The Digital Path to AI in Cancer Care

David West
David West
CEO, Proscia

As cancer care becomes data-driven, artificial intelligence (AI) will play an increasingly central role across the treatment continuum, from biomarker identification and drug development to clinical trial recruitment and diagnostics. In this corner of healthcare, the ability of AI to interpret and annotate tumor sample slides that have been digitized is taking center stage. While the promise is great, and AI interpretation is already influencing some clinical care, it has not yet reached critical mass.

“There’s something like a billion slides created every year for diagnostic purposes, and today most of those, about 85%, are still read by a pathologist with a microscope on physical glass slides,” said David West, CEO and co-founder of digital pathology company Proscia. In practice, that means pathologists manually examine slides, identify cancer, grade tumors, and dictate reports in a traditional approach to diagnosing cancer that has seen little change in decades.

Mohamed Omar
Mohamed Omar, MD
Associate Professor
Cedars-Sinai Medical Center

But that foundation is now shifting. Advances in slide scanning, cloud storage, and AI are turning digital pathology images into data that can be analyzed at scale. At Memorial Sloan Kettering Cancer Center, large archives of digitized slides helped launch Paige AI, one of the earliest companies to train deep learning systems on pathology images linked to clinical and genomic outcomes. This yielded the first U.S. Food and Drug Administration (FDA)-approved diagnostic using AI and digital pathology: Paige Prostate Detect. The company, which was acquired last year by AI-enabled precision medicine company Tempus, now combines Paige’s digital pathology-based AI with Tempus’s broad genomic sequencing data platform.

Researchers in the field say the implications of AI in digital pathology extend beyond image analysis. Mohamed Omar, MD, an associate professor of computational biology at Cedars-Sinai Medical Center, Los Angeles, noted that large language models can help clinicians navigate a research landscape that produces “hundreds of papers every single day” to inform ongoing cancer research. Multimodal AI tools promise to unlock even more insights from digital pathology data by combining it with genomic, radiomic, and clinical data to build powerful new models of both common and rare cancers for diagnosis, drug development, and clinical trial enrollment.

Razik Yousfi
Razik Yousfi
SVP and GM, Tempus

While adoption is in its early stages, the advent of faster and less expensive scanners is bringing digital pathology within reach of both regional and rural hospitals. Razik Yousfi, senior vice president and general manager of AI products at Tempus, and a co-founder of Paige, predicts that within the next 10 years, the majority of pathology workflows will be digital. The ultimate goal of the application of AI here is not to replace human pathologists, but to empower them with a capable assistant while spreading adoption beyond major medical centers.

Building the foundations

As the field of applying AI to digital pathology progresses, it needs to build the groundwork for a wider range of potential applications that could address rare cancers and other areas without an abundance of data. One such project is called Atlas, a collaboration between researchers in Korea, Germany, and the United States to build a foundation model trained using 1.2 million histopathology whole-slide images from 490,000 cases sourced from the Mayo Clinic and Charité – Universitätsmedizin Berlin.

Foundation models like Atlas allow large-scale pre-training of data to develop numerical representations called embeddings that capture both the structural and contextual features of slides in the dataset. Atlas incorporates a diversity of diseases, staining types, and scanners, and uses multiple image magnifications during training. This broad approach confers power and utility. It allows the digitized representations of the histology to be adapted, queried, or fine-tuned to very specific downstream tasks using much less data than would be needed to build a one-off model.

As such, a foundation model provides a reusable digitized computational backbone that can be tapped across a wide range of uses, like tumor classification, detection of morphologic structures, biomarker quantification, and outcome prediction. In short, foundational models make the process of querying digital pathology images more efficient compared with past approaches.

Andrew P. Norgan
Andrew P. Norgan, MD, PhD
CMO, Mayo Clinic

“In the case of pathology, the successful AI models developed using ‘conventional’ neural network approaches before the advent of FMs (foundation models) typically required huge amounts of training data to achieve high performance and generalizability—the ability to work across datasets distinct from the training data,” said lead Atlas researcher Andrew P. Norgan, MD, PhD, CMO of Mayo Clinic Digital Pathology and assistant professor of laboratory medicine and pathology. “We think of FMs as [an] enabler that allows model development in pathology … to move from artisanal or craft processes to more scalable and reproducible processes that should allow for the rapid development of high-quality models to address problems in pathology.”

At Paige AI, the company’s early work resulted in the first FDA-approved AI diagnostic, Paige Prostate Detect. Its algorithm was built using a technique called multiple instance learning instead of traditional supervised neural network techniques that require detailed human annotation of slides, a time-consuming and expensive method that could expose the learning to human error. The difference between the two methods is that traditional neural networks expose AI to a slide with cancer and tell it that there is cancer present. In multiple instance learning, the model is shown unannotated slides and is tasked with finding the cancer.

Even this approach, however, required a very large dataset. It became apparent to company leaders that the heavy lifting required to get Paige Prostate Detect to work wasn’t scalable.

