The authors show that existing regulatory requirements for approval have so far only partially addressed many of these so-called “human factors-related risks”. This can create gaps that impact the safety and quality of care. To address these, the researchers identify seven key risks and develop practical recommendations for action that can be integrated into existing regulatory and documentation processes.

Risks in the use of AI systems

AI-based medical devices can be used in various areas of clinical environments. In radiology, for example, they assist in detecting cancer. Clinical decision support systems help select personalized therapies for patients.  AI can also support real-time monitoring and early warning systems, as well as chatbots for applications such as patient communication and software that automatically generate medical reports or summarize findings. The analysis focuses on risks that may arise in the practical use of such AI systems. These include, for example, an increased likelihood of outputs being misunderstood or misinterpreted due to the sometimes-opaque nature of AI systems. Problems can also occur when trust in the application is miscalibrated: resulting in users either relying too heavily on AI assistance or ignoring relevant recommendations. The researchers also point to the risk of automation bias: the tendency to uncritically adopt recommendations from automated systems, potentially overlooking errors or forgoing independent judgment. Additional risks include potential deskilling, technostress among users, an unchecked expansion of indications beyond the originally intended scope (indication creep), and errors related to system changes or different operating modes. Such factors can create additional burdens or unexpected failures in clinical practice – even when the technical performance of a system itself is strong.

A practical guide for manufacturers and evaluators

For their analysis, the research team evaluated existing standards on usability and safety, regulatory guidelines, alongside the scientific literature on AI in healthcare. In addition, expert discussions from the fields of clinical application, regulation, and human factors were incorporated. The result is a practical guide, that fills a gap in current standards, with seven recommendations. These are intended to support manufacturers and evaluators both before and after a product is placed on the market. The aim is to identify AI-specific risks in interaction with human users at an early stage and to address them systematically.

The framework recommends developing and deploying AI-based medical devices in a way that clearly defines the users, in which context the systems are applied, and which tasks are assigned to humans and which to the system. Furthermore, results should be presented in a way that is easy to understand, integrated into existing clinical workflows, and supplemented by training where needed as well as safe fallback options in the event of system failures. The authors emphasize the importance of continuous monitoring after market entry. Usage patterns, potential misuse, or overreliance on AI systems should be systematically observed and corrected as needed. Changes to the systems must also be communicated transparently so that work processes can be adjusted accordingly.

The recommendations are deliberately formulated in general but regulatory-aligned terms so that they can be applied to different AI-enabled medical devices and application scenarios. In a next step, the researchers aim to test and further develop their recommendations based on concrete pilot applications with AI-enabled medical devices. In the long term, human factors should be systematically considered in the regulation and evaluation of AI-based health technologies – reducing avoidable risks while supporting safe innovation in medicine.

The article was authored by researchers from TU Dresden (EKFZ for Digital Health, Chair of Industrial Design Engineering, and Faculty of Business and Economics), in collaboration with experts from the University of Oxford (United Kingdom) and Geneva University Hospital (Switzerland).

Publication

Rebecca Mathias, Anne Schmitt, Mateo Campos, Baptiste Vasey, Sebastian Lorenz, Peter McCulloch, Stephen Gilbert: Evaluation of Human Factors-Related Risks in AI-Enabled Medical Devices: A Practical Guide, NEJM AI, 2026. Link: https://ai.nejm.org/doi/full/10.1056/AIpc2501297

Else Kröner Fresenius Center (EKFZ) for Digital Health

The EKFZ for Digital Health at the Faculty of Medicine at TUD Dresden University of Technology and University Hospital Carl Gustav Carus Dresden was established in September 2019. It receives funding of around 40 million euros from the Else Kröner Fresenius Foundation for a period of ten years. The center focuses its research activities on innovative, medical and digital technologies at the direct interface with patients. The aim here is to fully exploit the potential of digitalization in medicine to significantly and sustainably improve healthcare, medical research and clinical practice.

The World Health Organization estimates that 1 in 10 medications ranging from cancer treatment to contraceptives are either fake or otherwise “substandard.” Though this primarily affects the developing world, there are also gray markets for weight-loss or anti-aging drugs in the U.S.

“Watered-down or illicit versions of drugs like Botox or popular GLP-1 inhibitors have caused serious injuries or death,” said William Grover, associate bioengineering professor at the University of California, Riverside.

In response to this problem, Grover’s laboratory has developed a fake drug detector that could be manufactured for under $30, and potentially for as little as $5. Open-source plans to build the device are detailed in a new paper in the journal Analytical Chemistry.

At its core is a low-cost infrared sensor made for use in toy robots able to follow lines drawn on paper. The researchers repurposed the sensors to instead track the rate at which pills dissolve in water.

All pills of a given drug dissolve — or should dissolve — at roughly the same rate.  Legitimate medications don’t necessarily dissolve any faster or slower than counterfeit ones. But they were made by different people at different facilities and with different ingredients, so their dissolution rates form a “fingerprint” that makes them identifiable and different from that of a fake drug.

“The theory here is that if it’s a legitimate medicine, the manufacturer made every pill identical enough that they’ll all behave roughly the same way when they dissolve,” Grover explained. “So if you test a suspect pill, and it dissolves at a different rate than the real thing, this suggests the suspect pill is counterfeit.”

While others have used dissolution rates to determine a medication’s legitimacy, Grover’s laboratory made the tests more sophisticated by creating an electronic device that converts a pill’s dissolution into a digital signature that they call a “disintegration fingerprint.”

