Tag: Pratt School of Engineering

Amid the constant drumbeat of campus events, much of the conversation turned toward the challenges we face in energy policy, security and transitions during Duke’s annual Energy Week, held Nov. 11-15.

On the second day, the Innovation Showcase featured not only startups making their pitches for clean energy and sustainable tech products, but students doing so as well.

Currently in its second year, Duke Design Climate is a new initiative between the Pratt School of Engineering and the Nicholas School of the Environment. It functions as a two-course sequence, in which students form groups to prototype and promote climate solutions after conducting market research.

As I made my rounds to the teams, I met a mix of graduate students and undergraduates with academic backgrounds ranging from engineering to economics to environmental science. The ideas they have aren’t purely theoretical: all are looking for sponsors or partners to help implement their solutions into real-world use. Here were some of the highlights:

Team ReefCycle is building from plants: Our first stop is named after the company whose product they intend to scale up. Initially, Mary Lempres founded ReefCycle to develop sustainable material for artificial reefs. Regular industrial production for cement requires intensive heating– burning of fossil fuels–releasing tons of carbon dioxide. ReefCycle sought to reduce this climate impact with a different method: their cement is plant-based and enzymatic, meaning its essentially grown using enzymes from beans. Testing in the New York Harbor yielded some promise: the cement appeared to resist corrosion, while becoming home for some oysters. The Design Climate team is now trying to bring it to more widespread use on land, while targeting up to a 90% reduction in carbon emissions across all scopes.

Team Enfield is uplifting a local community: Design Climate, evidently, is by no means limited to science. Instead, these team members intend to address an environmental justice issue close to home: energy inequality. Around 30-35% of Enfield residents live below the poverty line, and yet suffer from some of the highest energy bills in the larger area. Located a ninety minute drive east of Durham, this rural town is one of the poorest in North Carolina. Historic redlining and unfavorable urban planning are responsible for its lack of development, but now this team aims to bring back commerce to the area through microfinance. Once enough funding is gathered from investors and grants, the team hopes to provide microloans and financial literacy to spur and empower businesses.

Team Methamatic promotes a pragmatic e-methane solution: This team is harnessing the power of sunlight to drive fuel production. Synthetic methane, commonly referred to as e-methane, is produced by reacting green hydrogen and carbon dioxide. “Currently, the power-to-gas process can be carbon neutral,” said team member Eesha Yaqub, a senior. “Sourcing the recycled carbon dioxide from a carbon capture facility essentially cancels out the emissions from burning methane.” However, this power-to-gas (P2G) process is an intensive one requiring high heat, energy, and pressure–hoops that might not have to be jumped through if an alternative process could break through the market. Professor Jie Liu and the Department of Chemistry have been working on developing a reactor that would conduct this same reaction without those obstacles. “[Utilizing] the energy from ultraviolet light, which is absorbed by a catalyst …makes the process less energy intensive,” Yaqub said.

Right now, the team has a small prototype, but one used for commercial generation would appear much larger and cost between $15,000 to $20,000. Their intended customers? Oil and gas companies under pressure to shift away from fossil fuels. If successfully scaled up, they predict this process would produce e-methane at a price of $5 per kilogram.

Analyzing living shorelines through Team Coastal Connect: If “Coastal Connect” sounds more like an app than a project name, that’s because it is one. This group is designing what one member dubbed a “fitbit for shorelines”: a monitoring system that brings data from ocean buoys to the phones of local landowners. While measurements in salinity and water level aren’t always telling for the average person, the app would contextualize these into more useful phrases. Is it currently safe to swim? It’ll let you know.

Moreover, it would also allow for the long-term monitoring of living shorelines. While we know this nature-based solution offers resilience to natural disasters and presents erosion, short-term fixes like seawalls are often built instead to continue allowing development up to the edge of beaches. The team hopes that ideally, providing concrete data on living shorelines would allow us to demonstrate their benefits and promote their implementation.

By Crystal Han, Class of 2028

Invented at Duke, Inspired at Duke

By Stone Yan

On November 25, 2024

In Biomedical Engineering, Entrepreneurship

“Our technology is tailored towards scanning animals. In fact, we can run scans on entire organisms!”

