When you walk through a museum, the path you take feels natural — guided by curiosity, aesthetics, and maybe a helpful app. But behind the scenes, that journey is shaped by decisions about layout and design that can make or break your experience. Research by Abhishek Deshmane, assistant professor of operations management, reveals how data-driven models can help cultural institutions — and other experience-based businesses — optimize these layouts to boost engagement.

Read more » 

Georgia Tech’s Institute for Matter and Systems (IMS) hosted its second Boundaries and Breakthroughs panel on Jan. 27, bringing together leading clinicians, engineers, and data experts to examine why promising medical technologies often fail to translate into clinical practice.

Moderated by IMS Executive Director Eric Vogel, the panel explored how innovation, regulation, economics and clinical realities intersect to shape the future of medical devices. 

The panel featured John Duke, physician and director of the Center for Health Analytics and Informatics at Georgia Tech Research Institute; Matthew Flavin, assistant professor in the School of Electrical and Computer Engineering; HyunJoo Oh, assistant professor in the schools of Industrial Design and Interactive Computing; and Lokesh Guglani, pediatric pulmonologist and clinician-researcher at Children’s Healthcare of Atlanta. 

Vogel opened the event by highlighting the gap between technological novelty and real-world medical adoption. 

“About 75% of medical device start-ups never achieve commercial success or make it to market, and some industry estimates push this higher,” Vogel said. “Even those that reach the market often fail to gain meaningful adoption. This may be because technologists optimize for platforms five or 10 years out and are rewarded by novelty, whereas clinicians demand reliability, interpretability, and outcomes that hold up with real patients, real workflows, and real liability.”

Throughout the discussion, panelists examined the tension between rapid innovation and clinical safety, noting that the level of invasiveness often determines how bold developers can be.

“We must remember that in medicine—and especially when we're dealing with human lives—there's a significant asymmetry of the harm that could be done,” said Guglani. “Even a small change or an oversight at the design level of a medical device can have significant downstream repercussions for patients and create liability for institutions and providers.”

Flavin and Duke added that excessive conservatism, particularly around non-invasive wearable, can also slow potentially life-changing advancements. 

All panelists agreed that breakthrough technology alone is not enough to ensure clinical adoption. Usability, workflow fit, and time efficiency often determine whether clinicians adopt a device. Tools that require lengthy calibration or add to a clinician’s already tight schedule rarely succeed. Even when a technology integrates well, reimbursement barriers can prevent adoption. 

 “A lot of technologies come out, but then if the clinic is using them and is not being reimbursed for the time spent, that creates a bottleneck,” said Guglani.

Economic constraints also shape who benefits from innovation. Children with rare diseases, stroke survivors, and other small or heterogeneous patient groups often struggle to attract investors, even when their needs are urgent.

The panelists also discussed the dual role of regulatory and manufacturing standards. Good Manufacturing Practice (GMP) requirements ensures consistent, safe production, but force teams to lock designs earlier than ideal, adding cost and slowing iteration. These requirements protect patients but also function as an economic filter for many early-stage technologies.

The conversation then turned to data, AI, and the education of future innovators. Despite massive amounts of health data, many clinically important areas remain data‑scarce. Wearable devices, such as smart watches, may help close these gaps, but AI models remain limited by the quality of input data. 

When asked about preparing the next generation of MedTech innovators, panelists emphasized the importance of “interface literacy” or the ability to collaborate across disciplinary boundaries and understand how design decisions cascade into real clinical environments.  

“You really do have to be able to be interdisciplinary,” said Duke. “Now of course what makes things go is not often the knowledge of the domain, but the person’s role or connectivity into the system.”

Vogel closed by emphasizing that successful medical technology development requires “ongoing, honest collaboration” across fields. The Boundaries and Breakthroughs series will continue that mission in February with a panel on the future of the electric grid.

While not as highlight-reel worthy as the Winter Olympics and the World Cup, experts expect high-performance computing (HPC) to have an even bigger impact on daily life in 2026.

Georgia Tech researchers say HPC and artificial intelligence (AI) advances this year are poised to improve how people power their homes, design safer buildings, and travel through cities.

According to Qi Tang, scientists will take progressive steps toward cleaner, sustainable energy through nuclear fusion in 2026. 