“We had kind of cracked this recipe,” said Yousfi. “We know how to use a lot of GPU (graphics processing unit) compute, and if we get a ton of data and a lot of compute, we can build anything. But GPU infrastructure is very expensive, and it takes a lot of time to train a very large system.”

Perhaps the most important factor moving Paige away from this model is that it will not work when there is only a small amount of data available. This blocks the ability to train AI to recognize rare cancers for which sample counts are low. The company needed a different approach.

“We had this idea [for] a new system that was basically trained on all of the images we had access to, independent of the organ and indication and tissue and task,” Yousfi said. “Back then, we didn’t know what that thing was called. But ultimately, that became what everyone is calling today a foundation model.”

Originally trained on 200,000 slides, Paige’s new model now includes 3.5 million images and roughly two billion parameters, making it the backbone for other downstream applications the company builds today. This ability to use foundation models as the AI and data encyclopedia for smaller applications will ultimately propel the field of digital pathology forward by widening the playing field.

Going multimodal

To address more complex predictive problems, additional data types can be integrated. Clinical, radiologic, or genomic data can be combined with morphologic embeddings or used during training to help the model learn which tissue features carry a signal of disease or identify a biomarker. These approaches aim to support precision oncology by making morphologic data computable and aligning slide-derived features with other cancer-focused datasets. “These approaches can surface subtle or ‘latent’ patterns in pathology slides and align them with other data sources,” Norgan said. Pathologist and oncology care teams can then evaluate and interpret the features identified by the models within the clinical and biological context.

“In this way, pathologists and oncology teams use these outputs as decision-support tools, while clinical judgment remains central to diagnostic interpretation and therapeutic decision making,” Norgan added.

Atlas has now been succeeded by Atlas2, which was trained on 5.5 million pathology images and is now a two billion-parameter model, making it one of the largest pathology foundation models to date. The team has explored distilling methods to create smaller, more efficient, and targeted versions of the model that retain performance, with an eye toward finding a balance between scale and deployability.

Proscia is embarking on a different multimodal approach that combines vision models with language models, with the intent of creating methods to query the morphology of digitized slides. Their efforts in vision-language models (VLMs) combine textual data with visual data and allow the model to describe the morphology of a slide, answer questions about what it contains, find images in a database based on a text query, and even follow multimodal instructions such as “circle the tumor area on this image.”

In short, a VLM can be engaged in the same way you can engage a human. “I could go ask a pathologist to point out all the areas of tumor-infiltrating lymphocytes,” West said. “Now, because language-vision models are encoding language and images in the same space, they can do that, too. You can ask the model to describe what is happening in an image, and it will tell you exactly what it sees.”

At Cedars-Sinai, Omar’s work with large language models takes a less direct route of leveraging queries to gather information from research studies or even images. “Basically, you could go to the tool, ask questions, and the tool will provide you with pieces of code,” he explained. “These pieces of code are what you use on the slide to get more information.”

Atlas provides a similar function at the Mayo Clinic, Norgan noted. Because the model-generated embeddings in the digitized slide also encode semantic information, the Atlas team is now building a slide search function, which would allow researchers or clinicians to identify and access slides, or regions of slides, with related features.

Democratizing care

Although it will take time to disseminate the tools needed for AI-enabled digitized models of cancer care to smaller health systems, the future is now at Moffitt Cancer Center, where the research hospital is engaged in a top-to-bottom digitization of its system.

Marilyn Bui
Marilyn Bui, MD, PhD
Senior Member
Moffitt Cancer Center

According to Marilyn Bui, MD, PhD, senior member of the departments of pathology and machine learning, the comprehensive cancer center plans for full digital adoption across clinical and research labs by 2027. Last August, it entered a multi-year collaboration with integrated AI and digital pathology company PathAI to deploy its cloud-based digital pathology image management system for both research and clinical applications.

Within the pathology department, the transition will mean that all glass slides will be scanned and reviewed digitally, providing the basis for applying AI computational tools to assist pathologists. Bui said that the cancer center is accelerating its move toward clinical AI adoption: “Just today I received an email asking which AI algorithms we plan to incorporate for clinical utility—prostate cancer, breast cancer, general tumor detection,” she said. “For us, it’s no longer just research.”

Moffitt is taking a hybrid approach to algorithm development and deployment within the system. Some AI tools will come from commercial vendors and will be validated internally, while others will be developed by investigators through the center’s translational pathology work. Taking this approach will allow it to apply AI to both common cancers and the rare tumor types Moffitt frequently encounters.

While the digital initiative will be transformational, Bui emphasized that the goal is not to replace pathologists but to enhance their capabilities. She prefers to refer to AI as augmented intelligence to reflect this. “Artificial intelligence suggests a robot replacing us,” she said. “But what we mean is augmented intelligence—tools that assist and enhance our ability to make clinical decisions.”

Further, Moffitt intends to integrate digitized slide data with genomic, proteomic, and clinical outcome data to build a multimodal data environment that could advance precision oncology. “Digital pathology and AI will allow us to extract far more information from tissue samples,” Bui said, “making our diagnoses more actionable for the clinical team and ultimately improving patient care.”