Image from the Photoacoustic Imaging Lab that made it onto the front page of Science: glassfrog transparency!

Excitedly, Soon-Woo Cho, a postdoctoral associate in the Photoacoustic Imaging Lab, referred me to the standing poster at the Nov. 20 Invented at Duke showcase. While I stood puzzled looking intensely at the articulate images, I suddenly realized that the jumble of blue and red outlined the shape of a frog!

As one could imagine, this technology, the masterpiece invention of biomedical engineering professor Junjie Yao and his team, is too advanced for a first-semester undergraduate to understand.

Nonetheless, Cho patiently explained its basic mechanisms to me in simpler terms. One of the technology’s key attributes was its speed; while traditional imaging counterparts were known for their long processing times, Yao’s team was able to reduce that time to mere seconds.

Another accomplishment is the product’s versatility and widespread application. Not only can the system distinguish between arteries and veins, coloring them as red and blue respectively, it can also play an important role in diagnosing cancer cells, as these malignant cells are known for inducing abnormal growth of surrounding blood vessels.

After hearing this inspirational work, I traveled a few steps to another booth. While both research projects take place within the biomedical engineering department, their focus could not be more different. Ruth Verrinder, a current PhD student working in Jonathan Viventi’s lab, explained to me how the flexible electrode strips on display are part of an effort to address a significant medical need.

Ruth Verrinder, PhD student and member of the Viventi Lab.

Today, many surgeries to treat epilepsy are disappointingly unsuccessful. Even after a lengthy medical process including diagnosis and highly intensive treatment and procedures, such failures are simply too much to bear for many patients and families. The Viventi Lab believes that through improving the quality and quantity of data collected by medical electrodes, more surgical successes would naturally follow.

Their current product is already in use at Duke, and the team has ambitious plans for further developing the product. The top priority is to build implantable electrodes so brain signals could be tracked for weeks to months before prospective surgeries, better informing surgeons and medical professionals on the specific patient’s conditions.

While the booths hosting major inventions attracted the most fanfare, many other organizations were also present. One can hardly avoid the history exhibition: the bending, wave-like wall of “A Century of Innovation at Duke” greeted every visitor as they walked in the Penn Pavilion doors. On the other side of the wall, a history table curated by the Rubenstein Library displayed remarkable patents from Blue Devils across time, not to mention the popular button-making station that touted designs like “I love patents!”

Although the acclaimed Dr. Robert Califf, director of the Food and Drug Administration, did not make it to the event, the occasion was nonetheless an overwhelming success. As a biomedical engineering student, I got to witness some of the most advanced research occurring in my field of study and meet prominent faculty. In the crowd of attendees, many students, regardless of undergraduate or graduate, studying humanities or the sciences, huddled around posters while inquisitively listening to inventors. Even academics from other institutions came to attend the sixth annual Invented at Duke: while I was learning more about the Viventi Lab’s research, a scholar from the University of Georgia joined the huddle and posed questions.

Even as all attendees, including myself, were astounded by the ingenious discoveries presented, I think there is a deeper takeaway than simply being “wowed” by incredibly advanced brain electrodes or imaging systems.

As stressed by the Office of Translation and Commercialization, Office of Innovation and Entrepreneurship, and Nucleate, a student-led organization focused on biotechnology innovation, groundbreaking development is feasible and not a feat to be done alone. For those with bold ideas, there are innumerable resources on campus to help bring those visions into reality.

For those interested in innovation but do not have the “sparks,” there are countless ways to get involved with existing projects and find one that suits your passions. Above all, those whose interest lies beyond biomedical sciences should not be discouraged: if there are current initiatives aimed at improving satellite images, there are surely many other non-biomedical endeavors for you to explore!

Let us not only celebrate what’s invented, but also the thriving spirit of invention here at Duke. Onwards!

Duke experts discuss the potential of AI to help prevent, detect and treat disease

By Robin Smith

On October 15, 2024

In Artificial Intelligence, Biomedical Engineering, Engineering, Entrepreneurship, Medicine

Sure, A.I. chatbots can write emails, summarize an article, or come up with a grocery list. But ChatGPT-style artificial intelligence and other machine learning techniques have been making their way into another realm: healthcare.

