“Animal models have been a workhorse for the industry for decades,” said Jan Lichtenberg, CEO of InSphero AG. “But they are not human, and we are developing drugs for humans.”

This simple truth is now driving a profound shift in preclinical science. Traditional models often fail to capture the nuances of human biology, metabolism or immune response. As precision medicine and advanced therapies, such as cell and gene therapies, gain ground the need for systems that reflect human biology has become urgent.

Microphysiological systems (MPS), engineered platforms that combine living human cells with microfabricated environments, are offering a solution. These models mimic the function of tissues and organs, allowing scientists to test new drugs under conditions that better reflect the complexity of the human body.

At the recent Open Mic: Next in Health session, Gilles Weder, Head of Research & Business Development in Life Science Technologies at CSEM, framed this transformation as part of a broader megatrend: bioconvergence.

“For a long time, science has been divided into disciplines,” he explained. “Today, we see a transversal, multidisciplinary approach integrating biology, engineering and AI to address current healthcare challenges.”

At CSEM, this intersection is where innovation thrives – combining expertise in microengineering, sensor technology and data science to enable the next generation of human-relevant models.

The shift toward MPS is not simply a technical replacement for animal studies; it’s a rethinking of experimental design itself.

Dominic Hoepfner, who leads the Functional Genomics Group at Novartis Biomedical Research, described this evolution:

“It’s not about recreating an entire organ or immune system in a dish. The key is to be as complex as needed, but as simple as possible.”

That pragmatic philosophy is now shaping how researchers define the “context of use” for in vitro models – balancing biological relevance with scalability and practicality.

Meanwhile, Annie Moisan, Discovery Area Leader for Nephrology at Roche, emphasized that new omics data and stem cell technologies are making human-first drug discovery possible:

“We used to rely on animal models to interpret disease. Now, we start with human data – genetics, transcriptomics, proteomics, etc. – and build from there. It’s a paradigm shift.”

Despite the promise of organoids and organ-on-chip technologies, the path to widespread adoption remains challenging. These systems can be costly and complex, with issues around reproducibility, cell sourcing and throughput.

Automation and digital tools are increasingly stepping in to fill that gap. Robotics can standardize workflows, while AI algorithms can analyze vast datasets to identify meaningful biological patterns or predict compatibility between cell types.

As Hoepfner noted, “Robotics and data automation are making it possible to scale in vitro systems in ways animal testing never could. And AI is helping us make sense of the enormous amount of data generated.”

As the science advances, regulatory frameworks are beginning to catch up. Agencies in Europe and the U.S. have started to recognize the potential of microphysiological systems as valid tools for safety and efficacy testing.

This shift could have far-reaching implications for the pharmaceutical industry – reducing reliance on animal testing, accelerating timelines and improving translatability from bench to bedside.

Switzerland has become a fertile ground for this convergence of biology and technology. Organizations like CSEM, alongside startups such as InSphero, and global pharma leaders Roche and Novartis, are creating a collaborative ecosystem that blends academic innovation with industrial scalability.

As Lichtenberg summarized, “When we start with human models from day one, we can make better decisions, faster. It’s the key to more efficient and successful science.”

The momentum behind human-relevant preclinical models is unmistakable. The combination of bioconvergence, digital transformation and regulatory openness is paving the way for safer, faster and more ethical drug discovery.

This shift is not just about replacing animal testing; it’s about reshaping how we understand and translate human biology.

Please note: This article was based on discussion during the recent Open Mic: Next in Health event held on November 10, 2025, titled “Paving the way for human science in preclinical testing”.

To learn more about this event series, register for our next edition and sign up for our newsletter, click here.

ALIS Transformer – an AI-powered software that automates ICD-10 medical coding, ensuring efficient, secure, and compliant ambulant billing. The solution ensures efficient, secure, and compliant medical coding while supporting hospitals in cost savings and operational efficiency during the transition to TARDOC and Flat-rate tariffs. It integrates AI-driven coding, explainability, data privacy and user-centric workflow design.