The promise of AI in oncology isn’t just better algorithms, it’s broader access. The maturation of computational pathology and its dissemination from large cancer centers like Moffitt to regional and rural health systems has the potential to provide levels of care typically only available at large research hospitals in community settings as well.

“It’s about democratizing access to care,” said Omar. “For a person in Maine or Wisconsin or another place to have access to the same high-quality care that you would get from a larger academic medical center in LA or New York, slides have to be digitized.”

Over the next 10 years, there could be a compelling business case for hospitals to embrace digital pathology. As the cost of scanners comes down and a broad range of diagnostic tools becomes available, digitizing routine H&E slides could become common.

While genetic cancer testing can cost hundreds of dollars, Omar pointed out that pathology slides “cost $5 [and] they are available universally, in all patients with cancer.” As AI models increasingly identify genomic-level insights directly from those inexpensive images, it represents a “huge win for accessibility, making AI work for patients who cannot afford genetic tests,” Omar said. If there is broad adoption of digital pathology “it is very easy to roll out any kind of AI models and computational tools across the board, across situations and locations that don’t have access to care.”

“At the end of the day, all slides will be digitized,” he concluded. “It’s just a matter of time.”

 

Chris Anderson, a Maine native, has been a B2B editor for more than 25 years. He was the founding editor of Security Systems News and Drug Discovery News, and led the print launch and expanded coverage as editor in chief of Clinical OMICs, now named Inside Precision Medicine.

The post The Digital Path to AI in Cancer Care appeared first on Inside Precision Medicine.

Strength of Evidence to Support Decision-Making on the Use of Digital Mental Health Technologies in NICE Evaluations: Cross-Sectional Analysis of Studies

Background: Digital mental health technologies (DMHTs) are playing an increasing role in mental health services. The quality of evidence for DMHTs is variable, and there are concerns that evidence is not sufficient to support decision-making. Objective: This study used a cross-sectional analysis of evidence supporting DMHTs included in National Institute for Health and Care Excellence (NICE) evaluations to examine the strength of evidence available for decision-making. Methods: We identified all NICE evaluations relating to DMHTs by reviewing details of published NICE evaluations on the NICE website. From each of these evaluations, we identified included DMHTs and reviewed committee documentation to identify studies that provided supporting evidence for each of these technologies. We extracted information on a series of items relating to study quality and summarized the characteristics of evidence both at the level of individual studies and across the package of evidence from multiple studies supporting DMHTs. We also identified key evidence gaps in available evidence. Results: We included nine NICE evaluations relating to anxiety, depression, psychosis, insomnia, attention deficit hyperactivity disorder (ADHD), and tic disorders. These evaluations included 30 DMHTs and referenced 78 supporting studies. We identified common evidence gaps relating to effectiveness compared to relevant comparators, use of appropriate outcomes, including health-related quality of life, cost of delivery, and impact on resource use, and reporting of adverse events. Conclusions: Our study highlights that some DMHTs have been supported by high-quality studies and that evidence to support DMHTs is likely to be developed across a series of studies. However, there are often key evidence gaps that need to be addressed to provide a stronger case for adoption. Developers should ensure that they consider these gaps while planning evidence generation, and where possible, address them earlier in the product lifecycle.
<img src="https://jmir-production.s3.us-east-2.amazonaws.com/thumbs/825f13db8cbad54213afa5c433d7adde" />

Mosaic HA Vaccine Confers Cross-Strain Immunity in Influenza

Researchers at the Institute for Biomedical Sciences at Georgia State University have developed a vaccine platform designed to provide protection against a range of influenza virus infections by targeting conserved viral structures and inducing immunity at mucosal surfaces. The study, published in ACS Nano, details how the development of the novel vaccine uses cell-derived extracellular vesicles (EVs) engineered to display multiple influenza hemagglutinins (HAs) in an inverted configuration, which allows the immune system to recognize conserved regions shared across viral strains. In mouse models, the vaccine elicited cross-reactive antibodies, cellular immune responses, and mucosal immunity, providing protection against heterosubtypic H5N1 and H7N9 influenza virus challenges following intranasal administration.

“The influenza virus is smart. They have evolved to evade the immune system by hiding their critical conserved structures, rendering these elements poorly immunogenic,” said senior author Bao-Zhong Wang, PhD, a professor at the Institute for Biomedical Sciences at Georgia State.

The vaccine’s design centers on two key features: the use of extracellular vesicles (EVs) as a delivery platform and the inversion of HA proteins on their surface. EVs are natural nanoparticles involved in cell-to-cell communication and have been researched extensively for therapeutic delivery due to their biocompatibility. In this study, they were engineered to display multiple HA subtypes simultaneously. The HAs were presented in an upside-down orientation, which partially shields the highly variable head domain while exposing the conserved stalk domain. This structural arrangement directs the immune response toward regions less prone to mutation, enabling broader protection across influenza strains.