After designing the device, the researchers sought to create a library of these fingerprints that could be used to identify a suspect pill. The group tested over 30 different medications ranging from antibiotics and vitamin supplements to prescription opioids and over-the-counter painkillers. They found that 90% of these pills could be correctly identified using the fingerprinting method.

The group also tested whether their technique could distinguish name-brand and generic versions of the same drug.

“We took Bayer aspirin pills and drug-store-brand aspirin — these are basically identical medicines with the same active ingredient and very similar inactive ingredients,” Grover said, “but when ran through our tests, we could easily tell the difference between the two products.”

The research team even recruited their friends and family to collect samples of drug products from across the U.S. and Canada. They found that pills of the same product typically have similar disintegration fingerprints regardless of where they were purchased. However, some manufacturers make slightly different versions of products for different countries and fingerprinting successfully distinguished U.S. and Canadian versions of a product.

Though there are high-quality pharmaceuticals widely available in the U.S., the CDC warns that there is a public health risk for people ordering what they believe to be prescription medications from disreputable online pharmacies. These medications are frequently found to be fakes.

Other times, a medication could contain irregularities because of manufacturing mistakes. “A facility could get a drum of mislabeled ingredients that can get incorporated into the medicine,” Grover said. “But even an honest error can lead to death.”

In the future, Grover would like to use this method to detect fake antimalarial drugs. These are drugs that treat malaria, a major cause of death in many tropical regions.  Malaria is treatable with the right medications.

“Unfortunately, bad actors know they can make money preying on the need for antimalarials. They sell pills that have the same packaging as authentic antimalarials, but  don’t contain the active ingredients,” Grover said. “If someone gives these pills to their child, they won’t cure their infection.”

Grover hopes to get his tool into the hands of those who can use it to fight fake antimalarials and other fake drugs.

“I can’t imagine a more despicable person than someone who would sell fake medicine to a child. I hope our work makes those criminals’ lives a little harder.”

Image: By counting the particles formed when a pill dissolves in a water-filled cup, the team’s device can identify fake medications.

View more Credit: William Grover/UCR

The researchers in the School of Pharmacy have created a customizable wound scaffold that delivers natural, biodegradable antibacterials over time to encourage healing. Researchers Michael Repka, distinguished professor of pharmaceutics and drug delivery; Sateesh Vemula, postdoctoral researcher; and doctoral candidate Nouf Alshammari published their results in the European Journal of Pharmaceutics and Biopharmaceutics.

“People with limited mobility or diabetes often have wounds with reduced oxygen supply,” Vemula said. “This can slow the body’s normal repair process and make wounds more likely to become long-lasting, while also increasing the chance that bacteria can grow and lead to infection.”

Chronic wounds, including diabetic ulcers and pressure sores, can linger for months or even years.

Repka and his team are 3D-printing a breathable, patch-like structure that can be placed over the wound. The patch is made using chitosan – a natural material found in crustaceans, insects and fungi – along with plant-derived antimicrobials that help fight germs. Chitosan helps accelerate the growth of skin cells while reducing inflammation and preventing infection.

This structure acts as a scaffold, encouraging growth while also protecting the wound from outside sources of infection or contamination.

“A lot of bandages are made with organic solvents, which actually hurt the wound-healing process, especially when applied intimately on the wound,” Repka said. “With the materials and technique we’re using, you don’t have organic solvents.

“We’re also not using traditional antibiotics over a long period of time, because that can often cause the bacteria to become resistant. That’s the advantage of using natural products.”

Using a 3D printer to create the scaffold means that the patch can be tailored to fit any wound on any part of the body.

“The materials we used are also biodegradable,” Alshammari said. “With time, the scaffold is going to be absorbed into the skin. And it’s an inactive material, so we don’t have to worry about side effects or toxic residuals.”

Being biodegradable also means that if the material is applied to wounds inside the body, health care professionals don’t have to make a second incision to remove it, Vemula said.

The technology can be applied to other types of wounds where a traditional bandage would not be suitable, the Ole Miss researchers said.

“Depending on what kind of wound it is, a regular bandage might work well and this wouldn’t be necessary,” Repka said. “But there are a lot of applications for this technology. These could be printed in the field for, say, military applications.

“If you have a generator that can run these 3D printers, you can print the scaffold you need based on what kind of wound has occurred.”

Before the scaffold can be used clinically, it will need further testing and review by the Food and Drug Administration.

“The goal is translating this from research to patients,” Repka said.

Image: Michael Repka, distinguished professor of pharmaceutics and drug delivery, works with a 3D-printed medical device in his lab in Shoemaker Hall. Repka’s latest research shows that 3D-printed wound scaffolding could aid in healing chronic wounds. 

View more Credit: Photo by Thomas Graning/Ole Miss Digital Imaging Services

A new study, published in the March 9 online issue of npj Health Systems [https://doi.org/10.1038/s44401-026-00077-0], suggests that the answer depends less on the AI itself and more on how it’s designed.

The investigators found that health care AI systems work far better when tasks are distributed among multiple specialized AI “agents”—software systems that can perform complex tasks, learn, and adapt—rather than relying on a single, all-purpose agent. This multi-agent approach kept performance steady even as demands increased, while dramatically reducing computing costs and delays, say the investigators.