AmbuCody – an AI-powered ICD-10 code prediction for Switzerland’s new ambulatory TARDOC and flat-rate billing system. The solution requires no training and can be used out of the box to accurately code ambulatory cases. Each prediction includes a confidence score showing how certain the model is, along with a detailed explanation of why it arrived at the predicted code.

KODiQ is an automated coding for outpatient tariffs with diagnosis code. The solution receives ALIS documents via file interface or other interface compliant with ALIS standards. The solution first applies deterministic rule-based logic according to the coding rules. In a second step, an ML-enhanced logic is used to determine the ICD-10 code. All required catalog data (ICD-10-GM, LKAAT, TARDOC, outpatient flat rates) and ML classifier are contained in the system. Coders and Health Care Service Managers can view the cases via the Web UI and train the classifier by reporting ICD-10 codes. Administrators can make configuration settings and call the REST API with additional functions.

Tar.ai is a smart pre-billing validation layer that ensures coding and ICD-10 diagnosis accuracy and compliance under the 2026 TARDOC reform. This AI platform automatically detects missing, inconsistent, or incorrect ICD-10/LKAAT codes, suggests corrections, flags risky billing patterns, and highlights cases requiring human review with confidence scores – serving as a pre-billing validation layer.

CareBoost brings AI-powered scanning and documentation to the bedside, freeing time for what matters most: safe, effective care. The solution links every action and material directly to the patient and therefore ensures quality through full traceability. Nurses spend less time on administration, while hospitals gain efficiency in their supply chain management and billing processes.

A common phrase in AI is that it needs “data, data, data.” But sheer volume is not the answer. What determines the usefulness of AI in oncology is not just how much data we have, but how it is generated, structured and applied. Even a small quality gap in the data – or missing data points – can have outsized effects on outcomes. Poorly contextualized or incomplete records can send algorithms down the wrong path, undermining the very purpose of using AI in patient care.

In practice, this means paying attention to the full process: how data is captured, the standards guiding its collection, and the purpose for which it was originally gathered. The raw quantity of information is far less important than its reliability and the integrity of the methods behind it.

In clinical trials, data quality is carefully managed through protocols. But in everyday patient care, data is often fragmented, inconsistently recorded, or scattered across systems that cannot easily communicate with one another. In such cases, any AI tool built on top of this foundation risks amplifying uncertainty rather than clarifying it.

The key lies in improving how data is captured in routine settings. Without this foundation, even the most sophisticated AI model cannot deliver meaningful or reproducible insights.

The tools available for generating biological data are advancing rapidly. RNA sequencing, single-cell analysis and other technologies can produce extraordinary details about a patient’s cancer. But the challenge remains: how to translate that complexity into decisions that matter for the individual. More data does not automatically mean better decisions – it needs to be contextualized, explained and linked to actionable options.

This is where explainability becomes central. If clinicians are to trust AI tools, they must not only deliver accurate outputs but also make it possible to understand why a particular conclusion or recommendation was reached. Transparent, explainable models build confidence and make adoption far more likely.

The uptake of AI varies significantly across medical specialties. Radiology and radiotherapy are ahead of the curve, helped by standardized imaging formats and mature tools for automated image analysis. By contrast, fields such as molecular pathology are only beginning to experiment with AI-driven methods. This uneven progress reflects both technical readiness and the complexity of implementing solutions in different areas of cancer care.

Rather than expecting one “super model” to manage every dimension of oncology, the most realistic approach is a suite of specialized tools that serve particular functions –for example, tools for imaging, genomics or decision support – that can progressively be integrated into broader workflows.

To realize the full promise of AI, healthcare systems will need to rethink how data is collected and reused. Consent processes must allow patients to contribute their data not only for immediate treatment, but also for future research and secondary applications. Hospitals will need infrastructure that enables secure, interoperable and scalable data sharing, while ensuring compliance with ethical and regulatory frameworks.