“These (vaccine responses) highlight that the inverted HA is a smarter strategy for inducing protective immunity to the conserved HA stalk. Meanwhile, cell-origin EVs are a biocompatible platform for mucosal vaccine delivery. Using EVs simultaneously displaying multiple inverted HAs is a powerful approach for developing universal influenza vaccines,” Wang added.

To test their vaccine design the researchers immunized mice intranasally with the EV-based vaccine, allowing researchers to assess mucosal immunity in addition to systemic responses. The data showed that the vaccine induced cross-reactive antibodies targeting HA stalks, virus-specific T cell responses, and a balanced Th1/Th2 immune profile. Importantly, the vaccinated mice were fully protected against lethal infections from reassortant H5N1 and H7N9 viruses.

The new vaccine designed was based on previous research into EV-based vaccine delivery and different strategies to target the HA stalk. Earlier studies had shown that EVs could serve as adjuvants and antigen carriers for intranasal vaccines. In addition, other research seeking to develop a universal influenza vaccine has focused on the conserved HA stalk domain, which evolves more slowly than the immunodominant head. As the researchers noted, “the conserved HA stalk domain has emerged as a promising candidate for a universal influenza vaccine due to its low evolutionary rate and greater tolerance to mutations.” However, previous approaches had used isolated HA stalk constructs, but faced shortcoming related to structural stability and immunogenicity.

By preserving the full HA ectodomain while inverting its orientation, the new design addressed these limitations. “Our findings suggest that utilizing the entire HA ectodomain as an immunogen, while hiding the HA head and increasing exposure of the HA stalk, is an effective strategy to induce robust immune responses targeting conserved HA epitopes,” the researchers wrote, noting that this approach allows the immune system to access structurally intact conserved regions.

If this vaccine design can be shown effective in humans, it could provide a vaccine with broader and longer-lasting protection against influenza, and reduce the need for frequent reformulations. The use of intranasal delivery could also change how vaccines are administered by targeting immune responses at the site of viral entry. “Mucosal vaccination effectively induces local immune responses, protecting against respiratory virus infections at the site of invasion,” the team noted.

Next steps for the team include continued characterization of the immune responses induced by the vaccine, to include the specificity and neutralizing capacity of antibodies, as well as evaluation of anti-EV immunity with repeated dosing. More animal studies, and eventually clinical trials, will be needed to assess safety, scalability, and efficacy in humans.

The post Mosaic HA Vaccine Confers Cross-Strain Immunity in Influenza appeared first on Inside Precision Medicine.

From Reactive to Proactive: Reimagining Hypertension Management in the Precision Medicine Era

According to the World Health Organization, an estimated 1.4 billion adults aged 30–79 worldwide had hypertension in 2024, representing around one-third of the global population of that age. Of these, 44% were unaware that they were living with a leading risk factor for premature death and poor health worldwide due to its association with myocardial infarction, stroke, and kidney disease.

Despite the size of the hypertension problem, its diagnosis and treatment pathway has remained largely the same for decades.

A 60-year-old pathway

“The current pathway in hypertension diagnosis and treatment has really not changed in over 60 years,” said Sandosh Padmanabhan, MD, PhD, chair of pharmacogenomics and professor of cardiovascular genomics and therapeutics at the University of Glasgow in Scotland.

He explained that it is based on opportunistic detection of hypertension, which has traditionally been defined as a blood pressure (BP) of 140/90 mmHg in the clinic, although thresholds vary by measurement method and guideline. For example, out-of-office measures typically use lower cut-points (e.g., home/daytime ambulatory averages) of 135/85 mmHg.

Sandosh Padmanabhan
Sandosh Padmanabhan, MD, PhD
Professor
University of Glasgow

Diagnosis typically occurs when a patient visits their primary care physician (PCP) or has a pharmacy BP check. Confirmation follows, ideally with out-of-office BP monitoring to avoid misclassification caused by one-off measurements.

Patients are then stratified by predicted 10-year cardiovascular risk, using risk calculators such as Q-risk or the PREVENT score, and treatment is based on a stepwise algorithm. First, patients are generally given lifestyle advice like reducing salt, alcohol, and caffeine intake, improving sleep, managing stress, and increasing exercise. This may give them a chance to reduce their BP without pharmacologic intervention.

If unsuccessful, depending on local guidelines, patients may be offered an angiotensin-converting enzyme (ACE) inhibitor or angiotensin receptor blocker if under 55 years of age. Those over 55 years or of Black African or Caribbean origin are started on a calcium channel blocker. The next steps combine ACE inhibitors and calcium channel blockers, then add a thiazide-like diuretic, followed by spironolactone or other drugs.

However, this approach uses “a population-level logic,” said Padmanabhan. Although age and ethnicity are considered, “these are broad demographic proxies that don’t include any understanding of the individuals’ underlying pathophysiology or the genetic makeup.”

He stresses that, on a public health basis, the system works. There are multiple effective, low-cost antihypertensive drug classes and many generic options available that effectively lower BP. Despite this, control rates are poor. “Fewer than one in four hypertensive adults globally have their BP adequately controlled,” he said.