“For health care organizations, our findings point to a smarter way to use AI,” says senior study author Girish N. Nadkarni, MD, MPH, Barbara T. Murphy Chair of the Windreich Department of Artificial Intelligence and Human Health, Director of the Hasso Plattner Institute for Digital Health, Irene and Dr. Arthur M. Fishberg Professor of Medicine at the Icahn School of Medicine, and Chief AI Officer of the Mount Sinai Health System. “By assigning different tasks, such as finding patient information, extracting data, or checking medication doses, to specialized AI agents, systems can run faster and more reliably while keeping costs under control. Ultimately, this kind of design could help health care teams spend less time on administrative work and more time focusing on patients.”

As part of the study, the researchers compared two approaches to clinical AI: a single system responsible for handling many different clinical tasks, and a coordinated network of specialized AI agents overseen by a central “orchestrator.” Using state-of-the-art language models, the team evaluated performance across common clinical functions, including information retrieval, data extraction, and medication dosing calculations—under simulated real-world conditions involving up to 80 simultaneous tasks.

“What we found is that AI systems behave a lot like people,” says study lead author Eyal Klang, MD, formerly with the Icahn School of Medicine. “When you ask one system to do too many different things at once, performance suffers. But when one orchestrator agent divides the work among specialized agents, the system stays accurate, responsive, and far more efficient, even under heavy demand.”

The coordinated multi-agent system maintained superior accuracy levels while using far fewer computing resources, up to 65 times fewer, than a single-agent design. The study simulated real clinical “traffic,” where many types of tasks arrive at once and compete for attention, the investigators say.

“Our findings show that smart coordination is not just a technical preference,” Dr. Klang says. “It can make the difference between an AI system that continues to function smoothly and one that begins to break down when it is exposed to the pressures of real clinical workloads.”

Next, the research team plans to test these coordinated AI systems directly in clinical settings, using real-time patient data. If successful, this approach could help shape how hospitals and health systems scale AI in the future, helping them handle peak workloads without sacrificing quality or safety.

The researchers emphasize that the gains are not automatic: even sophisticated AI can fall short when systems are poorly designed or implemented. “Health care does not operate one task at a time,” Dr. Nadkarni says. “Hospitals face constant, overlapping demands, especially during busy periods. Our findings show that the future of health care AI is not a single super-intelligent system, but a coordinated team of focused agents that work together to scale safely, control costs, and support real clinical operations.”

“When a single agent handles everything, you can’t trace where it went wrong. With the orchestrator, every step is logged, which tool was called, what it returned, and how the answer was assembled. At 80 simultaneous tasks, the single agent dropped to 16 percent accuracy while burning 65 times more compute—and you’d have no way to figure out why. That kind of transparency isn’t optional in medicine,” says second author Mahmud Omar, MD, a visiting researcher in the Windreich Department. “This matters more now than ever—agentic AI is no longer a research concept. Tools like OpenAI’s operator mode, Claude’s Cowork, and similar platforms are putting autonomous agents directly in the hands of clinicians and patients. As that adoption accelerates, the architecture behind these systems has to be auditable from the start.”

The paper is titled “Orchestrated multi agents sustain accuracy under clinical‑scale workloads compared to a single agent.”

The study’s authors, as listed in the journal, are Eyal Klang, Mahmud Omar, Ganesh Raut, Reem Agbareia, Prem Timsina, Robert Freeman, Lisa Stump, Alexander Charney, Benjamin S. Glicksberg, Girish N. Nadkarni.

This work was supported  in part by the Clinical and Translational Science Awards (CTSA) grant UL1TR004419 from the National Center for Advancing Translational Sciences. Research reported in this publication was also supported by the Office of Research Infrastructure of the National Institutes of Health under award number S10OD026880 and S10OD030463.

For more Mount Sinai artificial intelligence news, visit: https://icahn.mssm.edu/about/artificial-intelligence.

In a new study published in Proceedings of the National Academy of Sciences, the team directly measured how water interactions influence nanoparticle biological performance.

“Water is necessary for all life,” said Navrotsky, the lead author of the study, Regents Professor in the School of Molecular Sciences and director of Arizona State University’s Center for Materials of the Universe. “And in medicine, it is the first molecule that interacts with any nanoparticle surface in a biological environment. By directly measuring the energetics of water adsorption, we can quantify the interaction potential of the nanoparticle surface and better predict how it will behave in the body.”

This so-called hydration energetics were measured for a series of biomolecule-coated magnetite nanoparticles, revealing how different surface coatings alter water interactions, immune recognition and drug delivery potential.

The study, led by Navrotsky and ASU scientists including first author Kristina Lilova, Tamilarasan Subramani, Isabella Montini, Anne Harrison, Manuel Scharrer, Jun Wu and Hongwu Xu, provides the first quantitative, thermodynamic framework linking how primary water energetics relate to nanoparticle biological performance.

Why water matters

Despite major efforts, the promise of nanomedicine has largely failed to deliver a new generation of better drugs to treat illness and disease. This has been mainly due to the human body, which has provided a formidable maze of barriers and defenses for scientists to overcome to deliver the right drug to the right target at the right time.

That’s also why cancer chemotherapy has had its long-known severe side effects, delivering unwanted toxins throughout the body while trying to kill the tumor.

Therefore, scientists have been hard at work to develop a Trojan horse type of nanomedicine therapy by surrounding drugs within a protective cage of nanoparticles.

But there are huge, unresolved challenges.

These nanoparticles, designed for drug delivery, imaging and therapeutic applications must first function in complex biological fluids such as blood, gut or brain fluids after being swallowed. Once introduced into the body, nanoparticles are immediately surrounded by water molecules and biomolecules, forming a nanocomplex stew that dictates their stability, circulation time, immune response and cellular uptake.