Anonymization and de-identification techniques will play an important role, allowing valuable datasets to be repurposed without compromising patient privacy. By designing for reuse from the outset, healthcare systems can unlock far greater value from the data already being generated.

Beyond research, some of the most immediate opportunities for AI lie in easing the burden on clinical teams and supporting decisions. For example: 

These kinds of use cases, focused on augmenting rather than replacing human expertise, are likely to gain traction first.

Despite the progress, several barriers continue to slow adoption. Data availability and quality remain uneven. Many models still lack sufficient performance for clinical use. And the “black box” nature of some AI systems raises concerns about explainability and accountability. On top of this, regulatory pathways are evolving, and healthcare providers face the challenge of investing in infrastructure and skilled personnel to implement solutions safely.

Overcoming these hurdles will require collaboration across startups, hospitals, regulators and pharmaceutical companies. Education will also be vital: clinicians must be trained not just in how to use AI tools, but in how to evaluate them critically and select the right tool for the right context.

Ultimately, the promise of AI in oncology is not only about accelerating discovery, but also about transforming the patient’s journey.

These perspectives point to a future where data works harder for patients, caregivers and clinicians alike. Realizing it will take persistence, trust and cross-sector collaboration – but the impact could be profound.

This article was inspired by discussions at DayOne’s Open Mic: Next in Health event on “The role of healthtech and AI in cancer treatment.”

Six outstanding teams were selected to move from the idea to MVP stage, each offering a unique approach to data capture, usability and interoperability through openEHR:

Anamedi improves data capture and quality through ambient AI in clinical settings, while reducing clinicians’ manual documentation time. Its solution captures doctor-patient conversations using speech-to-text, fine-tuned for Swiss German and medical terminology, and can be deployed in hospitals, GP offices and psychotherapy practices. Specialized models ensure accurate transcription and terminology across the field. It is compatible with most common healthcare IT standards, including openEHR.

This is an initiative of the Institute for Medical Informatics at the Bern University of Applied Sciences (BFH). The team is examining whether structured and intuitive digital symptom documentation by patients could lead to a more complete and reliable patient history, which healthcare professionals can assess during and in preparation for consultations. The project involves designing a conceptual mobile application and openEHR modelling of symptom data and initially focuses on the capture of pain symptoms.

This is a comprehensive openEHR-based clinical applications portfolio that scales across different healthcare environments and professional groups. Lifecare Clinical Modules empower healthcare professionals with unified, modular software built on open standards. Clinical data is stored in a vendor-neutral openEHR format, enabling seamless interoperability, reuse and integration across systems so that clinicians can act on patient data efficiently.

These are digital assessments of movement impairment to enhance data quality, increase data density, and automate workflows. Building upon observation of clinical workflows, Healthcore is developing frontends that guide the assessor through the data collection process. They incorporate advanced biomechanical modelling tools that enable accurate kinematic analysis, and display the results on data dashboards in near-time.

Automating clinical score calculation using EHR data to reduce errors, save time, and improve diagnostics. RADICAL automates diagnostic score calculations within hospital workflows using openEHR standards. It also reduces manual effort, improves accuracy, and enables structured, interoperable data capture, laying the foundation for scalable, machine learning-ready diagnostics algorithms.

This is a webapp by ALPINA+SANA for nutritionists to view patient meal data, stored in openEHR format; data comes from an AI-based food tracking system. The AI-powered food tracking replaces inaccurate, manual “plate protocols” with automated, next-day nutrition data in OpenEHR format – giving nutritionists a time-saving, precise overview of all patients, including those not yet flagged for malnutrition.

Clinical research is essential for medical progress – but it comes at a steep environmental cost. If the global healthcare sector were a country, it would rank as the fifth-largest greenhouse gas emitter, accounting for roughly 4–5% of worldwide emissions.

Within that, the pharmaceutical and biotech industry produces hundreds of millions of tons of CO₂ annually. A single late-stage clinical trial has an average carbon footprint on the order of 78 tons CO₂-equivalent (the range can top 100 tons). These emissions stem from energy-intensive lab work, global trial logistics, the manufacture and shipping of drugs and materials, and extensive travel by both patients and staff.