The measurement problem

Part of the issue lies in how BP is measured. “To give you an idea about the scale of inertia, we diagnose BP using a device that was introduced in the late 19th century,” Padmanabhan noted, referring to the sphygmomanometer invented by Scipione Riva-Rocci in 1896. Not only that, the technique can also be flawed. Variables such as incorrect cuff size, improper positioning, and patient movement can distort readings. Even talking during measurement can increase BP values by 5–9 mmHg or even higher.

Crucially, a single measurement provides little insight into cumulative lifetime exposure to high BP and can be skewed by issues like white coat hypertension or masked hypertension. “We look at the BP number, but the patients don’t experience that number. What they experience is a lifelong vascular risk,” Padmanabhan explained. “Treatment is not about a short-term reduction in a number. It’s about long-term sustained risk reduction.”

Yet the current system remains reactive and is not working well enough. “We have to move away from reactive diagnosis to proactive identification,” Padmanabhan said. “The earlier we measure accurately and respond systematically, the fewer surprises we’ll see later.”

Continuous monitoring

The pitfalls of opportunistic, or even planned, BP measurement are driving the emergence of new technologies capable of continuous monitoring.

Josep Solà
Josep Solà, PhD
CTO and Co-founder
Aktiia

Josep Solà, PhD, began working on optical sensing technology in 2004 at the Centre for Electronics and Microtechnology in Switzerland. By analyzing subtle changes in reflected light caused by arterial dilation, it became clear that BP could be measured using these light signals. In 2018, this research was spun out into Aktiia, where Solà is CTO and co-founder. The company has developed and commercialized the Hilo™ band: a CE-certified wearable medical device designed for continuous, cuffless, BP monitoring that has been clinically validated against traditional ambulatory BP monitoring.

The band tracks BP and heart rate automatically, about 25 times per day, without requiring any action from users. Paired with an app, the device shows users daily, nightly, and long-term BP trends. It is currently available as a certified medical device across Europe, Australia, and Canada, and, following FDA approval in July 2025, the company is preparing for a U.S. launch.

Solà said he and co-founder Mattia Bertschi, PhD, were convinced they could change how hypertension is being managed today. He believes there is no good reason why most people with hypertension cannot control the condition. The medication is cheap and effective; the problem is that there has been no technology that patients can use to properly manage their condition.

“No one wants to use a cuff every day for the next 30 years,” said Solà. “They’re just so inconvenient, and you cannot expect people to proactively measure something they don’t feel.”

The Hilo band gives wearers a feedback loop that has historically been missing from BP measurement. Users can immediately see that reducing their salt or alcohol intake, for example, lowers their BP. “We are empowering people,” said Solà. “We are empowering them to look at the intervention, or combination of interventions, with or without medication, to see what is effective for them, and this reinforces their willingness to continue with the changes they are making.”

Hilo product
Credit: Hilo

Data published by Aktiia has shown that this approach works. A study of 8,950 U.K.-based Hilo users indicated that individuals who monitored their BP continuously showed better control over time. Specifically, users over 50 years of age appeared able to prevent the age-related rise in systolic BP typically seen in the general population, which the researchers say “may reflect greater awareness, stronger treatment adherence, and lifestyle changes prompted by continuous feedback.”

Wearables at scale: Opportunity and caution

Beyond dedicated monitoring devices like the Hilo band, smartwatches and other devices are increasingly capable of detecting physiological signals associated with cardiovascular risk. The Apple Watch can detect potential signs of chronic hypertension by analyzing heart rate sensor data over 30-day periods, the Huawei Watch D provides on-demand and 24-hour ambulatory BP monitoring using an air-filled strap, while the team behind the Oura ring is developing a “Blood Pressure Profile” feature to detect early signs of hypertension.

Although this represents a significant step toward embedding cardiovascular monitoring into everyday life, the increasing use of these devices raises important questions about accuracy, interpretation, and clinical integration, particularly as they often rely on indirect signals rather than direct BP measurement.

Adam Bress
Adam Bress, PharmD
Researcher
University of Utah

As Adam Bress, PharmD, from the Spencer Fox Eccles School of Medicine at the University of Utah, and colleagues have recently shown, translating wearable-derived signals into meaningful clinical information is not straightforward.

They evaluated the hypertension alert feature of the Apple Watch, which has a published sensitivity of 41% and specificity of 92%, meaning that approximately 59% of individuals with undiagnosed hypertension would not receive an alert, while about eight percent of those without hypertension would receive a false alert.

“The problem there, is that this data only tells you how the alert works in a very controlled, limited population,” said Bress. “In order to understand how it’s going to work in the real world, we need to know how the true prevalence of undiagnosed hypertension varies in the population and in subgroups and to what degree.”

Using data from nearly 4,000 adults in the U.S., Bress and colleagues showed that the pretest probability of having hypertension has a significant impact on the reliability of the alert. For example, among adults under 30 years of age, the pretest probability of having hypertension is 14%. A positive alert on the Apple Watch would increase this probability to 47%, whereas no alert reduces the probability to 10%.