Despite the central role of hydration in nanomedicine, previous research had not directly measured the energetics of water adsorption on biomolecule-coated magnetic nanoparticles.

Getting to the core of the problem

The ASU team addressed this gap by studying core–shell nanocomplexes composed of magnetite (iron oxide) cores coated with three representative biomolecules: a protein (bovine serum albumin), a polysaccharide (potato starch) and a fatty acid (lauric acid).

Using a highly sensitive calorimetry–gas adsorption system, the researchers measured the energetics of water adsorption on dry coated nanoparticles, their hydrophilic area and interaction potential, and compared the results to free biomolecules and uncoated magnetite.

The results showed that each coating dramatically alters the hydration behavior—and the biological interaction potential of the nanocomplex.

Patchy protein power

The first experiment of used a nanoparticle coated with a protein, bovine serum albumin (BSA), commonly used as a model for human serum albumin in drug delivery research. Overall, the protein coating produced the strongest initial interaction with water when coated onto magnetite nanoparticles. The BSA-coated particles exhibited strong binding sites exposed at the surface.

However, the total water uptake was lower than that of free BSA, revealing incomplete surface coverage and the presence of uncoated magnetite patches.

“The protein coating increases the surface interaction potential of the nanocomplex,” Lilova explained. “But the existence of exposed magnetite regions introduces heterogeneity that may promote protein corona formation and immune recognition.”

But such “patchiness” could favor the adsorption of opsonins—proteins that tag foreign particles for immune clearance—potentially reducing circulation lifetime.

A starch shell

In contrast, the starch-coated magnetite exhibited a large, water-loving (hydrophilic) surface area, but weaker interaction potential compared to free starch.

The researchers found that starch chains bind to the magnetite surface via hydroxyl groups, reducing the number of groups available for water interaction. Transmission electron microscopy revealed a dense encapsulating shell, limiting accessibility to external water molecules.

“The weaker interaction potential of the starch coating and its relatively large hydrophilic surface area suggest more dynamic and reversible binding,” Lilova said. “This may be beneficial in drug delivery, where mobility along cell membranes and reduced cytotoxicity are desirable.”

Such reversible interactions may allow nanoparticles to engage cell membranes without causing significant disruption—an important consideration for biocompatibility.

Fatty flavor

Perhaps the most striking finding involved lauric acid, a fatty acid coating. Free crystalline lauric acid does not adsorb water, because as any cook knows, water and fatty oils do not mix.  However, when coated onto magnetite nanoparticles, the fat coating reorganized into a partial bilayer structure, resulting in strong water interaction and a stable hydrated interfacial layer.

“The fatty acid rearranges into a partial bilayer with very strong hydrophilicity,” said Lilova. “That structure increases stability and may reduce immune activation compared to more hydrophobic surfaces.”

The bilayer arrangement may also promote longer circulation times in the body.

A better framework for nanomedicine

Across all three coatings, the study establishes that the science of water energetics (hydration enthalpy) can be a key thermodynamic parameter that reflects surface hydrophilicity, heterogeneity and biological interaction potential.

The results from the three coating may help the scientists with a “Goldilocks” predictive tool for getting nanoparticle design “just right.”

“Our findings show that surface functionalization doesn’t just change chemistry—it fundamentally alters the thermodynamic landscape at the nano-bio interface,” said Lilova.

“By understanding primary hydration energetics, we can rationally engineer nanocarriers with tailored stability, immune interactions and drug delivery behavior.”

Looking ahead

The work has broad implications for the design of nanomedicines used in applications such as targeted drug delivery, body imaging contrast agents, cancer treatments and biosensing applications.

“This research provides a thermodynamic foundation for designing nanocarriers with predictable biological reactivity,” said Navrotsky. “It moves us one step closer to truly rational nanomedicine.”

As nanomedicine research continues to evolve, hydration energetics may become a central tool in engineering safer, longer circulating and more effective nanoparticle therapies that could one day save lives. The work also provided a stepping stone for future research focused on the direct measurements of the stabilization effect of representative biomolecular coatings on the nanocomplex.

The research was supported by the U.S. Department of Energy and conducted at Arizona State University’s Center for Materials of the Universe, led by Navrotksy.

Using a large language model (LLM), the MIT team analyzed the genetic code of the industrial yeast Komagataella phaffii — specifically, the codons that it uses. There are multiple possible codons, or three-letter DNA sequences, that can be used to encode a particular amino acid, and the patterns of codon usage are different for every organism.

The new MIT model learned those patterns for K. phaffii and then used them to predict which codons would work best for manufacturing a given protein. This allowed the researchers to boost the efficiency of the yeast’s production of six different proteins, including human growth hormone and a monoclonal antibody used to treat cancer.

“Having predictive tools that consistently work well is really important to help shorten the time from having an idea to getting it into production. Taking away uncertainty ultimately saves time and money,” says J. Christopher Love, the Raymond A. and Helen E. St. Laurent Professor of Chemical Engineering at MIT, a member of the Koch Institute for Integrative Cancer Research, and faculty co-director of the MIT Initiative for New Manufacturing (MIT INM).

Love is the senior author of the new study, which appears this week in the Proceedings of the National Academy of Sciences. Former MIT postdoc Harini Narayanan is the paper’s lead author.

Codon optimization

Yeast such as K. phaffii and Saccharomyces cerevisiae (baker’s yeast) are the workhorses of the biopharmaceutical industry, producing billions of dollars of protein drugs and vaccines every year.