In short, today’s clinical trials literally carry the weight of a small country’s carbon output. Faced with this reality, the life sciences community is rallying to “rethink how we design and run our trials” in a more climate-conscious way.

At a recent DayOne Open Mic panel on the topic, experts from across the industry explored how digital innovation can help square the need for rigorous clinical research with urgent sustainability goals. The consensus: smarter use of digital tools – from remote trial technologies to data-driven efficiency measures – is already yielding win-win solutions that make trials greener and better. As Juergen Wieland, Development Sustainability Lead at Novartis, put it, “the biggest incentive to work on sustainability is our intrinsic need to ensure planetary and human health are thought together. There is just no healthy human being on a dead planet.”

One of the clearest opportunities to shrink a trial’s carbon footprint is to reduce the need for travel. Patient and staff travel can comprise the single largest emissions source in a study – an estimated 30–60% of a trial’s CO₂ output comes from participants driving or flying to sites, and from monitors (CRAs) traveling for on-site data checks.

During the COVID-19 pandemic, the industry accelerated the adoption of decentralized clinical trials (DCTs), using digital tools to bring studies to patients instead of always bringing patients to centralized sites. “Telemedicine allowing patients to participate from home reduces a lot of travel – and it’s good for patients, especially those with limited mobility,” noted Linus Kao, CEO and founder of Skyvor Medical. Digital health technologies like secure video visits, remote monitoring devices, and direct-to-patient drug shipments can replace many in-person visits. The environmental benefit is intuitive: fewer car and airplane trips mean fewer emissions.

Regulators are now on board as well. The U.S. FDA and the European Medicines Agency have recently issued guidance to facilitate decentralized trial elements in study protocols. This regulatory support, combined with rapid advances in telehealth and wearable sensors, has enabled sponsors to rethink trial design with an eye to both patient convenience and sustainability. For example, electronic informed consent and at-home nurse visits (areas explicitly encouraged by the EMA’s 2022 recommendation) mean that certain trial procedures can be done in a patient’s living room instead of a distant hospital. Each avoided trip not only cuts carbon; it also makes trial participation less burdensome, potentially improving recruitment and retention of volunteers.

Kao emphasized that digital decentralized tools have matured quickly: “During COVID we often said it was slow to adopt digital technologies, but a lot has changed. The FDA and EMA put out clear guidance by 2022 on using digital health tech for decentralized trials, and how that can reduce the carbon footprint.” According to Kao, travel and logistics together account for as much as 60–75% of a typical trial’s emissions, so even partial virtualization of a study can yield significant reductions. For instance, a remote telemedicine visit or home sensor can substitute for an on-site appointment that might have required a patient (and possibly a caregiver) to drive several hours. Beyond cutting carbon, these approaches often make trials more inclusive and patient-friendly, enabling people who live far from research centers to participate.

However, the panelists also cautioned that decentralization is not a panacea for all trials. Implementing a full suite of remote technologies can add complexity. Smaller biotech companies running lean early-phase trials may lack the budget and bandwidth to manage multiple new digital systems for e-consent, home nursing, remote data capture, etc. In those cases, the priority is using targeted digital strategies to streamline the trial process rather than force a fully virtual model. “For the smaller-scale trials, speed is the key,” Kao explained. “Any digital solutions that can reduce the timeline will also reduce a lot of carbon footprint.”

In practice, that might mean using data analytics to optimize site selection and patient recruitment – enrolling the right patients faster so that fewer clinic visits and less idle trial time accumulate. Or it might mean employing an all-in-one digital platform (instead of a patchwork of tools) so that trial teams can work more efficiently. The underlying principle is that a faster trial is a greener trial: every day shaved off the timeline is one less day of energy consumed by trial sites and equipment, one less day of data servers running, and often one less opportunity for material waste.