Imagine using AI to detect early changes in our health before we get sick, or understand what happens in our brains when we feel anxious or depressed — even design new ways to fight hard-to-treat diseases.

These were just a few of the research themes discussed at the Duke Summit on AI for Health Innovation, held October 9 – 11.

Duke assistant professor Pranam Chatterjee is the co-founder of Gameto, Inc. and UbiquiTx, Inc. Credit: Brian Strickland

For assistant professor of biomedical engineering Pranam Chatterjee, the real opportunity for the large language models behind tools like ChatGPT lies not in the language of words, but in the language of biology.

Just like ChatGPT predicts the order of words in a sentence, the language models his lab works on can generate strings of molecules that make up proteins.

His team has trained language models to design new proteins that could one day fight diseases such as Huntington’s or cancer, even grow human eggs from stem cells to help people struggling with infertility.

“We don’t just make any proteins,” Chatterjee said. “We make proteins that can edit any DNA sequence, or proteins that can modify other disease-causing proteins, as well as proteins that can make new cells and tissues from scratch.”

Duke assistant professor Monica Agrawal is the co-founder of Layer Health. Credit: Brian Strickland

New faculty member Monica Agrawal said algorithms that leverage the power of large language models could help with another healthcare challenge: mining the ever-expanding trove of data in a patient’s medical chart.

To choose the best medication for a certain patient, for example, a doctor might first need to know things like: How has their disease progressed over time? What interventions have already been tried? What symptoms and side effects did they have? Do they have other conditions that need to be considered?

“The challenge is, most of these variables are not found cleanly in the electronic health record,” said Agrawal, who joined the departments of computer science and biostatistics and bioinformatics this fall.

Instead, most of the data that could answer these questions is trapped in doctors’ notes. The observations doctors type into a patient’s electronic medical record during a visit, they’re often chock-full of jargon and abbreviations.

The shorthand saves time during patient visits, but it can also lead to confusion among patients and other providers. What’s more, reviewing these records to understand a patient’s healthcare history is time-intensive and costly.

Agrawal is building algorithms that could make these records easier to maintain and analyze, with help from AI.

“Language is really embedded across medicine, from notes to literature to patient communications to trials,” Agrawal said. “And it affects many stakeholders, from clinicians to researchers to patients. The goal of my new lab is to make clinical language work for everyone.”

Duke assistant professor Jessilyn Dunn leads Duke’s BIG IDEAs Lab. Credit: Brian Strickland

Jessilyn Dunn, an assistant professor of biomedical engineering and biostatistics and bioinformatics at Duke, is looking at whether data from smartwatches and other wearable devices could help detect early signs of illness or infection before people start to have symptoms and realize they’re sick.

Using AI and machine learning to analyze data from these devices, she and her team at Duke’s Big Ideas Lab say their research could help people who are at risk of developing diabetes take action to reverse it, or even detect when someone is likely to have RSV, COVID-19 or the flu before they have a chance to spread the infection.

“The benefit of wearables is that we can gather information about a person’s health over time, continuously and at a very low cost,” Dunn said. “Ultimately, the goal is to provide patient empowerment, precision therapies, just-in-time intervention and improve access to care.”

Duke associate professor David Carlson. Credit: Brian Strickland

David Carlson, an associate professor of civil and environmental engineering and biostatistics and bioinformatics, is developing AI techniques that can make sense of brain wave data to better understand different emotions and behaviors.

Using machine learning to analyze the electrical activity of different brain regions in mice, he and his colleagues have been able to track how aggressive a mouse is feeling, and even block the aggression signals to make them more friendly to other mice.

“This might sound like science fiction,” Carlson said. But Carlson said the work will help researchers better understand what happens in the brains of people who struggle with social situations, such as those with autism or social anxiety disorder, and could even lead to new ways to manage and treat psychiatric disorders such as anxiety and depression.

Following the people and events that make up the research community at Duke

Tag: Pratt School of Engineering

‘Design Climate’ Students Pitch Solutions at Energy Week 2024

Invented at Duke, Inspired at Duke

Duke experts discuss the potential of AI to help prevent, detect and treat disease