To engineer yeast for industrial protein production, researchers take a gene from another organism, such as the insulin gene, and modify it so that the microbe will produce it in large quantities. This requires coming up with an optimal DNA sequence for the yeast cells, integrating it into the yeast’s genome, devising favorable growth conditions for the it, and finally purifying the end product.

For new biologic drugs — large, complex drugs produced by living organisms — this development process might account for 15 to 20 percent of the overall cost of commercializing the drug.

“Today, those steps are all done by very laborious experimental tasks,” Love says. “We have been looking at the question of where could we take some of the concepts that are emerging in machine learning and apply them to make different aspects of the process more reliable and simpler to predict.”

In this study, the researchers wanted to try to optimize the sequence of DNA codons that make up the gene for a protein of interest. There are 20 naturally occurring amino acids, but 64 possible codon sequences, so most of these amino acids can be encoded by more than one codon. Each codon corresponds to a unique transfer RNA (tRNA) molecule, which carries the correct amino acid to the ribosome, where amino acids are strung together into proteins.

Different organisms use each of these codons at different rates, and designers of engineered proteins often optimize the production of their proteins by choosing the codons that occur the most frequently in the host organism. However, this doesn’t necessarily produce the best results. If the same codon is always used to encode arginine, for example, the cell may run low on the tRNA molecules that correspond to that codon.

To take a more nuanced approach, the MIT team deployed a type of large language model known as an encoder-decoder. Instead of analyzing text, the researchers used it to analyze DNA sequences and learn the relationships between codons that are used in specific genes.

Their training data, which came from a publicly available dataset from the National Center for Biotechnology Information, consisted of the amino acid sequences and corresponding DNA sequences for all of the approximately 5,000 proteins naturally produced by K. phaffii.

“The model learns the syntax or the language of how these codons are used,” Love says. “It takes into account how codons are placed next to each other, and also the long-distance relationships between them.”

Once the model was trained, the researchers asked it to optimize the codon sequences of six different proteins, including human growth hormone, human serum albumin, and trastuzumab, a monoclonal antibody used to treat cancer.

They also generated optimized sequences of these proteins using four commercially available codon optimization tools. The researchers inserted each of these sequences into K. phaffii cells and measured how much of the target protein each sequence generated. For five of the six proteins, the sequences from the new MIT model worked the best, and for the sixth, it was the second-best.

“We made sure to cover a variety of different philosophies of doing codon optimization and benchmarked them against our approach,” Narayanan says. “We’ve experimentally compared these approaches and showed that our approach outperforms the others.”

Learning the language of proteins

K. phaffii, formerly known as Pichia pastoris, is used to produce dozens of commercial products, including insulin, hepatitis B vaccines, and a monoclonal antibody used to treat chronic migraines. It is also used in the production of nutrients added to foods, such as hemoglobin.

Researchers in Love’s lab have started using the new model to optimize proteins of interest for K. phaffii, and they have made the code available for other researchers who wish to use it for K. phaffii or other organisms.

The researchers also tested this approach on datasets from different organisms, including humans and cows. Each of the resulting models generated different predictions, suggesting that species-specific models are needed to optimize codons of target proteins.

By looking into the inner workings of the model, the researchers found that it appeared to learn some of the biological principles of how the genome works, including things that the researchers did not teach it. For example, it learned not to include negative repeat elements — DNA sequences that can inhibit the expression of nearby genes. The model also learned to categorize amino acids based on traits such as hydrophobicity and hydrophilicity.

“Not only was it learning this language, but it was also contextualizing it through aspects of biophysical and biochemical features, which gives us additional confidence that it is learning something that’s actually meaningful and not simply an optimization of the task that we gave it,” Love says.

###

The research was funded by the Daniel I.C. Wang Faculty Research Innovation Fund at MIT, the MIT AltHost Research Consortium, the Mazumdar-Shaw International Oncology Fellowship, and the Koch Institute.

The global scoping review looked at this early phase of testing and revealed huge variations in the way the trials are being conducted and the measures used to assess the effectiveness of the tools.

“This lack of guidance around silent trials is concerning as AI models can be unpredictable and difficult to use in real-world settings if they haven’t been tested thoroughly,” said corresponding author Lana Tikhomirov, a PhD candidate from Adelaide University’s Australian Institute for Machine Learning.

“Some of the trials in our review focused on AI metrics that weren’t clinically useful, while others looked at the bare minimum with no details on how the model performed in a clinical setting.

“If these AI tools are rolled out without comprehensive testing and things go wrong, it could expose both patients and clinicians to harmful advice.”

Silent trials are when AI models are tested in their intended setting for use, but the results don’t influence patient care as they aren’t given to the clinical team at the time of treatment.

Currently there are no formal guidelines on how to conduct these trials, which researchers say are critical to ensure an AI tool will be useful and beneficial in a local setting.

“Silent trials are a low-risk way to test technology without compromising patient outcomes,” said co-author Associate Professor Melissa McCradden, who is the Deputy Director of Adelaide University’s Australian Institute for Machine Learning, AI Director at the Women’s and Children’s Health Network and Hospital Research Foundation Fellow in Paediatric AI Ethics.

“We know that many AI models fail when they’re introduced into real-world settings and an AI tool that works in one hospital may not work in another.

“Conducting comprehensive silent trials that adhere to a clear set of international guidelines is critical if we want to successfully take AI tools from bench to bedside.”