“I am very hopeful about the role of advanced computing and AI in making fusion a clean energy source,” said Tang, an assistant professor in the School of Computational Science and Engineering (CSE). 

“Fusion systems involve many interconnected processes happening across different scales. Modern simulations, combined with data-driven methods, allow us to bring these pieces together into a unified picture.”

Tang’s research connects HPC and machine learning with fusion energy and plasma physics. This year, Tang is continuing work on large-scale nuclear fusion models.

Only a few experimental fusion reactors exist worldwide compared to more than 400 nuclear fission reactors. Tang’s work supports a broader effort to turn fusion from a promising idea into a practical energy source.

Nuclear fusion occurs in plasma, the fourth state of matter, where gas is heated to millions of degrees. In this extreme state, electrons are stripped from atoms, creating a hot soup of fast-moving ions and free electrons. In plasma, hydrogen atoms overcome their natural electrical repulsion, collide, and fuse together. This releases energy that can power cities and homes.

Computers interpret extreme temperatures, densities, pressures, and plasma particle motion as massive datasets. Tang works to assimilate these data types from computer models and real-world experiments.

To do this, he and other researchers rely on machine learning approaches to analyze data across models and experiments more quickly and to produce more accurate predictions. Over time, this will allow scientists to test and improve fusion reactor designs toward commercial use. 

Beyond energy and nuclear engineering, Umar Khayaz sees broader impacts for HPC in 2026.

“HPC is the need of the day in every field of engineering sciences, physics, biology, and economics,” said Khayaz, a CSE Ph.D. student in the School of Civil and Environmental Engineering. 

“HPC is important enough to say that we need to employ resources to also solve social problems.”

Khayaz studies dynamic fracture and phase-field modeling. These areas explore how materials break under sudden, rapid loads. 

Like nuclear fusion, Khayaz says dynamic fracture problems are complex and data-intensive. In 2026, he expects to see more computing resources and computational capabilities devoted to understanding these problems and other emerging civil engineering challenges.

CSE Ph.D. student Yiqiao (Ahren) Jin sees a similar relationship between infrastructure and self-driving vehicles. He believes AI will innovate this area in 2026.

At Georgia Tech, Jin develops efficient multimodal AI systems. An autonomous vehicle is a multimodal system that uses camera video, laser sensors, language instructions, and other inputs to navigate city streets under changing scenarios like traffic and weather patterns.

Jin says multimodal research will move beyond performance benchmarks this year. This shift will lead to computer systems that can reason despite uncertainty and explain their decisions. In result, engineers will redefine how they evaluate and deploy autonomous systems in safety-critical settings.

“Many foundational problems in perception, multimodal reasoning, and agent coordination are being actively addressed in 2026. These advances enable a transition from isolated autonomous systems to safer, coordinated autonomous vehicle fleets,” Jin said. 

“As these systems scale, they have the potential to fundamentally improve transportation safety and efficiency.”

Georgia residents now have a new way to compare the estimated costs paid for a large variety of health care services in the state, thanks to a searchable “shop for care” resource launched as part of the Georgia All-Payer Claims Database (GA APCD).
 

The Georgia APCD Cost Comparison Tool (apcd.georgia.gov/cost-comparison-tool) contains information on more than 200 different medical procedures ranging from cardiac stress tests and childbirth to knee replacement and colonoscopies. The resource provides information on the median cost paid for the procedures statewide, along with information on what individual medical facilities and professional providers have been paid for each type of procedure. 
 

For each procedure, the tool identifies medical facility providers nearest to the consumer, and includes facility ratings collected by the Centers for Medicare & Medicaid Services (CMS). For each facility providing a specific service, the comparison data includes the median cost for the procedure and the range of costs that were paid. Costs can be filtered by payer category, including commercial, Medicare, and Medicaid. While that data is understandably incomplete and includes caveats, developers of the new service say it provides a much-needed resource for Georgians facing a decision on a costly medical procedure.
 

“In health care, there are a lot of factors that can drive cost and it’s not always a straightforward equation, so it’s worth doing the research,” said Dr. Jon Duke, an M.D. and principal research scientist in the Georgia Tech Research Institute’s (GTRI) Health Emerging and Advanced Technologies Division, which administers the APCD for the state of Georgia. “This is really just one part of health care decision-making, and it will help patients be more proactive advocates for themselves when considering potential options for care.”
 

Read more about this project on the GTRI home page