change, but the differences were unique to each individual.

The Many Parts of a Medical Digital Twin

Elements of the medical digital twin include a new sensor platform built into a smart pill, toilets that analyze stool and urine, a smart lunch box, cameras that track what people eat and how they do it, and wearable devices to correlate these measures with stress and mental well-being.

As for the ingestible, a lot of work has gone into building a resilient package that’s small enough to swallow, enough to measure the right things, and tough enough to survive the harsh environment suitable for breaking down most substances. They are currently working on the regulatory process and how to start first-in-human trials early next year.

Smart pill developed by Imec.
Photo courtesy of Imec.

The team wanted to be able to take chemical and biological measurements, record physical characteristics like sound, and communicate wirelessly. It also needed very efficient electronics, as it had to run for up to a week. They also needed to build some sort of GPS so the stomach could track where it was moving through the body.

Models to refine

Today, knowledge of the factors that improve or worsen gut health is known only at the level of the general population. As a result, doctors tend to focus on population-level advice, such as avoiding fatty or spicy foods, which isn’t always helpful.

“We hope to create a model of the person to see what is virtually causing the flare-ups so that the person is not a guinea pig for treatment,” Van Hoof said, “rather the digital twin is the guinea pig to try new interventions for. see what would work best for them.

The team is exploring a range of strategies from individualized digital twins to larger digital twins for groups based on genotype, phenotype, or behavioral characteristics or microbiomes. Van Hoof said: “There is hope that we won’t have to create billions of models. Instead, we could create a few models and then refine them based on the data we capture to make them more manageable. »

Creating these new models will require a different approach than other areas. For example, a cardiovascular researcher can monitor electrocardiogram data to diagnose many diseases without knowing anything specific about the patient. “But there’s no gold standard for what the signal should look like for gut health,” he said.

Actionable insights

The effort is also on the user interface side of the digital twin. Most countries have basic health pyramids characterizing the basic elements of a healthy diet. But getting people to eat more of some things and less of others requires a behavioral rather than an informational approach.

For example, they created a smart snack box equipped with cameras to study people’s snacking behaviors. It turns out that many people, especially frequent snackers, tend to eat more calories than they take in due to unconscious eating habits. and wearable sensors can track mental and stress changes before someone snacks.

“We see physiological changes before a person has a craving for sweets. This is part of the model that we hope to link to gut health, where we can pick up on these signals and hopefully direct people to alternatives. healthy,” Van Hoof said.

Build the right data framework

A digital twin of gut health involves bringing together data from many sources and no one knows how to do it at scale. Ultimately, the hope is that the digital twin can work with sensors, applications, and data infrastructure from many parties. But in the meantime, the group integrates everything into the Imec OpenPlanet infrastructure, a low code health and environment research platform.

OpenPlanet includes applications for data collection, data connectivity, storage and analysis. It also supports curated algorithms and applications for various use cases. For example, data from wearable devices can be shared live between doctor and patient or between a digital twin and a health avatar. This can help democratize access to digital twins in addition to predefined templates, data formats and machine learning Managed workflows with appropriate security and privacy barriers.

Van Hoof thinks past research on the relationship between gut health and other areas has been hampered due to different ways of collecting, formatting and analyzing data. They avoid these problems by building and integrating all the parts in-house. tools like federated learning could help support a wider range of sensors, data sources and applications on the road.

Creating a digital twin will require further studies and many partners with medical, business and healthcare expertise. Van Hoof said they are looking for other parties to join the effort in food and beverage technology, pharmaceutical and medical companies.

VentureBeat’s mission is to be a digital public square for technical decision makers to learn about transformative enterprise technology and conduct transactions. Learn more about membership.

#Imec #Advances #Creating #Medical #Digital #Twin #Gut #Health

Leave a Comment

Your email address will not be published. Required fields are marked *