However, for adults aged 60 years and older, an alert increases the probability of an individual having hypertension from a pretest level of 45% to 81%, whereas the absence of an alert only lowers it to 34%. This translates to large numbers of false negatives when applied across millions of users.

In Apple’s validation study, the company stresses that the watch is not intended to replace traditional diagnosis methods or to be used as a method of BP surveillance, and that the absence of a notification does not indicate the absence of hypertension.

“The concern is, if you’re not getting an alert, will people interpret that as them not having hypertension,” said Bress. “That’s the worry. … The groups in which the negative alert is the least trustworthy contain the people with the highest risk. We’re most worried about people being falsely reassured.”

At the same time, he is clear that wearables should not be dismissed. “This technology is an important step forward; we need more wearable tech that can screen,” he said.

Unfortunately, access to these devices is not universal. Advanced monitoring technologies are often first adopted by the “worried well”—people who are more affluent and health-conscious—rather than those at highest risk.

“The only thing that can change this is a clear political decision to make awareness of hypertension large scale,” said Solà. Devices like the Hilo band could be used much like the continuous glucose monitors for diabetes. The difference is that if someone with diabetes doesn’t keep their blood glucose levels under control through regular monitoring, they can become ill very quickly. With hypertension, the effects of poor control don’t become apparent for decades.

“We need the policymakers to understand that investing in this technology today will have a return on investment in 10 years from now, not in one year from now,” Solà remarked.

Targeted drug selection

Even when hypertension is detected early and monitored closely, treatment remains largely empirical and can lead to therapeutic inertia, one of the biggest current challenges in hypertension care. “BP is not like diabetes, it doesn’t cause symptoms, and because of that, we don’t escalate treatment often enough,” said Padmanabhan.

At the same time, treatment selection remains largely trial-and-error. Clinicians cycle through medications sequentially, adjusting regimens based on response rather than underlying biology. The issue is that failed attempts risk side effects and can erode trust. That lack of trust can then impact adherence and, therefore, cardiovascular risk.

Instead, Padmanabhan believes that we need to move toward mechanistically informed drug selection.

This approach is common in oncology, where targeted therapies have been matched to specific mutations, but the picture is more complex for BP. Genome-wide association studies (GWAS) have identified more than 30 genes associated with monogenic forms of hypertension or hypotension and more than 2,100 single nucleotide polymorphisms linked to BP regulation, underscoring its highly polygenic nature.

This, combined with the strong influence of environmental factors, means that there is no single pathway or biomarker that can be easily targeted to reduce BP.

Padmanabhan’s work on the uromodulin gene (UMOD), however, shows that GWAS data can translate into therapy. His team identified a signal on chromosome 16 linked to uromodulin, a protein that is only expressed in one part of the kidney and plays a role in salt regulation. In a clinical trial  comparing people with low BP to those with high BP, they found that people with the UMOD allele that increases protein expression experienced a sustained reduction in BP when treated with the loop diuretic torasemide, whereas the effect was only temporary and followed by rebound in those carrying the UMOD allele that lowers protein expression.

Approximately two-thirds of the population carry the UMOD allele that increases protein expression, meaning that loop diuretics like furosemide or torasemide, which are more commonly used to treat heart failure, could potentially be used in hypertension personalized by the patient’s genotype.

So far, “this is the only clinical trial from a GWAS-identified genetic variant in hypertension,” Padmanabhan noted, highlighting both the promise and challenge of pharmacogenomics in hypertension.

Although clinical translation from GWAS of hypertension has been limited, research has shown that genetic variation in drug-metabolizing enzymes can significantly impact hypertension treatment efficacy and toxicity. For example, variants of CYP2D6 affect metoprolol metabolism whereas those in CYP2C9 influence responses to losartan. Research is needed to determine whether testing for these variants or others could reduce trial-and-error prescription, minimize side effects, and thus increase patient confidence and long-term engagement.

Teresa Castielo
Teresa Castielo, MD
Director
MIAL Healthcare

On a more fundamental level, biological sex differences remain a significant consideration in cardiovascular medicine. “Biological factors are an integral part of the clinical picture,” noted Teresa Castiello, MD, consultant cardiologist and director of MIAL Healthcare in London. She points out that clinical trials have historically seen a predominance of male participants; as a result, many standard medication dosages are based on data primarily derived from men.

This can lead to challenges with tolerability and a higher incidence of side effects in women as the therapeutic dose required for efficacy often tends to be lower in female patients.

Castiello suggests that this area of management warrants further refinement in clinical practice. She also emphasizes that key aspects of female cardiovascular risk, including reproductive history, menopause, and conditions like polycystic ovary syndrome, are nuances that may not always receive the necessary focus in routine care.

Toward a precise, preventative system

Ultimately, transforming hypertension care will require more than new technologies or therapies. It will require a fundamental change in how care is delivered.

Padmanabhan argues that hypertension should be managed through a “precision prevention service,” that integrates early detection, continuous monitoring, and personalized treatment, and involves more than just PCPs.