Beyond travel, trial logistics and material waste are another major contributor to the environmental footprint. Clinical trials involve moving a lot of physical goods – from investigative drugs and lab kits shipped around the world, to paper documents, to the disposable supplies used in administering treatments and tests. Until recently, these processes were rife with inefficiencies. Wieland recounted how a few years ago, Novartis examined its global clinical supply operations and discovered startling waste in the system: overproduction of trial drug doses, oversized shipments, and large volumes of unused lab kits that would ultimately be thrown away. Much of this stemmed from well-intentioned caution – for example, manufacturing more investigational product than needed “just in case,” or sending every site a full batch of pre-labeled sample collection kits for every patient “just in case” they might be used. The result, however, was mountains of expired pills and unused materials.

Here is where digital tools and better data have made a profound impact. By implementing advanced supply chain management software, analytics, and forecasting models, Novartis was able to bring unprecedented transparency and control to its trial operations. Wieland described how connecting real-time data on patient enrollment, drug inventory, and site needs allowed the company’s teams to optimize shipments and production in ways previously not possible. “We saw a lot of opportunities to first bring transparency into the demand and inventory levels, and [by] reducing the total volume of drug for clinical use we cut technical demand by more than two-thirds in a few years’ time,” he said. In practice, that means far less medication being manufactured only to never be administered – saving energy, resources, and cost.

Likewise, Novartis and others streamlined how often and how full their shipments travel. With better planning, consolidated shipments became the norm: sending larger batched deliveries rather than many small parcels. Over about two years, Novartis managed to reduce its annual clinical trial shipments by more than 50% (from around 86,000 down to under half that number). Fewer shipments translate directly to lower transport emissions, not to mention financial savings. As Wieland noted, sustainability efforts often reveal hidden inefficiencies. When you fix them, “we obviously see a lot of cost savings linked to that. We were able to make the business case in the company.” In fact, one initiative – switching from single-use thermal packaging to reusable insulated shipping boxes – has already been used in over 100,000 shipments, avoiding piles of Styrofoam waste and saving tens of millions of dollars.

Waste reduction is a clear area of win-win outcomes. A leaner trial supply chain not only cuts emissions and waste disposal costs but also makes trials faster and more reliable. The panel discussed creative programs to repurpose unavoidable surplus – for example, donating unopened expired kits for veterinary or training use – but the ultimate goal is to generate less excess in the first place.

Here too, cross-industry collaboration and standards can help. Wieland mentioned the idea of standardizing lab kit components (like blood draw tubes) across sponsors, so that a site isn’t stuck discarding an entire custom kit just because one tube type expired. If all companies draw blood with, say, a common 10 ml tube, those supplies could be pooled or shared rather than wasted per trial. Such coordination requires industry agreement, but it’s the kind of systemic change that digital inventory tracking and data sharing platforms can enable soon.

Crucially, what makes these improvements possible is the data-driven visibility that digital tools provide. It’s difficult to eliminate waste you can’t see. By digitizing inventory management and using sensors or RFID tracking on shipments, trial managers now have granular data on where materials are, how they’re used, and where the bottlenecks or waste points occur. Those insights allow for continuous optimization. And success begets success: once teams see that smarter logistics can dramatically cut costs and carbon, it creates momentum to tackle other areas (for instance, the 100,000+ biological sample shipments that large trials generate, which involve refrigerated transport and lots of packaging). In Wieland’s experience, “the more we make it easy and attractive – and even cost-saving – to choose the sustainable option, the faster we can scale up these solutions.” Sustainability doesn’t have to mean sacrifice; often it means embracing operational excellence, doing more with less.

Digital technology’s greatest contribution might be its power to illuminate problems and unlock human ingenuity. “If you put data in the hands of researchers, they’re going to use it,” said James Connelly, CEO of My Green Lab, underlining that scientists by nature respond to evidence. Historically, many sustainability challenges in R&D were “invisible” or not measured – think of all the ultra-cold freezers humming in laboratories or the mountains of single-use plastics being discarded.