The scoping review has been published in Nature Health and is part of a larger study looking at silent phase evaluations for healthcare AI.

Project CANAIRI – Collaboration for Translational Artificial Intelligence Trials – is focusing on developing guidance for silent trials to ensure health settings in which AI is intended to be used are ready and able to do so in a beneficial way.

“Ultimately, we would like to see silent trials become a mandatory part of the process of adopting AI tools in medicine,” said Associate Professor McCradden, who is the lead of Project CANAIRI.

An interdisciplinary George Mason University team led by Farrokh Alemi, an expert in machine-learning and AI, compared how effective recommendations were from AI-guided tools/models that knew the patient’s race and factors uniquely relevant to African American patients against tools/models that didn’t. The team found that recommendations based on “race-blind” AI models—those that do not know the patient’s race—tended to recommend medications that were less effective for African American patients.

“Anti-depressant recommendations from race-specific models outperformed recommendations from general models across all antidepressants studied. The findings highlight why clinical AI, like clinical practice, shouldn’t rely solely on general-population patterns when prescribing for African Americans with depression,” said Vladimir Cardenas, master of science in health informatics ’24.

Why This Matters

“If AI systems are not trained on correct information, including patient demographic information, such as race, it will give incorrect or inaccurate information, which can result in people ending up with less effective medications,” said Alemi.

Alemi and his co-researchers observed that when advising patients on options for treating depression. “AI systems could be biased against African Americans, recommending antidepressants that work for general, mostly White, patients but not for African Americans,” said Alemi.

The Details

Researchers looked at bias in an AI system meant to guide treatment for Major Depressive Disorder (MDD)—and whether race-blind models miss important signals for African American patients. The AI system used medical history—including whether a patient completed the full dose of the antidepressant—to recommend a medication. Researchers coded whether a patient discontinued the use of the antidepressant as a measure of AI-guided treatment failure or success.

The study underscores that race is not a biological determinant of depression or treatment response, emphasizing the social and environmental factors that affect depression. Some of these factors more common among African American patients may be poverty, low education, exposure to violence, discrimination, cultural stigma and negative attitudes toward mental health, and low access to mental health treatment resources.

“These data highlight the need to tailor antidepressants to fit the patient’s individual medical history. Clinicians do this, and, if done right, an AI system can help clinicians do so as well,” said Cardenas.

“I hope that our approach will help inform AI in health care design and governance. This way we can truly pursue AI that improves the health of all,” said Cardenas.

The research team included Kevin Lybarger, assistant professor in the College of Engineering and Computing, along with master of science in health informatics graduates Cardenas, Maria Kurian, and Rachel Christine King; and Niloofar Ramezani from Virginia Commonwealth University.

Bias in AI-guided management of patients with major depressive disorders was published in the Journal of Health Equity in January 2026. The study was supported by the Artificial Intelligence/Machine Learning Consortium to Advance Health Equity and Researcher Diversity. Research was partially funded through a Patient-Centered Outcomes Research Institute (PCORI) Award.

Key Takeaways

• AI systems for antidepressant guidance may be less effective for African American patients because models use data from general, primarily White, populations.
• Race-specific models were more accurate in predicting African Americans’ responses to medications across all antidepressants studied.
• Clinical AI treating mental health shouldn’t rely solely on general population data when prescribing antidepressants for African Americans with depression.

For years, drug companies and industry allies have argued that the U.S. gets faster and wider access because its government moves quicker than foreign regulators, but the new analysis suggests the U.S. advantage in drug access is driven less by faster government review and more by when companies apply for review and the type of drugs they submit.

The study, published in Health Affairs, looked at every new prescription drug approved between 2014 and 2018 in the U.S., and Europe, and then tracked submission delays and review times for these products across regulators in Canada, Japan and Australia through the end of 2022. The analysis assessed the speed of the review process and the timing of submissions for approval, with results broken down by drug characteristics, including therapeutic value of the drugs.

Specifically, the researchers explored whether different patterns in submission and review times emerged for drugs that offered little added medical benefit over drugs that were already on the market.

“Some commentators have argued that foreign regulators take too long to review drugs and should do more to ensure timely access to new therapies, often pointing to limited availability of new cancer therapies in Europe and other rich markets relative to what’s on the market in the United States, as evidence that regulatory red tape is getting in the way of timely patient access,” said lead author Irene Papanicolas, a professor of health services, policy and practice at the Brown University School of Public Health. “Where we’re coming at this from is saying that broader availability of new medicines is generally a great thing — we want patients to get access to new meds — but not all new medications are equally important from a medical standpoint.”

In fact, what stood out most was how companies handled drugs that provide little therapeutic advantage over existing treatments, which the authors referred to as “low-value” drugs in their analysis. The researchers found these drugs were typically submitted to U.S. regulators months or even years before companies sought approval in other high-income countries, giving Americans earlier and wider access to expensive drugs that may not significantly improve patient outcomes.

The findings likely reflect a mix of business incentives and policy choices, according to the research team which along with Papanicolas and other Brown co-authors Olivier Wouters and Tania Sawaya also includes health policy experts from Vanderbilt University and the London School of Economics and Political Science.

The U.S. is the world’s largest drug market, and manufacturers can generally set prices freely when a drug launches. In contrast, many other countries evaluate how much a new drug improves health compared with existing treatments and use that information to negotiate prices or limit coverage, said Wouters, an associate professor in the Department of Health Services, Policy, and Practice.