This approach recognizes that the disease is not just a clinical condition but a societal one, influenced by factors such as diet, socioeconomic status, work patterns, and access to care. Equity remains another critical issue. “We treat the ideal average patient under ideal circumstances but that’s not reality,” said Padmanabhan.

There also needs to be a cultural shift, said Castiello. “It’s not just the doctor’s responsibility; we also need to take responsibility for our own health.”

Solà shares a similar vision for the future: he would like to see BP measurement to become as routine as brushing your teeth, supported by technologies that empower individuals and reduce the burden on healthcare systems.

If realized, this shift could transform hypertension from a silent, progressive disease into a manageable, preventable condition, saving millions of lives in the process.

 

Laura Cowen is a freelance medical journalist who has been covering healthcare news for over 10 years. Her main specialties are oncology and diabetes, but she has written about subjects ranging from cardiology to ophthalmology and is particularly interested in infectious diseases and public health.

The post From Reactive to Proactive: Reimagining Hypertension Management in the Precision Medicine Era appeared first on Inside Precision Medicine.

Integrating BP Monitoring With Precision

Teresa Castiello
Teresa-Castiello

Laura Cowen interviewed Teresa Castiello, MD, a cardiologist and healthcare prevention advocate, to discuss her insights on hypertension management in the era of precision medicine. Castiello shared her perspectives on the need for a proactive approach to hypertension care, the role of precision medicine and pharmacogenomics, and the potential impact of digital health Hilo in transforming how hypertension is diagnosed, monitored, and treated.

Q: Do you think there needs to be a shift in how hypertension is diagnosed and treated?

Teresa Castiello, MD: Without a doubt. We must move from reactive medicine—treating damage once it has occurred—to proactive medicine. Hypertension is frequently underdiagnosed because it often remains asymptomatic until organ damage is already underway. Furthermore, traditional office readings are often biased by the “white coat” effect, which is why clinical guidelines, including those from the ESC (European Society of Cardiology), are moving away from them. Current monitoring also has limitations; nocturnal readings from standard cuffs often wake the patient, and sporadic readings fail to reflect the true, dynamic daily blood pressure response.

Q: Are there any “uncomfortable truths” about hypertension care that we don’t talk about enough?

Castiello: A significant “uncomfortable truth” is the lingering bias that considers a rising blood pressure to be a normal part of aging. It isn’t. Data from the Yanomami population in the Amazon shows that systolic blood pressure can remain constant at approximately 100 mmHg throughout life. In our Westernized society, blood pressure increases as a response to environmental and stressful “insults” rather than as a physiological necessity. Unfortunately, current clinical practice in the U.K. has not yet fully implemented recent ESC changes. We still see values defined as “normal” when guidelines now identify them as elevated (anything above 120/70 mmHg). Cardiovascular risk actually begins to climb much sooner than most realize, often at systolic levels as low as 110–115 mmHg.

Q: Is there a risk of current treatment strategies controlling blood pressure numbers without addressing underlying mechanisms?

Castiello: Yes. Labeling most cases as “essential hypertension” is essentially admitting we are treating a multifactorial condition of unknown cause. We often fail to assess the individual holistically. Stress, hormonal shifts, poor work-life balance, diet, and physical inactivity are profound drivers of blood pressure increases. While medical therapy is a vital tool, we must not forget that humans are multifaceted and complex. We need a healthcare approach that treats the person, not just the metric.

Q: Is there a need for increased precision medicine in hypertension, e.g., with the use of pharmacogenomics? Could this information redefine high-risk?

Castiello: We are in an era where precision medicine is the only way to deliver effective care. The power of data is enabling us to target prevention and early diagnosis like never before. Pharmacogenomics is a key part of this; by understanding how a patient’s genetic profile influences their metabolism of a drug, we can move away from “trial and error.” This information redefines “high-risk” from a generic population score to an individual biological reality. It allows us to define optimal doses that maximize efficacy while minimizing the toxicity that often leads to treatment non-compliance.

Q: Are healthcare systems ready to integrate continuous blood pressure monitoring into routine care?

Castiello: Probably not yet, but they will be forced to be. COVID-19 showed that we can adapt to global interconnection and remote monitoring in a very short time when we have no choice. Prevention is the only way for healthcare systems to survive the rising burden of chronic disease. Philosophically, if we wait until we feel “ready” to take action, we will never act. The time to implement these preventive strategies is now.

Q: In ten years’ time, how do you hope hypertension will be managed differently?

Castiello: I hope every individual has access to a medical-grade wearable—whether a band, ring, or chip—empowered by AI to feed data into a proactive health system. This data will be filtered to flag those requiring care at a pre-pathological stage. We can no longer afford to wait for a crisis to occur before we treat it; global healthcare systems cannot handle that burden. We must prevent what is possible and focus our hospital resources on the conditions that occur despite our best preventive strategies

The post Integrating BP Monitoring With Precision appeared first on Inside Precision Medicine.

High-Throughput Platform for Fast-Acting Covalent Protein Therapies

Researchers at Westlake University in China, lead by Bobo Dang, PhD, and Ting Zhou, PhD, report the development of a high-throughput platform for engineering fast-acting covalent protein therapeutics. The team says their study “A high-throughput selection system for fast-acting covalent protein drugs,” published in Science, opens new avenues for next-generation biologics.