Now, new tools are making the environmental impact of research measurable and transparent, which is spurring action. Connelly’s organization, for instance, developed an Impact Calculator and Certification program for labs that allows scientists to input their equipment and practices and get a quantified readout of their energy, water and waste footprint. When AstraZeneca rolled this out to over 100 research labs last year, the results were eye-opening: simple changes like raising ultra-low freezer temps from -80°C to -70°C (without compromising samples) and closing fume hood sashes when not in use translated into a 5× return on investment in energy savings within one year. In Connelly’s words, “a green lab isn’t a more complicated lab – it’s just a more efficient operation. It’s about pursuing operational excellence…running it as efficiently as possible, and then you have a better lab.”

This ethos applies directly to clinical trials. Many trials rely on networks of diagnostic labs and data centers that consume significant resources. By monitoring and optimizing those facilities with digital solutions, companies can drive down the footprint of each test or data transaction. Cloud-based platforms now allow R&D teams to model different scenarios – for example, simulating how switching to renewable energy at data centers or consolidating lab analyses in fewer locations might reduce emissions – and make decisions informed by that analysis. Wearable sensors and remote data collection can also cut down on ancillary resource use; for instance, continuous monitoring might catch issues earlier and prevent unnecessary procedures or hospital visits.

Another exciting frontier is the use of AI and computational modelling to redesign how trials are conducted. Advanced analytics can sift through troves of data to identify the most efficient trial designs, optimal site locations, or even predict enrollment challenges before they happen. Wieland mentioned that Novartis is investing in AI-driven tools to improve site and patient selection – speeding up recruitment and ensuring trial populations are representative without endless global site expansions. More ambitiously, machine learning could help create “digital twins” of trials – virtual simulations of the trial process to experiment with changes in real time. While true end-to-end virtual trials remain a future vision (and current regulations still require actual patients and control arms), AI is already helping in narrower scopes, such as analyzing historical data to replace or reduce placebo arms. If a company can use existing patient data to avoid enrolling 100 extra people on placebo, that’s 100 people who don’t need to travel, and a leaner trial protocol overall.

The panel agreed that digital innovation and sustainability go hand in hand. Often, the greener approach is simply the more modern, efficient approach. “Doing better science often is more efficient,” Connelly noted. Tools that improve data quality or automate manual processes not only save time and money – they prevent waste and repetition. Electronic data capture, remote monitoring, AI-driven data analysis: all reduce the need for paper, redundant tests, physical storage and archiving. And importantly, they generate metrics. “That which gets measured gets managed, and eventually improved,” as they say.

A recurring theme in the discussion was that no single company or stakeholder can crack sustainable trials alone – nor do they need to. Cross-industry collaboration is accelerating progress by pooling knowledge and aligning standards. Wieland highlighted that major pharma players have been joining forces in pre-competitive initiatives like the Sustainable Healthcare Coalition and the Sustainable Markets Initiative’s health sector task forces. Competitors sit together to share best practices on everything from green clinical supply strategies to sustainable lab frameworks. The Innovative Health Initiative in Europe (a public-private partnership) is another venue where pharma, biotech startups, academia and regulators pilot new methods with an eye on both innovation and sustainability. These collaborations have already led to tangible outcomes – for example, the Low Carbon Clinical Trial Guide developed through the Sustainable Healthcare Coalition provides a common methodology for measuring a trial’s footprint and identifying “hotspots,” which companies can then target for improvement.

Regulators, too, are increasingly seen as partners in this mission. Not long ago, well-intended health regulations sometimes inadvertently hampered sustainability – such as rules that all drug packaging include paper leaflets, resulting in millions of printed pages that most patients never read. Now there’s movement to modernize those requirements (e-leaflets, anyone?) in line with environmental goals. Countries like Japan and Singapore have led the way by allowing electronic drug information via QR codes years ago, and Europe is testing similar approaches. More broadly, policy drivers are emerging that will reinforce corporate climate action. In the EU, for instance, new regulations taking effect in 2026 will require any environmental claims by companies to be backed up with hard data and third-party verification. This kind of policy shift will help separate real progress from greenwashing, and it underscores the value of the measurement tools and transparency the panelists championed.