“There are many drugs that enter the U.S. market that frankly aren’t much better than what’s already available,” Wouters said. “Companies generally seem to submit these lower-value products for approval  earlier in the United States than in other markets. This may reflect the fact that governments in other countries tend to drive a tougher bargain than U.S. payers, which could influence companies’ decisions about where and when to seek approval.”

The study also showed that drugs offering clear medical benefits over existing treatments tended to reach most high-income countries at roughly the same time. This is because drugmakers typically submit those products for approval simultaneously across the high-income countries the researchers looked at. The Food and Drug Administration was only slightly faster than its counterparts abroad in approving the drugs by a few weeks or a month on average, the researchers said.

“Historically, yes, the U.S. gets more new drugs and gets them faster than other countries but a lot of what is driving this pattern aren’t the drugs that have this meaningful therapeutic gain for patients,” Papanicolas said. “Everybody’s getting those important new drugs quickly.”

Overall, the study helps add nuance to the question of why the U.S. spends far more on prescription drugs than other high-income countries without consistently better health outcomes. It also paints a more complicated picture as policymakers debate proposals such as the “most favored nation” approach, to bring down drug spending, which proposes linking U.S. drug prices to those paid in peer countries.

“It’s not clear how this is going to work,” Papanicolas said. “How will the US authorities handle products that haven’t yet been marketed abroad? Will the policy affect where and when companies decide to submit drugs abroad? No one really knows yet.”

Amid growing adoption of new AI tools across the industry, the regulators have set out broad guidance on how the technology can be used to generate evidence, manufacture products and monitor safety.

The principles are relevant for those developing medicines, as well as for marketing authorisation applicants and holders, the regulators said in a joint statement. They will underpin future AI guidance in both jurisdictions and support enhanced international collaboration. The development of formal guidelines in the EU is already underway, building on the EMA AI reflection paper published in 2024.

‘The principles are a good showcase of how we can work together on the two sides of the Atlantic to preserve our reading role in the global innovation race, while ensuring the highest level of patient safety,’ said European Commission for Health and Animal Welfare, Olivér Várhelyi.

The European Commission’s Biotech Act proposal, published in December, notes the promise of AI as a tool to accelerate innovation. New pharmaceutical legislation, meanwhile, aims to accommodate the broader use of AI in regulatory decision-making, and creates additional possibilities for testing AI-driven methods for medicines in a controlled environment.

To realise these benefits, say regulators, AI needs to be expertly managed, including the mitigation of risks. Ethics should be at the forefront of policymaking and regulations, it noted.

As AI continues to evolve, a principles-based approach will help regulators, pharmaceutical companies and medicines developers harness the potential of these technologies while ensuring patient safety and regulatory compliance.

The new reporting system, which can be incorporated into existing pill capsules, contains a biodegradable radio frequency antenna. After it sends out the signal that the pill has been consumed, most components break down in the stomach while a tiny RF chip passes out of the body through the digestive tract.

This type of system could be useful for monitoring transplant patients who need to take immunosuppressive drugs, or people with infections such as HIV or TB, who need treatment for an extended period of time, the researchers say.

“The goal is to make sure that this helps people receive the therapy they need to help maximize their health,” says Giovanni Traverso, an associate professor of mechanical engineering at MIT, a gastroenterologist at Brigham and Women’s Hospital, and an associate member of the Broad Institute of MIT and Harvard.

Traverso is the senior author of the new study, which appears today in Nature Communications. Mehmet Girayhan Say, an MIT research scientist, and Sean You, a former MIT postdoc, are the lead authors of the paper.

A pill that communicates

Patients’ failure to take their medicine as prescribed is a major challenge that contributes to hundreds of thousands of preventable deaths and billions of dollars in health care costs annually.

To make it easier for people to take their medication, Traverso’s lab has worked on delivery capsules that can remain in the digestive tract for days or weeks, releasing doses at predetermined times. However, this approach may not be compatible with all drugs.

“We’ve developed systems that can stay in the body for a long time, and we know that those systems can improve adherence, but we also recognize that for certain medications, we can’t change the pill,” Traverso says. “The question becomes: What else can we do to help the person and help their health care providers ensure that they’re receiving the medication?”

In their new study, the researchers focused on a strategy that would allow doctors to more closely monitor whether patients are taking their medication. Using radio frequency — a type of signal that can be easily detected from outside the body and is safe for humans — they designed a capsule that can communicate after the patient has swallowed it.

There have been previous efforts to develop RF-based signaling devices for medication capsules, but those were all made from components that don’t break down easily in the body and would need to travel through the digestive system.

To minimize the potential risk of any blockage of the GI tract, the MIT team decided to create an RF-based system that would be bioresorbable, meaning that it can be broken down and absorbed by the body. The antenna that sends out the RF signal is made from zinc, and it is embedded into a cellulose particle.

“We chose these materials recognizing their very favorable safety profiles and also environmental compatibility,” Traverso says.

The zinc-cellulose antenna is rolled up and placed inside a capsule along with the drug to be delivered. The outer layer of the capsule is made from gelatin coated with a layer of cellulose and either molybdenum or tungsten, which blocks any RF signal from being emitted.

Once the capsule is swallowed, the coating breaks down, releasing the drug along with the RF antenna. The antenna can then pick up an RF signal sent from an external receiver and, working with a small RF chip, sends back a signal to confirm that the capsule was swallowed. This communication happens within 10 minutes of the pill being swallowed.