Covalent small-molecule drugs have shown great success in cancer therapy by forming irreversible bonds with their targets. This has inspired efforts to extend covalent strategies to protein therapeutics, especially engineered miniproteins. However, their development is limited by a kinetic mismatch. Miniproteins are rapidly cleared in vivo, while covalent bond formation is typically slow. In addition, high-throughput platforms for systematically optimizing covalent protein reactivity have been lacking.

To address this challenge, the researchers proposed that precise spatial positioning of chemical warheads within protein scaffolds could enable molecular preorganization, thereby accelerating covalent bond formation without increasing intrinsic reactivity (see figure).

The principle for developing fast-acting covalent proteins via comprehensive crosslinker and protein sequence engineering. [Bobo Dang's Lab at Westlake University]
The principle for developing fast-acting covalent proteins via comprehensive crosslinker and protein sequence engineering. [Bobo Dang’s Lab at Westlake University]

Based on this concept, the team created a high-throughput platform that combines yeast surface display with chemoselective protein modification to screen diverse crosslinkers and millions of protein variants. The platform enables rapid and irreversible target engagement.

Using this platform, the researchers developed a covalent antagonist targeting PD-L1, termed IB101. Structural analysis revealed that IB101 forms a defined binding pocket that precisely positions the active moiety in a reactive conformation, greatly accelerating covalent bond formation.

Functionally, IB101 effectively blocks the PD-1/PD-L1 immune checkpoint pathway and demonstrates strong antitumor activity in mouse models. Notably, despite its short in vivo half-life, IB101 achieves durable target engagement and tumor suppression, outperforming conventional antibody-based therapies under comparable conditions, according to the scientists.

The platform was further applied to cytokine engineering, leading to the development of a covalent IL-18 variant, IB201. This engineered cytokine rapidly forms a covalent interaction with its receptor, enhancing signaling strength and duration. In vivo studies showed that IB201 induces potent antitumor immune responses without detectable systemic toxicity. These results highlight the potential of covalent engineering to improve the efficacy and safety of cytokine-based therapies.

Beyond immunotherapy targets, the platform was also applied to develop a covalent inhibitor targeting the receptor-binding domain (RBD) of SARS-CoV-2. This molecule showed durable viral neutralization, demonstrating the versatility of the approach across different therapeutic modalities, note the researchers, adding that the study establishes a general strategy for engineering fast-acting covalent protein therapeutics.

By enabling covalent bond formation on timescales compatible with rapid in vivo clearance, the platform overcomes a fundamental limitation in the field, say the scientists. These findings, they continue, provide a new framework for designing biologics with both rapid kinetics and sustained target engagement, with broad implications for cancer immunotherapy, antiviral therapy, and beyond.

 

 

 

The post High-Throughput Platform for Fast-Acting Covalent Protein Therapies appeared first on GEN – Genetic Engineering and Biotechnology News.

Medtech OEMs face a rare but closing window of opportunity

This is a manufacturing decision you can’t defer in 2026. Mark Freitas, Alvarez & Marsal Private-equity-backed CDMO platforms are aging into exits. OEMs who know what they want will move first. The 2022-2024 structural reset is over and the financing gap is narrowing. The sector has emerged from a period of value depression and as…

The post Medtech OEMs face a rare but closing window of opportunity appeared first on Medical Design and Outsourcing.

Zeus adds catheter components to Chamfr marketplace

NEWS RELEASE: Zeus expands access to catheter components through Chamfr marketplace Over 100 Zeus liner and heat shrink components will now be available to engineers through Chamfr’s online marketplace to accelerate medical device development. ORANGEBURG, S.C. — Zeus, a global leader in advanced polymer solutions and catheter manufacturing, announced a partnership with Chamfr to make…

The post Zeus adds catheter components to Chamfr marketplace appeared first on Medical Design and Outsourcing.

Sovato’s new CEO explains the plan to scale telesurgery and take it worldwide

Now leading Sovato as the telesurgery software startup’s CEO, former Intuitive EVP and Chief Digital Officer Brian Miller sees a big opportunity to realize the full potential of remote medical procedures. In a Medical Design & Outsourcing interview ahead of the announcement that he’s joined Sovato, Miller — who joined Sovato co-founder Yulun Wang’s Computer…

The post Sovato’s new CEO explains the plan to scale telesurgery and take it worldwide appeared first on Medical Design and Outsourcing.

Bodycote plans to open a new heat treatment facility in Mexico

Bodycote plans to open a new heat treatment facility near Monterrey in Apodaca, Mexico, this year to increase local processing capacity and improve regional support as manufacturing activity continues to grow. London-based Bodycote provides heat treatment and specialist thermal processing services for the medical device industry and other industrial sectors. The planned facility in Apodaca…

The post Bodycote plans to open a new heat treatment facility in Mexico appeared first on Medical Design and Outsourcing.