Perhaps the most important ingredient is culture. Sustainability must become ingrained in the way trial teams operate day to day. One encouraging insight shared was that much of Novartis’s green trials effort started bottom-up – passionate employees across different departments volunteering ideas and pushing initiatives, long before there was a top-down mandate. Once small pilot successes were achieved, leadership support (and funding) followed, creating a positive feedback loop. Empowering those grassroots efforts with data and resources can turn a few isolated eco-champions into an organization-wide movement. And when leadership further ties sustainability to core business objectives (for example, including climate targets in management KPIs or linking cost savings to green projects), it cements the idea that “planet-friendly” also means “patient-friendly” and “business-friendly.”

Looking ahead, the consensus is that climate-conscious trial design will become the new normal. The health innovation ecosystem is uniquely positioned to lead on this front. “This industry has a culture of innovation and a mission of improving health,” Connelly observed. “We’re used to making long-term investments for society’s benefit. One of the most important contributions pharma can make now is to show that we can reach zero carbon while still delivering amazing medicines.” Achieving net-zero clinical trials will not happen overnight, but the momentum is building. Each success – a faster trial timeline, a reduction in waste, a new digital platform that eliminates unnecessary travel – is both a climate win and a proof point that it can be done.

The call to action for the sector is clear: step up and lead. As Wieland urged, “Don’t wait for your boss or the others. Find what contribution you can bring to the table.” Whether you’re a big pharma executive, a startup founder, a research nurse, or a regulator, there are practical steps you can take today: implement that digital tool, question that wasteful process, share your findings with the community, and demand higher standards where they matter. The technology and know-how to make trials more sustainable are advancing rapidly – but it will require collective will to implement them at scale.

In the end, climate action in clinical trials isn’t just about carbon accounting; it’s about rethinking innovation to be smarter and more responsible. As the panel’s discussion demonstrated, doing the right thing for the planet often aligns with doing the right thing for patients and science. Decentralized and data-driven approaches are already enhancing trial diversity and patient centricity. Efficiency measures are already cutting costs and speeding deliveries of new therapies. The greener path is truly the better path for healthcare.

DayOne, as an ecosystem catalyst, is committed to driving this conversation and supporting solutions at the intersection of healthtech and clinical trials. The growing movement to green our clinical trials reflects a broader transformation in healthcare – one where climate consciousness is embedded in innovation. By harnessing digital tools and collaborative ingenuity, we can ensure that the trials powering tomorrow’s cures leave a lighter footprint on the world. The challenge is urgent, but the opportunity is immense: to heal patients and protect the planet, one smart trial at a time.

Please note: This article was developed from the proceedings of the Open Mic: Next in Health event held on May 26, 2025, “Digital tools for sustainability in clinical trials.”

To learn more about this event series, register for our next edition, and sign up for our newsletter, check out the Open Mic page.

This granular understanding is pushing the field beyond treatment selection into disease prevention, early detection and continuous patient monitoring—forming the foundation for a more proactive, precise and patient-centric model of care. 

Innovation in precision medicine: How industry leaders are shaping the biomarker landscape 

Biomarker discovery is no longer confined to academic research or traditional lab settings—it is being accelerated by industry leaders using cutting-edge technologies, agile R&D models and cross-sector collaboration. Two companies, Scailyte and Roche Diagnostics, illustrate how innovation is being redefined across the biomarker value chain. 

Scailyte focuses on single-cell omics combined with Artificial Intelligence (AI) to uncover previously undetectable biomarkers. By analyzing the behavior of individual cells, their platform captures a more detailed picture of disease heterogeneity—one that can reveal subtle signals overlooked by bulk analysis. Their use of AI in biomarker discovery enables early detection and precise patient stratification by processing complex, high-dimensional data to identify patterns linked to disease states. 