The RF chip, which is about 400 by 400 micrometers, is an off-the-shelf chip that is not biodegradable and would need to be excreted through the digestive tract. All of the other components would break down in the stomach within a week.

“The components are designed to break down over days using materials with well-established safety profiles, such as zinc and cellulose, which are already widely used in medicine,” Say says. “Our goal is to avoid long-term accumulation while enabling reliable confirmation that a pill was taken, and longer-term safety will continue to be evaluated as the technology moves toward clinical use.”

Promoting adherence

Tests in an animal model showed that the RF signal was successfully transmitted from inside the stomach and could be read by an external receiver at a distance up to 2 feet away. If developed for use in humans, the researchers envision designing a wearable device that could receive the signal and then transmit it to the patient’s health care team.

The researchers now plan to do further preclinical studies and hope to soon test the system in humans. One patient population that could benefit greatly from this type of monitoring is people who have recently had organ transplants and need to take immunosuppressant drugs to make sure their body doesn’t reject the new organ.

“We want to prioritize medications that, when non-adherence is present, could have a really detrimental effect for the individual,” Traverso says.

Other populations that could benefit include people who have recently had a stent inserted and need to take medication to help prevent blockage of the stent, people with chronic infectious diseases such as tuberculosis, and people with neuropsychiatric disorders whose conditions may impair their ability to take their medication.

###

The research was funded by Novo Nordisk, MIT’s Department of Mechanical Engineering, the Division of Gastroenterology at Brigham and Women’s Hospital, and the U.S. Advanced Research Projects Agency for Health.

Image: MIT engineers have designed a pill that can report when it has been swallowed. The outer layer of the capsule is made from gelatin coated with a layer of cellulose and either molybdenum or tungsten, which blocks any RF signal from being emitted.

View more Credit: Mehmet Say

Their findings were published last month in Nature Chemistry (https://www.nature.com/articles/s41557-025-02011-7).

For nearly thirty years, researchers who tried to control when and where plastics harden focused on designing special “sleeping” catalysts, molecules that stay dormant until they are triggered by light, heat, or another signal. These catalysts are often sensitive, expensive, and difficult to handle.

The BGU team turned this logic on its head, as PhD student Nir Lemcoff, one of the lead authors on the paper, described, “This work demonstrates a new way of thinking about a general problem in polymer science and will hopefully inspire scientists in the field to look at the challenges in their own work with a fresh point of view”.

Instead of trying to put the on/off switch in the catalyst, they hid it inside the plastic building blocks themselves, creating so-called “latent monomers.” These are stable liquid building blocks that remain inactive for weeks. They then “snap” into a solid plastic-like material only when exposed to light or gentle heating.

These new latent monomers are built from small molecules called norbornadienes. Norbornadienes can be opened and linked into long chains by a standard plastic-making method called ROMP (ring-opening metathesis polymerization). When UV light is shined on them, they change into a different form called quadricyclane, which is basically the “off” state: it is inactive and does not build chains. Later, gentle heating with tiny gold nanoparticles switches quadricyclane back “on” to the reactive norbornadiene, so the chain-building can start again on demand. Because chemists can easily make many different norbornadienes, this switchable system could give rise to hundreds of new plastic-like materials, including some that are very hard to make with existing methods.

“Instead of a ‘sleeping’ catalyst, we created ‘sleeping’ building blocks of the material itself,” explains Prof. Yossi Weizmann of the Department of Chemistry at Ben-Gurion University, who led the study. “The mixture can sit quietly on the shelf for weeks and will snap together into a solid only when you shine light on it or warm it up. That kind of on-demand, light-driven curing could make industrial production, printing, and repair processes safer, simpler and more energy-efficient.”

The new liquids contain three key ingredients:

• Building blocks that can link together into long plastic-like chains
• A standard industrial catalyst that drives the chain-forming reaction
• Tiny gold nanoparticles that act as microscopic heaters when illuminated with near-infrared light

In their “sleeping” state, the latent monomers are locked in a form that does not react, even though the catalyst is already present. When the researchers shine light on the gold nanoparticles, they heat up their immediate surroundings and flip the monomers into an “active” form that quickly links into a solid material. The same switch can also be thrown by conventional heating, but not as efficiently.

Since nothing happens until the trigger is applied, manufacturers could in principle:

• Store and ship a ready-to-use liquid formulation for weeks without it thickening or hardening
• Fill, coat, or print parts first, and only then turn on curing in selected regions using light patterns or masks
• Reduce waste and energy use by avoiding the need to constantly mix fresh batches or heat entire volumes for long periods

The study also shows that this idea of switchable building blocks can do much more than simply turn a reaction on and off. By mixing building blocks that are active from the start with others that stay asleep until they are heated, the team can make plastics whose chains have two different sections, which gives materials with combined properties in one product. They can also first create a soft material that is easy to shape and later lock it into a tougher and more durable solid, all in a single process.

Prof. Weizmann is a member of the Zuckerman STEM Leadership Program.

Additional researchers on the project, all from Ben-Gurion University of the Negev, include Ronny Niv from Prof. N. Gabriel Lemcoff’s group who are joint first authors on the paper, as well as Keren Iudanov from the Lemcoff lab, and Gil Gordon, Aritra Biswas, Uri Ben-Nun and Ofir Shelonchik from the Weizmann lab.

The work was supported by the Israel Science Foundation (ISF, grant no. 2491/20) and the United States–Israel Binational Science Foundation (BSF, grant no. 2020144).

Image: Prof. Yossi Weizmann

View more Credit: Amit Paor/BGU