Roche Diagnostics is approaching innovation from another angle—investing in experimental platforms for early detection. With a focus on diseases where validated biomarkers are still lacking, such as neurodegenerative and inflammatory conditions, the company is building tools that enable faster, more sensitive detection at earlier stages. These efforts are being developed within a dedicated innovation ‘think tank’ environment to enable operations with startup-like speed and flexibility. 

Digital biomarkers are also gaining traction as a complementary innovation, especially for chronic and neurological conditions. By collecting real-time physiological data via wearable devices and sensors, researchers are beginning to explore how these digital signals can augment molecular biomarkers, improve disease monitoring and support continuous, real-world assessment of patient health. 

From Parkinson’s disease and inflammatory bowel disease (IBD) to endometriosis and cancer prognosis, these innovations are already being applied to high-burden, high-complexity conditions. While their technologies differ, both startups and pharma agree: the key to success lies in partnership. Whether through collaborations with academic labs, licensing IP from small ventures or co-developing validation studies, progress depends on breaking silos. 

Bridging the gap from scientific discovery to real-world implementation 

While scientific advances in biomarker discovery and precision diagnostics are accelerating, their adoption in everyday clinical practice is lagging. Many of the most promising technologies remain stuck in the translational gap, a space where regulatory hurdles, outdated frameworks and real-world constraints slow or prevent implementation. 

One of the biggest challenges lies in regulatory alignment. As precision diagnostics become more complex, integrating AI models, multi-omic data or digital biomarkers, they often do not easily fit into existing approval pathways. Furthermore, reimbursement structures and business models are still optimized for traditional, one-size-fits-all care, rather than personalized care pathways informed by companion diagnostics. 

Clinical trial design is another limiting factor. Standard models often fail to capture the granularity needed to validate new biomarker tools or reflect the diversity of real-world patient populations. This disconnection between scientific potential and clinical validation creates friction for both innovators and regulators, delays benefit for patients, and continues to limit the clinical implementation of biomarkers in real-world settings. 

A related concern is data transparency and trust. As AI enters the biomarker space, questions around explainability and evidence become central. Clinicians need confidence in how predictions are made, and regulators require robust validation. Companies like Scailyte are addressing this by using supervised learning approaches and explainable AI models to ensure that biomarker-driven insights can be traced and understood, not just statistically inferred. 

One way to build that trust is through the earlier integration of diagnostics and companion tools. By embedding biomarker-based decision-making earlier in the care pathway, before disease is advanced or treatment options narrow, healthcare systems can generate clearer evidence of clinical value, support regulatory confidence and move toward more proactive, cost-effective care. 

Unlocking precision medicine at scale 

Scaling what is scientifically possible into what is clinically routine remains one of the greatest—and most urgent—challenges in precision medicine. As technologies advance, the question is no longer whether they work, rather whether they can work at scale. From breakthrough biomarker platforms to real-time patient monitoring, the challenge is ensuring that these innovations are equitably accessible, sustainably reimbursed and systemically adopted. 

A major part of the equation lies in restructuring incentives. Current healthcare models often reward volume over value, and diagnostics are frequently undervalued in reimbursement schemes despite their central role in guiding treatment. For precision medicine to scale, payers and regulators need to recognize the economic and clinical value of early detection, patient stratification and treatment response prediction and reflect that in policy and funding frameworks. 

Equitable access remains a persistent gap. Precision approaches risk deepening existing disparities if tools and technologies are only available in specialized or well-funded settings. Broader uptake will depend not only on affordability but also on system readiness: clinician training, workflow integration and digital infrastructure that can support data-driven care. 

The path forward requires coordinated effort across industry, academia, regulators and health systems. It calls for shared investment in biomarker validation, streamlined regulatory pathways and clearer incentives for adoption. Just as importantly, it demands a shift in mindset—from viewing diagnostics as ancillary to recognizing them as foundational to treatment success. 

Please note: This article was developed from the proceedings of the Open Mic: Next in Health event held on March 24, 2025, “Innovations in precision medicine and biomarker development.” To learn more about this event series, register for our next edition, and sign up for our newsletter, check out the Open Mic page.